Linked e-resources
Details
Table of Contents
Cross-Domain Ensemble Distillation for Domain Generalization
Centrality and Consistency: Two-Stage Clean Samples Identification for Learning with Instance-Dependent Noisy Labels
Hyperspherical Learning in Multi-Label Classification
When Active Learning Meets Implicit Semantic Data Augmentation
VL-LTR: Learning Class-Wise Visual-Linguistic Representation for Long-Tailed Visual Recognition
Class Is Invariant to Context and Vice Versa: On Learning Invariance for Out-of-Distribution Generalization
Hierarchical Semi-Supervised Contrastive Learning for ContaminationResistant Anomaly Detection
Tracking by Associating Clips
RealPatch: A Statistical Matching Framework for Model Patching with Real Samples
Background-Insensitive Scene Text Recognition with Text Semantic Segmentation
Semantic Novelty Detection via Relational Reasoning
Improving Closed and Open-Vocabulary Attribute Prediction Using Transformers
Training Vision Transformers with Only 2040 Images
Bridging Images and Videos: A Simple Learning Framework for Large Vocabulary Video Object Detection
TDAM: Top-Down Attention Module for Contextually Guided Feature Selection in CNNs
Automatic Check-Out via Prototype-Based Classifier Learning from Single-Product Exemplars
Overcoming Shortcut Learning in a Target Domain by Generalizing Basic Visual Factors from a Source Domain
Photo-Realistic Neural Domain Randomization
Wave-ViT: Unifying Wavelet and Transformers for Visual Representation Learning
Tailoring Self-Supervision for Supervised Learning
Difficulty-Aware Simulator for Open Set Recognition
Few-Shot Class-Incremental Learning from an Open-Set Perspective
FOSTER: Feature Boosting and Compression for Class-Incremental Learning
Visual Knowledge Tracing
S3C: Self-Supervised Stochastic Classifiers for Few-Shot ClassIncremental Learning
Improving Fine-Grained Visual Recognition in Low Data Regimes via Self-Boosting Attention Mechanism
VSA: Learning Varied-Size Window Attention in Vision Transformers
Unbiased Manifold Augmentation for Coarse Class Subdivision
DenseHybrid: Hybrid Anomaly Detection for Dense Open-Set Recognition
Rethinking Confidence Calibration for Failure Prediction
Uncertainty-Guided Source-Free Domain Adaptation
Should All Proposals Be Treated Equally in Object Detection?
VIP: Unified Certified Detection and Recovery for Patch Attack with Vision Transformers
incDFM: Incremental Deep Feature Modeling for Continual Novelty Detection
IGFormer: Interaction Graph Transformer for Skeleton-Based Human Interaction Recognition
PRIME: A Few Primitives Can Boost Robustness to Common Corruptions
Rotation Regularization without Rotation
Towards Accurate Open-Set Recognition via Background-Class Regularization
In Defense of Image Pre-training for Spatiotemporal Recognition
Augmenting Deep Classifiers with Polynomial Neural Networks
Learning with Noisy Labels by Efficient Transition Matrix Estimation to Combat Label Miscorrection
Online Task-Free Continual Learning with Dynamic Sparse Distributed Memory.
Centrality and Consistency: Two-Stage Clean Samples Identification for Learning with Instance-Dependent Noisy Labels
Hyperspherical Learning in Multi-Label Classification
When Active Learning Meets Implicit Semantic Data Augmentation
VL-LTR: Learning Class-Wise Visual-Linguistic Representation for Long-Tailed Visual Recognition
Class Is Invariant to Context and Vice Versa: On Learning Invariance for Out-of-Distribution Generalization
Hierarchical Semi-Supervised Contrastive Learning for ContaminationResistant Anomaly Detection
Tracking by Associating Clips
RealPatch: A Statistical Matching Framework for Model Patching with Real Samples
Background-Insensitive Scene Text Recognition with Text Semantic Segmentation
Semantic Novelty Detection via Relational Reasoning
Improving Closed and Open-Vocabulary Attribute Prediction Using Transformers
Training Vision Transformers with Only 2040 Images
Bridging Images and Videos: A Simple Learning Framework for Large Vocabulary Video Object Detection
TDAM: Top-Down Attention Module for Contextually Guided Feature Selection in CNNs
Automatic Check-Out via Prototype-Based Classifier Learning from Single-Product Exemplars
Overcoming Shortcut Learning in a Target Domain by Generalizing Basic Visual Factors from a Source Domain
Photo-Realistic Neural Domain Randomization
Wave-ViT: Unifying Wavelet and Transformers for Visual Representation Learning
Tailoring Self-Supervision for Supervised Learning
Difficulty-Aware Simulator for Open Set Recognition
Few-Shot Class-Incremental Learning from an Open-Set Perspective
FOSTER: Feature Boosting and Compression for Class-Incremental Learning
Visual Knowledge Tracing
S3C: Self-Supervised Stochastic Classifiers for Few-Shot ClassIncremental Learning
Improving Fine-Grained Visual Recognition in Low Data Regimes via Self-Boosting Attention Mechanism
VSA: Learning Varied-Size Window Attention in Vision Transformers
Unbiased Manifold Augmentation for Coarse Class Subdivision
DenseHybrid: Hybrid Anomaly Detection for Dense Open-Set Recognition
Rethinking Confidence Calibration for Failure Prediction
Uncertainty-Guided Source-Free Domain Adaptation
Should All Proposals Be Treated Equally in Object Detection?
VIP: Unified Certified Detection and Recovery for Patch Attack with Vision Transformers
incDFM: Incremental Deep Feature Modeling for Continual Novelty Detection
IGFormer: Interaction Graph Transformer for Skeleton-Based Human Interaction Recognition
PRIME: A Few Primitives Can Boost Robustness to Common Corruptions
Rotation Regularization without Rotation
Towards Accurate Open-Set Recognition via Background-Class Regularization
In Defense of Image Pre-training for Spatiotemporal Recognition
Augmenting Deep Classifiers with Polynomial Neural Networks
Learning with Noisy Labels by Efficient Transition Matrix Estimation to Combat Label Miscorrection
Online Task-Free Continual Learning with Dynamic Sparse Distributed Memory.