
-
Understanding Catastrophic Forgetting and Remembering in Continual Learning with Optimal Relevance Mapping
Catastrophic forgetting in neural networks is a significant problem for ...
read it
-
CReST: A Class-Rebalancing Self-Training Framework for Imbalanced Semi-Supervised Learning
Semi-supervised learning on class-imbalanced data, although a realistic ...
read it
-
Occluded Video Instance Segmentation
Can our video understanding systems perceive objects when a heavy occlus...
read it
-
NeMo: Neural Mesh Models of Contrastive Features for Robust 3D Pose Estimation
3D pose estimation is a challenging but important task in computer visio...
read it
-
COMPAS: Representation Learning with Compositional Part Sharing for Few-Shot Classification
Few-shot image classification consists of two consecutive learning proce...
read it
-
Meticulous Object Segmentation
Compared with common image segmentation tasks targeted at low-resolution...
read it
-
Mask Guided Matting via Progressive Refinement Network
We propose Mask Guided (MG) Matting, a robust matting framework that tak...
read it
-
ViP-DeepLab: Learning Visual Perception with Depth-aware Video Panoptic Segmentation
In this paper, we present ViP-DeepLab, a unified model attempting to tac...
read it
-
Robust Instance Segmentation through Reasoning about Multi-Object Occlusion
Analyzing complex scenes with Deep Neural Networks is a challenging task...
read it
-
MaX-DeepLab: End-to-End Panoptic Segmentation with Mask Transformers
We present MaX-DeepLab, the first end-to-end model for panoptic segmenta...
read it
-
Robustness Out of the Box: Compositional Representations Naturally Defend Against Black-Box Patch Attacks
Patch-based adversarial attacks introduce a perceptible but localized ch...
read it
-
Unsupervised Part Discovery via Feature Alignment
Understanding objects in terms of their individual parts is important, b...
read it
-
Batch Normalization with Enhanced Linear Transformation
Batch normalization (BN) is a fundamental unit in modern deep networks, ...
read it
-
Can Temporal Information Help with Contrastive Self-Supervised Learning?
Leveraging temporal information has been regarded as essential for devel...
read it
-
Weakly-Supervised Amodal Instance Segmentation with Compositional Priors
Amodal segmentation in biological vision refers to the perception of the...
read it
-
Shape-Texture Debiased Neural Network Training
Shape and texture are two prominent and complementary cues for recognizi...
read it
-
CO2: Consistent Contrast for Unsupervised Visual Representation Learning
Contrastive learning has been adopted as a core method for unsupervised ...
read it
-
CoKe: Localized Contrastive Learning for Robust Keypoint Detection
Today's most popular approaches to keypoint detection learn a holistic r...
read it
-
Lymph Node Gross Tumor Volume Detection in Oncology Imaging via Relationship Learning Using Graph Neural Network
Determining the spread of GTV_LN is essential in defining the respective...
read it
-
Lymph Node Gross Tumor Volume Detection and Segmentation via Distance-based Gating using 3D CT/PET Imaging in Radiotherapy
Finding, identifying and segmenting suspicious cancer metastasized lymph...
read it
-
ASAP-Net: Attention and Structure Aware Point Cloud Sequence Segmentation
Recent works of point clouds show that mulit-frame spatio-temporal model...
read it
-
Probabilistic Multi-modal Trajectory Prediction with Lane Attention for Autonomous Vehicles
Trajectory prediction is crucial for autonomous vehicles. The planning s...
read it
-
Uncertainty-aware multi-view co-training for semi-supervised medical image segmentation and domain adaptation
Although having achieved great success in medical image segmentation, de...
read it
-
Compositional Convolutional Neural Networks: A Robust and Interpretable Model for Object Recognition under Occlusion
Computer vision systems in real-world applications need to be robust to ...
read it
-
Smooth Adversarial Training
It is commonly believed that networks cannot be both accurate and robust...
read it
-
DetectoRS: Detecting Objects with Recursive Feature Pyramid and Switchable Atrous Convolution
Many modern object detectors demonstrate outstanding performances by usi...
read it
-
Detecting Scatteredly-Distributed, Small, andCritically Important Objects in 3D OncologyImaging via Decision Stratification
Finding and identifying scatteredly-distributed, small, and critically i...
read it
-
Robust Object Detection under Occlusion with Context-Aware CompositionalNets
Detecting partially occluded objects is a difficult task. Our experiment...
read it
-
Domain Adaptive Relational Reasoning for 3D Multi-Organ Segmentation
In this paper, we present a novel unsupervised domain adaptation (UDA) m...
read it
-
Organ at Risk Segmentation for Head and Neck Cancer using Stratified Learning and Neural Architecture Search
OAR segmentation is a critical step in radiotherapy of head and neck (H ...
read it
-
PatchAttack: A Black-box Texture-based Attack with Reinforcement Learning
Patch-based attacks introduce a perceptible but localized change to the ...
read it
-
Context-Aware Group Captioning via Self-Attention and Contrastive Features
While image captioning has progressed rapidly, existing works focus main...
read it
-
Neural Architecture Search for Lightweight Non-Local Networks
Non-Local (NL) blocks have been widely studied in various vision tasks. ...
read it
-
Are Labels Necessary for Neural Architecture Search?
Existing neural network architectures in computer vision — whether desig...
read it
-
Synthesize then Compare: Detecting Failures and Anomalies for Semantic Segmentation
The ability to detect failures and anomalies are fundamental requirement...
read it
-
Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation
Convolution exploits locality for efficiency at a cost of missing long r...
read it
-
Compositional Convolutional Neural Networks: A Deep Architecture with Innate Robustness to Partial Occlusion
Recent work has shown that deep convolutional neural networks (DCNNs) do...
read it
-
When Radiology Report Generation Meets Knowledge Graph
Automatic radiology report generation has been an attracting research pr...
read it
-
Object as Hotspots: An Anchor-Free 3D Object Detection Approach via Firing of Hotspots
Accurate 3D object detection in LiDAR based point clouds suffers from th...
read it
-
AtomNAS: Fine-Grained End-to-End Neural Architecture Search
Designing of search space is a critical problem for neural architecture ...
read it
-
Learning from Synthetic Animals
Despite great success in human parsing, progress for parsing other defor...
read it
-
Identity Preserve Transform: Understand What Activity Classification Models Have Learnt
Activity classification has observed great success recently. The perform...
read it
-
Zero-shot Recognition of Complex Action Sequences
Zero-shot video classification for fine-grained activity recognition has...
read it
-
RSA: Randomized Simulation as Augmentation for Robust Human Action Recognition
Despite the rapid growth in datasets for video activity, stable robust a...
read it
-
Shape-aware Feature Extraction for Instance Segmentation
Modern instance segmentation approaches mainly adopt a sequential paradi...
read it
-
Identifying Model Weakness with Adversarial Examiner
Machine learning models are usually evaluated according to the average c...
read it
-
Rethinking Normalization and Elimination Singularity in Neural Networks
In this paper, we study normalization methods for neural networks from t...
read it
-
Adversarial Examples Improve Image Recognition
Adversarial examples are commonly viewed as a threat to ConvNets. Here w...
read it
-
Localizing Occluders with Compositional Convolutional Networks
Compositional convolutional networks are generative compositional models...
read it
-
Grouped Spatial-Temporal Aggregation for Efficient Action Recognition
Temporal reasoning is an important aspect of video analysis. 3D CNN show...
read it