Paper Reading Record in Computer Vision

Table of Contents

• Knowledge Distillation
• Domain Adaptation
• Semi-Supervised Learning
• Semantic Segmentation
• Object Detection
• Visual Object Tracking
• Data Augmentation
• Image-to-Image Translation
• Multi-Domain Learning
• Corruption Robustness
• Adversarial Robustness
• Self-Supervised Learning
• Attention
• Precious Papers
• Multimodal Large Language Models

Knowledge Distillation

• Knowledge Distillation and Student-Teacher Learning for Visual Intelligence: A Review and New Outlooks (ArXiv 2020) [Paper][Code] ⭐⭐⭐⭐⭐

• Knowledge distillation (KD) has been proposed to transfer information learned from one model to another
• In this work, we focus on analyzing and categorizing existing KD methods accompanied by various types of S-T structures for model compression and knowledge transfer
• Distillation from one teacher
• Data-free distillation
• Online distillation
• Cross-modal distillation
• Semi/self-supervised learning

• Structured Knowledge Distillation for Dense Prediction (ArXiv 2020) [Paper][Code] ⭐⭐⭐

• Knowledge Adaptation for Efficient Semantic Segmentation (CVPR 2019) [Paper][Code] ⭐⭐

• Learning From Multiple Experts: Self-paced Knowledge Distillation for Long-tailed Classification (ECCV 2020) [Paper][Code] ⭐

Domain Adaptation

• A Review of Single-Source Deep Unsupervised Visual Domain Adaptation (ArXiv 2020) [Paper][Code] ⭐⭐⭐⭐

• A Comprehensive Survey on Transfer Learning (ArXiv 2020) [Paper][Code] ⭐⭐⭐⭐

• Transfer Adaptation Learning: A Decade Survey (ArXiv 2020) [Paper][Code] ⭐⭐⭐⭐

• Deep Visual Domain Adaptation: A Survey (Neurocomputing 2018) [Paper][Code] ⭐⭐

• Multi-source Domain Adaptation in the Deep Learning Era: A Systematic Survey (ArXiv 2018) [Paper][Code] ⭐⭐

• DADA: Depth-Aware Domain Adaptation in Semantic Segmentation (ArXiv 2020) [Paper] [Code]

• Multi-source Domain Adaptation for Semantic Segmentation (ArXiv 2020) [Paper] [Code]⭐

• A Robust Learning Approach to Domain Adaptive Object Detection (ICCV 2019) [Paper][Code]

Semi-Supervised Learning

• Semi-Supervised Semantic Segmentation with Cross-Consistency Training (CVPR 2020) [Paper][Code] ⭐

• Semi-Supervised Semantic Segmentation via Dynamic Self-Training and Class-Balanced Curriculum (ECCV 2020) [Paper][Code] ⭐

• Guided Collaborative Training for Pixel-wise Semi-Supervised Learning (ECCV 2020) [Paper][Code] ⭐

• FeatMatch: Feature-Based Augmentation for Semi-Supervised Learning (ECCV 2020) [Paper][Code] ⭐⭐

Data Imbalance

• Prime Sample Attention in Object Detection (CVPR 2020) [Paper][Code] ⭐

Multi-Task Learning

• Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics (CVPR 2018) [Paper][Code]

Semantic Segmentation

• Benchmarking the Robustness of Semantic Segmentation Models (CVPR 2020) [Paper] [Code]:star::star::star:

Object Detection

• Boosting Weakly Supervised Object Detection with Progressive Knowledge Transfer (ECCV 2020) [Paper][Code]

• HoughNet: Integrating near and long-range evidence for bottom-up object detection (ECCV 2020) [Paper][Code]

Visual Object Tracking

• CLNet: A Compact Latent Network for Fast Adjusting Siamese Trackers (ECCV 2020) [Paper][Code] ⭐✔️

• Scale Equivariance Improves Siamese Tracking (ECCV 2020) [Paper][Code]

• Fully Convolutional Online Tracking (ArXiv 2020) [Paper][Code]

• Transformer Meets Tracker:Exploiting Temporal Context for Robust Visual Tracking (CVPR 2021)[Paper][Code]

• Transformer Tracking (CVPR 2021) [Paper][Code]

• Learning Spatio-Temporal Transformer for Visual Tracking (ICCV 2021) [Paper][Code]

• TrTr: Visual Tracking with Transformer (ArXiv 2021) [Paper][Code]

Data Augmentation

• Adversarial Semantic Data Augmentation for Human Pose Estimation (ECCV 2020) [Paper][Code]

• Unsupervised Data Augmentation for Consistency Training (NeurIPS 2020) [Paper][Code]

Image-to-Image-Translation

• Few-Shot Unsupervised Image-to-Image Translation (ICCV 2019) [Paper][Code]

• Unsupervised Domain Adaptation with Multiple Domain Discriminators and Adaptive Self-Training (ArXiv 2020) [Paper][Code]

• DRIT++: Diverse Image-to-Image Translation via Disentangled Representations (ArXiv 2020) [Paper][Code]:star::star:

• EDIT: Exemplar-Domain Aware Image-to-Image Translation (ArXiv 2020) [Paper][Code]:star:

• GANHOPPER: Multi-Hop GAN for Unsupervised Image-to-Image Translation (ArXiv 2020) [Paper][Code]:star:

• Exemplar Guided Unsupervised Image-To-Image Translation With Semantic Consistency (ArXiv 2020) [Paper][Code]:star:

• Geometry-Consistent Generative Adversarial Networks for One-Sided Unsupervised Domain Mapping (ArXiv 2020) [Paper][Code]:star:

• Domain Bridge for Unpaired Image-to-Image Translation and Unsupervised Domain Adaptation (ArXiv 2020) [Paper][Code]:star:

• On the Role of Receptive Field in Unsupervised Sim-to-Real Image Translation (ArXiv 2020) [Paper][Code]:star:

• Multi-mapping Image-to-Image Translation via Learning Disentanglement (ArXiv 2020) [Paper][Code]:star:

• INSTAGAN: Instrance-Aware Image-To-ImageTranslation (ArXiv 2020) [Paper][Code]:star:

• Towards Instance-level Image-to-Image Translation(ArXiv 2020) [Paper][Code]:star:

• TuiGAN: Learning Versatile Image-to-Image Translation with Two Unpaired Images (ArXiv 2020) [Paper][Code]:star:

Multi-Domain Learning

• Budget-Aware Adapters for Multi-Domain Learning (ArXiv 2020) [Paper][Code]

• Self-Supervised Representation Learning From Multi-Domain Data (ArXiv 2020) [Paper][Code]

• Efficient parametrization of multi-domain deep neural networks (ArXiv 2020) [Paper][Code]

Corruption Robustness

• ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness (ICLR 2019) [Paper][Code] ⭐⭐⭐⭐

• Benchmarking Neural Network Robustness to Common Corruptions and Perturbations (ICLR 2019) [Paper][Code] ⭐⭐⭐⭐

• Benchmarking Robustness in Object Detection: Autonomous Driving when Winter is Coming (NeurIPS 2019) [Paper][Code] ⭐⭐⭐⭐

• ADVERSARIAL AND NATURAL PERTURBATIONS FOR GENERAL ROBUSTNESS (ArXiv 2020, Rejected in ICLR 2021) [Paper][Code]

Adversarial Robustness

• Adversarial Examples in Modern Machine Learning: A Review (ArXiv 2019) [Paper][Code]:star::star::star::star:

• Opportunities and Challenges in Deep Learning Adversarial Robustness: A Survey (ArXiv 2020) [Paper][Code]:star::star::star::star:

• Defending against adversarial examples using defense kernel network (BMVC 2019) [Paper][Code]

• Towards Evaluating the Robustness of Neural Networks (ArXiv 2017) [Paper][Code]

• A simple way to make neural networks robust against diverse image corruptions (EECV 2020) [Paper][Code]:star::star:

Self-Supervised Learning

• Supervised Contrastive Learning (ArXiv 2020) [Paper][Code] ⭐⭐⭐

• Contrastive Representation Learning: A Framework and Review (IEEE ACCESS 2020) [Paper][Code] ⭐⭐

Attention

• AN IMAGE IS WORTH 16X16 WORDS: TRANSFORMERS FOR IMAGE RECOGNITION AT SCALE (ICLR 2021) [Paper][Code] ⭐⭐⭐⭐

• VOLO: Vision Outlooker for Visual Recognition (ArXiv 2021) [Paper][Code]

• SA-Net: Shuffle Attention for Deep Convolutional Neural Networks (ICASSP 2021) [Paper][Code]

• Involution: Inverting the Inherence of Convolution for Visual Recognition (CVPR 2021) [Paper][Code] ⭐⭐

• Swin Transformer: Hierarchical Vision Transformer using Shifted Windows (ICCV 2021) [Paper][Code]⭐⭐⭐

Precious Papers

• Shortcut Learning in Deep Neural Networks (ArXiv 2020) [Paper][Code] ⭐⭐⭐⭐⭐

• Scale-Equivariant Steerable Networks (ArXiv 2020) [Paper][Code]

Multimodal Large Language Models

Multimodal Instruction Tuning

• InternLM-XComposer2.5-OmniLive: A Comprehensive Multimodal System for Long-term Streaming Video and Audio Interactions (arXiv 2024) [Paper]
• StreamChat: Chatting with Streaming Video (arXiv 2024) [Paper]
• CompCap: Improving Multimodal Large Language Models with Composite Captions (arXiv 2024) [Paper]

Multimodal Hallucination

• LinVT: Empower Your Image-level Large Language Model to Understand Videos (arXiv 2024) [Paper]
• Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling (Tech Report 2024) [Paper]

Multimodal Chain-of-Thought

• NVILA: Efficient Frontier Visual Language Models (arXiv 2024) [Paper]
• T2Vid: Translating Long Text into Multi-Image is the Catalyst for Video-LLMs (arXiv 2024) [Paper]
• TimeMarker: A Versatile Video-LLM for Long and Short Video Understanding with Superior Temporal Localization Ability (arXiv 2024) [Paper]

Contact & Feedback

Feel free to contact me or pull request.

• E-mail

License

This list is released into the public domain.