Image to Video Domain Adaptation Using Web Supervision

08/05/2019
by   Andrew Kae, et al.
0

Training deep neural networks typically requires large amounts of labeled data which may be scarce or expensive to obtain for a particular target domain. As an alternative, we can leverage webly-supervised data (i.e. results from a public search engine) which are relatively plentiful but may contain noisy results. In this work, we propose a novel two-stage approach to learn a video classifier using webly-supervised data. We argue that learning appearance features and then temporal features sequentially, rather than simultaneously, is an easier optimization for this task. We show this by first learning an image model from web images, which is used to initialize and train a video model. Our model applies domain adaptation to account for potential domain shift present between the source domain (webly-supervised data) and target domain and also accounts for noise by adding a novel attention component. We report results competitive with state-of-the-art for webly-supervised approaches on UCF-101 (while simplifying the training process) and also evaluate on Kinetics for comparison.

READ FULL TEXT
research
05/21/2021

DAVOS: Semi-Supervised Video Object Segmentation via Adversarial Domain Adaptation

Domain shift has always been one of the primary issues in video object s...
research
05/20/2022

Explainable Supervised Domain Adaptation

Domain adaptation techniques have contributed to the success of deep lea...
research
09/26/2014

Unsupervised Domain Adaptation by Backpropagation

Top-performing deep architectures are trained on massive amounts of labe...
research
03/21/2016

Beyond Sharing Weights for Deep Domain Adaptation

The performance of a classifier trained on data coming from a specific d...
research
09/09/2021

Towards Robust Cross-domain Image Understanding with Unsupervised Noise Removal

Deep learning models usually require a large amount of labeled data to a...
research
06/07/2016

Semi-Supervised Domain Adaptation for Weakly Labeled Semantic Video Object Segmentation

Deep convolutional neural networks (CNNs) have been immensely successful...
research
03/04/2020

Unsupervised and Interpretable Domain Adaptation to Rapidly Filter Social Web Data for Emergency Services

During the onset of a disaster event, filtering relevant information fro...

Please sign up or login with your details

Forgot password? Click here to reset