
-
Fine-Grained Few-Shot Classification with Feature Map Reconstruction Networks
In this paper we reformulate few-shot classification as a reconstruction...
read it
-
Augmentation-Interpolative AutoEncoders for Unsupervised Few-Shot Image Generation
We aim to build image generation models that generalize to new domains f...
read it
-
Self-training for Few-shot Transfer Across Extreme Task Differences
All few-shot learning techniques must be pre-trained on a large, labeled...
read it
-
Learning Gradient Fields for Shape Generation
In this work, we propose a novel technique to generate shapes from point...
read it
-
Wasserstein Distances for Stereo Disparity Estimation
Existing approaches to depth or disparity estimation output a distributi...
read it
-
Train in Germany, Test in The USA: Making 3D Object Detectors Generalize
In the domain of autonomous driving, deep learning has substantially imp...
read it
-
Learning Feature Descriptors using Camera Pose Supervision
Recent research on learned visual descriptors has shown promising improv...
read it
-
Fashionpedia: Ontology, Segmentation, and an Attribute Localization Dataset
In this work we explore the task of instance segmentation with attribute...
read it
-
Extending and Analyzing Self-Supervised Learning Across Domains
Self-supervised representation learning has achieved impressive results ...
read it
-
End-to-End Pseudo-LiDAR for Image-Based 3D Object Detection
Reliable and accurate 3D object detection is a necessity for safe autono...
read it
-
Revisiting Pose-Normalization for Fine-Grained Few-Shot Recognition
Few-shot, fine-grained classification requires a model to learn subtle, ...
read it
-
LDLS: 3-D Object Segmentation Through Label Diffusion From 2-D Images
Object segmentation in three-dimensional (3-D) point clouds is a critica...
read it
-
When Does Self-supervision Improve Few-shot Learning?
We present a technique to improve the generalization of deep representat...
read it
-
On the Efficacy of Knowledge Distillation
In this paper, we present a thorough evaluation of the efficacy of knowl...
read it
-
Few-Shot Generalization for Single-Image 3D Reconstruction via Priors
Recent work on single-view 3D reconstruction shows impressive results, b...
read it
-
GeoStyle: Discovering Fashion Trends and Events
Understanding fashion styles and trends is of great potential interest t...
read it
-
PointFlow: 3D Point Cloud Generation with Continuous Normalizing Flows
As 3D point clouds become the representation of choice for multiple visi...
read it
-
Boosting Supervision with Self-Supervision for Few-shot Learning
We present a technique to improve the transferability of deep representa...
read it
-
Pseudo-LiDAR++: Accurate Depth for 3D Object Detection in Autonomous Driving
Detecting objects such as cars and pedestrians in 3D plays an indispensa...
read it
-
Few-Shot Learning with Localization in Realistic Settings
Traditional recognition methods typically require large, artificially-ba...
read it
-
Pseudo-LiDAR from Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Driving
3D object detection is an essential task in autonomous driving. Recent t...
read it
-
A Deep-Learning-Based Fashion Attributes Detection Model
Analyzing fashion attributes is essential in the fashion design process....
read it
-
Deep Fundamental Matrix Estimation without Correspondences
Estimating fundamental matrices is a classic problem in computer vision....
read it
-
Resource Aware Person Re-identification across Multiple Resolutions
Not all people are equally easy to identify: color statistics might be e...
read it
-
Low-Shot Learning from Imaginary Data
Humans can quickly learn new visual concepts, perhaps because they can e...
read it
-
Low-shot learning with large-scale diffusion
This paper considers the problem of inferring image labels for which onl...
read it
-
Inferring and Executing Programs for Visual Reasoning
Existing methods for visual reasoning attempt to directly map inputs to ...
read it
-
CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning
When building artificial intelligence systems that can reason and answer...
read it
-
Learning Features by Watching Objects Move
This paper presents a novel yet intuitive approach to unsupervised featu...
read it
-
Feature Pyramid Networks for Object Detection
Feature pyramids are a basic component in recognition systems for detect...
read it
-
Low-shot Visual Recognition by Shrinking and Hallucinating Features
Low-shot visual learning---the ability to recognize novel object categor...
read it
-
Iterative Instance Segmentation
Existing methods for pixel-wise labelling tasks generally disregard the ...
read it
-
DeepBox: Learning Objectness with Convolutional Networks
Existing object proposal approaches use primarily bottom-up cues to rank...
read it
-
Hypercolumns for Object Segmentation and Fine-grained Localization
Recognition algorithms based on convolutional networks (CNNs) typically ...
read it
-
Simultaneous Detection and Segmentation
We aim to detect all instances of a category in an image and, for each i...
read it
-
R-CNNs for Pose Estimation and Action Detection
We present convolutional neural networks for the tasks of keypoint (pose...
read it