Learning Video Object Segmentation from Unlabeled Videos (CVPR2020)
We propose a new method for video object segmentation (VOS) that addresses object pattern learning from unlabeled videos, unlike most existing methods which rely heavily on extensive annotated data. We introduce a unified unsupervised/weakly supervised learning framework, called MuG, that comprehensively captures intrinsic properties of VOS at multiple granularities. Our approach can help advance understanding of visual patterns in VOS and significantly reduce annotation burden. With a carefully-designed architecture and strong representation learning ability, our learned model can be applied to diverse VOS settings, including object-level zero-shot VOS, instance-level zero-shot VOS, and one-shot VOS. Experiments demonstrate promising performance in these settings, as well as the potential of MuG in leveraging unlabeled data to further improve the segmentation accuracy.READ FULL TEXT VIEW PDF
Conventional few-shot object segmentation methods learn object segmentat...
Significant progress has been made recently in developing few-shot objec...
In this paper, we present a novel Motion-Attentive Transition Network
Visual cognition of primates is superior to that of artificial neural
This work proposes a novel attentive graph neural network (AGNN) for
How to make a segmentation model to efficiently adapt to a specific vide...
We present a new method to learn video representations from large-scale
Learning Video Object Segmentation from Unlabeled Videos (CVPR2020)
Video object segmentation (VOS) has two common settings, zero-shot and one-shot. Zero-shot VOS (Z-VOS)111Some conventions [36, 60] also use ‘unsupervised VOS’ and ‘semi-supervised VOS’ to name the Z-VOS and O-VOS settings . In this work, for notational clarity, the terms ‘supervised’, ‘weakly supervised’ and ‘unsupervised’ are only used to address the different learning paradigms. is to automatically segment out the primary foreground objects, without any test-time human supervision; whereas one-shot VOS (O-VOS) focuses on extracting the human determined foreground objects, typically assuming the first-frame annotations are given ahead inference 1. Current leading methods for both Z-VOS and O-VOS are superviseddeep learning models that require extensive amounts of elaborately annotated data to improve the performance and avoid over-fitting. However, obtaining pixel-wise segmentation labels is labor-intensive and expensive (Fig. 1 (a)).
It is thus attractive to design VOS models that can learn from unlabeled videos. With this aim in mind, we develop a unified, unsupervised/weakly supervised VOS method that mines multi-granularity cues to facilitate video object pattern learning (Fig. 1 (b)). This allows us to take advantage of nearly infinite amounts of video data. Below we give a more formal description of our problem setup and main idea.
Problem Setup and Main Idea. Let and denote the input video space and output VOS space, respectively. Deep learning based VOS solutions seek to learn a differentiable, ideal video-to-segment mapping . To approximate , recent leading VOS models typically work in a supervised learning manner, requiring input samples and their desired outputs , where . In contrast, we address the problem in settings with much less supervision: (1) the unsupervised case, when we only have samples drawn from , , and want to approximate , and (2) the weakly supervised learning setting, in which we have annotations for , which is a related output domain for which obtaining annotations is easier than , and we approximate using samples from .
The standard way of evaluating learning outcomes follows an empirical risk/loss minimization formulation :
where denotes the hypothesis (solution) space, and
is an error function that evaluates the estimateagainst VOS-related prior knowledge . To make a good approximation of , current supervised VOS methods directly use the desired output , i.e., , as the prior knowledge, with the price of vast amounts of well-annotated data.
In our method, the prior knowledge
, in the unsupervised learning setting, is built upon several heuristics and intrinsic properties of VOS itself, while in the weakly supervised learning setting, it additionally considers a related, easily-annotated output domain. For example, part of the fore-background knowledge could be from a saliency model  (Fig. 1 (b)), or in a form of CAM maps [73, 76]
from a pre-trained image classifier (i.e., a related image classification domain )222Note that any unsupervised or weakly supervised object segmentation/saliency model can be used; saliency , and CAM [73, 76] are just chosen due to their popularity and relatively high performance.. Exploring VOS in an unsupervised or weakly supervised setting is appealing not only because it alleviates the annotation burden of , but also because it inspires an in-depth understanding of the nature of VOS by exploring . Specifically, we analyze several different types of cues at multiple granularities, which are crucial for video object pattern modeling:
At the short-term granularity, we impose the local consistency within the representations of short video clips, to describe the continuous and coherent visual patterns within a few seconds.
At the long-range granularity, we address semantic correspondence among distant frames, which makes the cross-frame representations robust to local occlusions, appearance variations and shape deformations.
At the whole-video granularity, we encourage the video representation to capture global and compact video content, by learning to aggregate multi-frame information and be discriminative to other videos’ representations.
All these constraints are formulated under a unified, multi-granularity VOS (MuG) framework, which is fully differentiable and allows unsupervised/weakly supervised video object pattern learning, from unlabeled videos. Our extensive experiments over various VOS settings, i.e., object-level Z-VOS, instance-level Z-VOS, and O-VOS, show that MuG outperforms other unsupervised and weakly supervised methods by a large margin, and continuously improves its performance with more unlabeled data.
Z-VOS. As there is no indication for objects to be segmented, conventional ZVOS methods resorted to certain heuristics, such as saliency [60, 62, 61, 7], object proposals [19, 37, 24], and discriminative motion patterns [31, 10, 33]. Recent advances have been driven by deep learning techniques. Various effective networks have been explored, from some early, relatively simple architectures, such as recurrent network [45, 32, 63], and two-stream network [6, 49, 77], to recent, more powerful designs, such as teacher-student adaption , neural co-attention 
and graph neural network[58, 68].
O-VOS. As the annotations for the first frame are assumed available at the test phase, O-VOS focuses on how to accurately propagate the initial labels to subsequent frames. Traditional methods typically used optical flow based propagation strategy [29, 9, 59, 28]. Now, deep learning based solutions become the main stream, which can be broadly classified into three categories, i.e., online learning, propagation and matching based methods. Online learning based methods [3, 55, 35] fine-tune the segmentation network for each test video on the first-frame annotations. Propagation based methods [18, 67, 71] rely on the segments of the previous frames and work in a frame-by-frame manner. Matching based methods [66, 54, 27] segment each frame according to its correspondence/matching relation to the first frame.
Typically, current deep learning based VOS solutions, under either Z-VOS or O-VOS setting, are trained using a large amount of elaborately annotated data for supervised learning. In contrast, the proposed method trains a VOS network from scratch using unlabeled videos. This is essential for understanding how visual recognition works in VOS and for narrowing down the annotation budget.
Learning VOS from unlabeled videos is an essential, yet rarely touched avenue. Among a few efforts,  represents an early attempt in this direction, which uses a modified, purely unsupervised version of  to generate proxy masks as pseudo annotations. With a similar spirit, some methods use heuristic segmentation masks  or weakly supervised location maps  as supervisory signals. With a broader view, some works [47, 11, 74] capitalized on untrimmed videos tagged with semantic labels. In addition to increased annotation efforts, they are hard to handle such a class-agnostic VOS setting. Recently, self-supervised video learning has been applied for O-VOS [56, 65], which imposes the learned features to capture certain constraints on local coherence, such as cross-frame color consistency  and temporal cycle-correspondence .
Our method is distinctive for two aspects. First, it explores various intrinsic properties of videos as well as class-agnostic fore-background knowledge in a unified, multi-granularity framework, bringing a more comprehensive understanding of visual patterns in VOS. Second, it shows strong video object representation learning ability and, for the first time, it is applied to diverse VOS settings after only being trained once. This gives a new glimpse into the connections between the two most influential VOS settings.
For a training video containing frames: , its features are specified as , obtained from a fully convolutional feature extractor : . Four-granularity characteristics are explored to guide the learning of (Fig. 2), described as follows.
Frame Granularity Analysis: Fore-background Knowledge Understanding. As is VOS-aware, basic fore-background knowledge is desired to be encoded. In our method, such knowledge (Fig. 1 (b)) is initially from a background prior based saliency model  (in an unsupervised learning setting), or in a form of CAM maps [73, 76] (in a weakly supervised learning setting).
Formally, for each frame , let us denote its corresponding initial fore-background mask as (i.e
., a binarized saliency or CAM activation map). In our frame granularity analysis, the learning ofis guided by the supervision signals of , i.e., utilizing the intra-frame information to regress :
Here is the cross-entropy loss, and where maps the input single-frame feature into a fore-background prediction map . is implemented by a convolutional layer with sigmoid activation.
Short-Term Granularity Analysis: Intra-Clip Coherence Modeling. Short-term coherence is an essential property in videos, as temporally close frames typically exhibit continuous visual content changes . To capture this property, we apply a forward-backward patch tracking mechanism . It learns by tracking a sampled patch forwards in a few successive frames and then backwards until the start frame, and penalizing the distance between the initial and final backwards tracked positions of that patch.
Formally, given two consecutive frames and , we first crop a patch from and apply on and , separately. Then we get two feature embeddings: and . With a design similar to the classic Siamese tracker , we forward track the patch on the next frame by conducting a cross-correlation operation ‘’ on and :
where is a sigmoid-normalized response map whose size is rescaled into . The new location of in is then inferred according to the peak value on . After obtaining the forward tracked patch in , we backward track to and get a backward tracking response map :
Ideally, the peak of should correspond to the location of in the initial frame . Thus we build a consistency loss that measures the alignment error between the initial and forward-backward tracked positions of :
where is a -dimensional Gaussian-shape map with the same center of
and variance proportional to the size of. As in , the above forward-backward tracking mechanism is extended to a multi-frame setting (Fig. 3). Specifically, after obtaining the forward tracked patch in , is further tracked to the next frame , and a new tracked patch is obtained. Then is reversely tracked to and further to the initial frame , and the local consistency loss in Eq. 5 is computed. Moreover, during training, we first random sample a short video clip consisting of six successive frames. Then we perform above forward-backward tracking based learning strategy over three frames random drawn from the six-frame video clip. With above designs, captures the spatiotemporally local correspondence and is content-discriminative (due to its cross-frame target re-identification nature).
Long-Term Granularity Analysis: Cross-Frame Semantic Matching. In addition to the local consistency among adjacent frames, there also exist strong semantic correlations among distant frames, as frames from the same video typically contain similar content [30, 69]. Capturing this property is essential for , as it makes robust to many challenges, such as appearance variants, shape deformations, object occlusions, etc. To address this issue, we conduct a long-term granularity analysis, which casts cross-frame correspondence learning as a dual-frame semantic matching problem (Fig. 4). Specifically, given a training pair of two disordered frames randomly sampled from , we compute a similarity affinity between their embeddings: by a co-attention operation :
where and are flat matrix formats of and , respectively. ‘softmax’ indicates column-wise softmax normalization. Given the normalized cross-correlation , in line with , we use a small neural network to regress the parameters of a geometric transformation , i.e
., six-degree of freedom (translation, rotation and scale).gives the relations between the spatial coordinates in and considering the corresponding semantic similarity:
where is a 2-D spatial coordinate of , and the corresponding sampling coordinates in . Using , we can warp to . Similarly, we can also compute , i.e., a 2-D warping from to . Let us consider two sampling coordinates and in and , respectively, we introduce a semantic matching loss :
where refers to the image lattice, gives the similarity value between the positions and in and , and determines if the correspondence between and is geometrically consistent. If , ; otherwise .
Video Granularity Analysis: Global and Discriminative Representation Learning. So far, we have used the pairwise cross-frame information in local and long terms to boost the learning of . is also desired to learn a compact and globally discriminative video representation. To achieve this, with a global information aggregation module, we perform a video granularity analysis within an unsupervised video embedding learning framework , which leverages supervision signals from different videos.
Starting with our global information aggregation module, we split into segments of equal durations: . For each segment , we randomly sample a single frame, resulting in a -frame abstract of . reduces the redundancy among successive frames while preserving global information.
With a similar spirit of key-value retrieval networks , for each , we set it as a query and the rest frames as reference. Then we compute the normalized cross-correlation between the query and reference:
where , and ‘’ denotes the concatenation operation. and are flat feature matrices of the query and reference, respectively. Subsequently, is used as a weight matrix for global information summarization:
Our global information aggregation module gathers information from the reference set by a correlation-based feature summarization procedure. For the query frame , we obtain its global information augmented representation by:
During training, the video granularity analysis essentially discriminates between a set of surrogate video classes . Specifically, given training videos, we randomly sample a single frame from each video, leading to training instances: . The core idea is that, for a query frame in the -th video, its global feature embedding is close to the instance from the same -th video, and far from other unrelated instances (from the other videos). We solve this as a binary classification problem via maximum likelihood estimation (MLE). In particular, for , instance should be classified into , while other instances
shouldn’t be. The probability ofbeing recognized as instance is:
where ‘GAP’ stands for global average pooling. Similarly, given , the probability of other instances be recognized as instance is:
Correspondingly, the probability of not being recognized as instance is . The joint probability of being recognized as instance and not being is: , under the assumption that different instances being recognized as are independent.
Then the loss function is defined as the negative log likelihood overquery frames from videos:
Next we will describe the network architecture during the training and inference phases. An appealing advantage of our multi-granularity VOS network is that, after being trained in a unified mode, it can be directly applied to both Z-VOS and O-VOS settings with only slight adaption.
Network Architecture. Our whole module is end-to-end trainable. The video representation space is learned by a fully convolutional network, whose design is inspired by ResNet-50 . In particular, the first four groups of convolutional layers in ResNet are preserved and dilated convolutional layer  is used to maintain enough spatial details as well as ensure a large receptive field, resulting in a 512-channel feature representation x whose spatial dimensions are of an input video frame .
During training, we use a mini-batch of videos and scale all the training frames into pixels. For frame granularity analysis, all the frames access to the supervision signal from the loss in Eq. 2.
For short-term granularity analysis, six successive video frames are first randomly sampled from each training video, resulting a six-frame video clip. For each video clip, we further sample three video frames orderly and randomly crop a patch as . With the feature embedding of , we forward-backward track and get its final backward tracking response map via Eq. 4. For computing the loss in Eq. 5, the Gaussian-shape map is obtained by convolving the center position of with a two-dimension Gaussian map with a kernel width proportional (0.1) to the patch size.
For long-term granularity analysis, after randomly sampling two disordered frames () from a training video , we compute the correlation map by the normalized inner production operation in Eq. 6. For the geometric transformation parameter estimator , it is achieved by two convolutional layers and one linear layer, as in . Then the semantic matching loss in Eq. 8 is computed.
For video granularity analysis, we split each training video into segments, and get the global information augmented representation for each query frame by Eq. 11. Then, we compute the soft-max embedding learning loss using Eq. 14, which leverages supervision signals from the training videos.
Iterative Training by Bootstrapping. As seen in Fig. 1 (b), the fore-background knowledge from the saliency  or CAM [73, 76] is ambiguous and noisy. Inspired by Bootstrapping , we apply an iterative training strategy: after training with the initial fore-background maps, we use our trained model to re-label the training data. With each iteration, the learner bootstraps itself by mining better fore-background knowledge and then leading a better model. Specifically, for each training frame , given the initial fore-background mask and current prediction of the model in -th training iteration, the loss in Eq. 2 in -th iteration is formulated in a bootstrapping format:
where and gives the value in position m. In such a design, the ‘confident’ fore-background knowledge is generated as a convex combination of the initial fore-background information and model prediction .
where s are coefficients: and .
The above designs enable a unified un-/weakly supervised feature learning framework. Once the model is trained, the learned representations can be used for Z-VOS and O-VOS, with slight modifications. In practice, we find that our model can perform well after being trained with 2 iterations; please see §4.2 for related experiments.
Now we detail our inference modes for object-level Z-VOS, instance-level Z-VOS, and O-VOS settings.
Object-Level Z-VOS Setting. For each test frame, object-level Z-VOS aims to predict a binary segmentation mask where the primary foreground objects are separated from the background while the identities of different foreground objects are not distinguished. In the classic VOS setting, since there is no any test-time human intervention, how to discover the primary video objects is the central problem. Considering the fact that interested objects frequently appear throughout the video sequence, we readout the segmentation results from the global information augmented feature r, instead of directly using intra-frame information to predict the fore-background mask (i.e., ). This is achieved by an extra segmentation readout layer , which takes the global frame embedding r as the input and produces the final object-level segmentation prediction. is also trained by the cross-entropy loss, as in Eq. 15. For notation clarity, we omit this term in the overall training loss in Eq. 16. Please note that is only used in Z-VOS setting; for O-VOS setting, the segmentation masks are generated with a different strategy.
Instance-Level Z-VOS Setting. Our model can also be adapted for the instance-level Z-VOS setting, in which different object instances must be discriminated, in addition to separating the primary video objects from the background without test-time human supervision. For each test frame, we first apply mask-RCNN  to produce a set of category agnostic object proposals.Then we apply our trained model for producing a binary foreground-background mask per frame. After combining object bounding-box proposals with binary object-level segmentation masks, we can filter out the background proposals and obtain pixel-wise, instance-level object candidates for each frame. Finally, to link those object candidates across different frames, similar to , we use overlap ratio and optical flow as the cross-frame candidate-association metric. Note that, mask-RCNN can be replaced with non-learning Edgebox  and GrabCut, resulting a purely unsupervised/weakly-supervised protocol.
O-VOS Setting. In O-VOS, for each test video sequence, instance-level annotations regarding multiple general foreground objects in the first frame are given. In such a setting, our trained network works in a per-frame matching based mask propagation fashion. Concretely, assume there are a total of object instances (including the background) in the first-frame annotation, each spatial position
will be associated with a one-hot class vector, whose element indicates whether pixel n belong to -th object instance. Starting from the second frame, we use both the last segmented frame as well as current under-segmented frame to build an input pair for our model. Then we compute their similarity affinity in the feature space: . After that, for each pixel m in
, we compute its probability distributionover the object instances as:
where is the affinity value between pixel n in and m in . For m, it is assigned to -th instance: , where . Then we get its label vector . In this way, from the segmented frame , we move to the next input frame pair and get the segmentation result for . As our method does not use any first-frame fine-tuning [6, 35] or online learning  technique, it is fast for inference.
|Reference||Full model (2 iterations)||58.0||-||61.2||-|
|Heuristic Saliency ||37.2||-20.8||-||-|
|w/o. Frame Granularity||40.2||-17.8||40.2||-21.0|
|w/o. Short-term Granularity||51.3||-6.7||57.1||-4.1|
|w/o. Long-term Granularity||52.8||-5.2||56.0||-5.2|
|w/o. Video Granularity||56.4||-1.6||60.4||-0.8|
|More Data||+ LaSOT dataset ||59.5||+1.5||62.3||+1.1|
Implementation Details. We train the whole network from scratch on the OxUvA  tracking dataset, as in . OxUvA comprises 366 video sequences with more than 1.5 million frames in total. We train our model with SGD optimizer. For our bootstrapping based iterative training, two iterations are used and each takes about 8 hours.
|Supervision||Non Learning||Unsupervised Learning||Weakly-supervised|
|Method||TRC ||CVOS ||KEY ||MSG ||NLC ||FST ||Motion Masks ||TSN ||Ours||COSEG ||Ours|
|Supervision||Non Learning||Unsupervised Learning||Weakly-supervised Learning|
|Method||CRANE ||NLC ||FST ||ARP ||Motion Masks ||TSN ||Ours||SOSD ||BBF ||COSEG ||Ours|
Configuration and Reproducibility.
MuG is implemented on PyTorch. All experiments are conducted on an Nvidia TITAN Xp GPU and an Intel (R) Xeon E5 CPU. All our implementations, trained models, and segmentation results will be released to provide the full details of our approach.
A series of ablation studies are performed for assessing the effectiveness of each essential component of MuG.
Initial Fore-Background Knowledge. Baselines Heuristic Saliency and CAM give the scores of initial fore-background knowledge, based on their CRF-binarized outputs. As seen, with the low-quality initial knowledge, our MuG gains huge performance improvements ( and promotions), showing the significance of our multi-granularity video object pattern learning scheme.
Multi-Granularity Analysis. Next we investigate the contributions of multi-granularity cues in depth. As shown in Table 1, the intrinsic, multi-granularity properties are indeed meaningful, as disabling any granularity analysis component causes performance to erode. For instance, removing the frame granularity analysis during learning hurts performance (mean : , ), due to the lack of fore-/background information. Similarly, performance drops when excluding short- or long-term granularity analysis, suggesting the importance of capturing local consistency and semantic correspondence. Moreover, considering video granularity information also improves the final performance, proving the meaning of comprehensive video content understanding in video object pattern modeling.
Iterative Training Strategy. From Table 1, we can see that with more iterations of our bootstrapping training strategy (), better performance can be obtained. However, further iterations () give only marginal performance change. We thus use two iterations in all the experiments.
More Training Data. To show the potential of our unsupervised/weakly supervised VOS learning scheme, we probe the upper bound by training on additional videos. With more training data (1400 videos) from LaSOT dataset , performance boosts can be observed in both two settings.
Datasets. Experiments are conducted on two famous Z-VOS datasets: DAVIS  and Youtube-Objects , which have pixel-wise, object-level annotations. DAVIS has 50 videos (3,455 frames), covering a wide range of challenges, such as fast motion, occlusion, dynamic background, etc. It is split into a train set (30 videos) and a val set (20 videos). Youtube-Objects contains 126 video sequences that belong to 10 categories (such as cat, dog, etc.) and has 25,673 frames in total. The val set of DAVIS and whole Youtube-Objects are used for evaluation.
Evaluation Criteria. For fair comparison, we follow the official evaluation protocols of each dataset. For DAVIS, we report region similarity , boundary accuracy and time stability . For Youtube-Objects, the performance is evaluated in terms of region similarity .
Quantitative Results. Table 2 presents the comparison results with several non-learning, unsupervised or weakly supervised learning competitors in DAVIS dataset. In particular, MuG exceeds current leading unsupervised learning-based methods (i.e., Motion Masks  and TSN  ) in large margins (58.0 vs 48.9 and 58.0 vs 31.2). MuG also outperforms classical weakly-supervised Z-VOS method COSEG , and all the previous heuristic methods. Table 3 summarizes comparison results on Youtube-Objects dataset, showing again our superior performance in both unsupervised and weakly supervised learning settings.
Runtime Comparison. The inference time of MuG is about 0.6s per frame, which is faster than most deep learning based competitors (e.g., MotionMask  (1.1s), TSN  (0.9s)). This is because, except CRF , there is no other pre-/post-processing step (e.g., superpixel , optical flow , etc.) and online fine-tuning .
|Supervision||Non Learning||Unsupervised Learning||Weakly-supervised|
|Method||HVS ||JMP ||FCP ||SIFT Flow ||BVS ||Vondrick et al. ||mgPFF ||TimeCycle ||CorrFlow ||Ours||FlowNet2 ||Ours|
|Supervision||Non Learning||Unsupervised Learning||Weakly-supervised|
|SIFT Flow||BVS||DeepCluster||Transitive Inv||Vondrick et al.||mgPFF||TimeCycle||CorrFlow||FlowNet2|
Datasets. We test the performance for instance-level Z-VOS on DAVIS  dataset, which has 120 videos and 8,502 frames in total. It has three subsets, namely, train, val, and test-dev, containing 60, 30, and 30 video sequences, respectively. We use the ground-truth masks provided by the newest DAVIS challenge , as the original annotations are biased towards the O-VOS scenario.
Three standard evaluation metrics, provided by DAVIS, are used, i.e., region similarity , boundary accuracy and the average value of .
Quantitative Results. Three top-performing ZVOS methods from the DAVIS benchmark are included. As shown in Table 4, our model achieves comparable performance with the fully supervised methods (i.e., AGS  and PDB ). Notably, it significantly outperforms recent RVOS  (mean : and in unsupervised and weakly-supervised learning setting, respectively).
Evaluation Criteria. Three standard evaluation criteria are reported: region similarity , boundary accuracy and the average value of . For DAVIS dataset, we further report the time stability .
Quantitative Results. Table 5 and Table 6 give evaluation results on DAVIS and DAVIS, respectively. Table 5 shows that our unsupervised method exceeds representative self-supervised methods (i.e., TimeCyle  and CorrFlow ) and the best non-learning method (i.e., BVS ) across most metrics. In particular, with the learned CAM as supervision, our weakly supervised method further improves the performance, e.g., mean of 65.7. Table 6 verifies again our method performs favorably against the current best unsupervised method, CorrFlow, according to mean (54.3 vs 50.3). Note that CorrFlow and our method use the same training data. This demonstrates our MuG is able to learn more powerful video object patterns, compared to previous self-learning counterparts.
Fig. 5 presents some visual results for object-level ZVOS (top row), instance-level Z-VOS (middle row) and O-VOS (bottom row). For blackswan in DAVIS , the primary objects undergo view changes and background clutter, but our MuG still generates accurate foreground segments. The effectiveness of instance-level Z-VOS can be observed in tram of DAVIS . In addition, MuG can produce high-quality results with the given first-frame annotations in O-VOS setting (see the results on the last row for scooter-black in DAVIS ), although the different instances suffer from fast motion and scale variation. More results can be found in supplementary materials.
We proposed MuG – an end-to-end trainable, unsupervised/weakly supervised learning approach for segmenting objects from the videos. Different from current popular supervised VOS solutions requiring extensive amounts of elaborately annotated training samples, our MuG models video object patterns by comprehensively exploring supervision signals from different granularities of unlabeled videos. Our model sets new state-of-the-arts over diverse VOS settings, including object-level Z-VOS, instance-level Z-VOS, and O-VOS. Our model opens up the probability of learning VOS from nearly infinite amount of unlabeled videos and unifying different VOS settings from a single view of video object pattern understanding.
Discriminative unsupervised feature learning with convolutional neural networks. In NIPS, Cited by: §3.1, §3.1.
JumpCut: non-successive mask transfer and interpolation for video cutout. ACM Trans. Graph. 34 (6), pp. 195:1–195:10. Cited by: §2.1, Table 5.
Learning deep features for discriminative localization. In CVPR, Cited by: 1st item, §1, §3.1, §3.2, footnote 2.