CVPR2024部分研究方向文章梳理（持续更新中）

CVPR2024部分研究方向文章梳理（持续更新中）

长尾分布（Long-Tailed）

1. DeiT-LT: Distillation Strikes Back for Vision Transformer Training on Long-Tailed Datasets.
   全文地址：DeiT-LT \(rangwani-harsh.github.io\)

领域自适应（Domain Adaptation）

1. Learning CNN on ViT:A Hybrid Model to Explicitly Class-specific Boundaries for Domain Adaptation.
   全文地址：
   Learning CNN on ViT: A Hybrid Model to Explicitly Class-specific Boundaries for Domain Adaptation | Project Page (dotrannhattuong.github.io)
2. Source-Free Domain Adaptation with Frozen Multimodal Foundation Model

视觉-语言预训练（Vision-language Pretraining）

1. A Closer Look at the Few-Shot Adaptation of Large Vision-Language Models.
   全文地址：CLAP (jusiro.github.io)
2. Improving Generalized Zero-Shot Learning by Exploring the Diverse Semantics from External Class Names
3. FairCLIP: Harnessing Fairness in Vision-Language Learning
4. Efficient Test-Time Adaptation of Vision-Language Models
5. ArGue: Attribute-Guided Prompt Tuning for Vision-Language Models
6. Dual Memory Networks: A Versatile Adaptation Approach for Vision-Language Models
7. Transductive Zero-Shot && Few-Shot CLIP
8. LP++: A Surprisingly Strong Linear Probe for Few-Shot CLIP
9. PeVL: Pose-Enhanced Vision-Language Model for Fine-Grained Human Action Recognition
10. Alpha-CLIP: A CLIP Model Focusing on Wherever You Want
11. PromptKD: Unsupervised Prompt Distillation for Vision-Language Models
12. JoAPR: Cleaning the Lens of Prompt Learning for Vision-Language Models
13. Label Propagation for Zero-shot Classification with Vision-Language Models
14. ProTeCt: Prompt Tuning for Taxonomic Open Set Classification
15. Active Prompt Learning in Vision Language Models

多模态大模型（Large Multimodal Models）

1. ViP-LLaVA: Making Large Multimodal Models Understand Arbitrary Visual Prompts
   全文地址：ViP-LLaVA
2. Generative Multimodal Models are In-Context Learners
3. Q-Instruct: Improving Low-level Visual Abilities for Multi-modality Foundation Models
   全文地址：Q-Instruct | ②[CVPR 2024] Low-level visual instruction tuning, with a 200K dataset and a model zoo for fine-tuned checkpoints. (q-future.github.io)

少样本学习（Few-shot Learning）

1. Descriptor and Word Soups: Overcoming the Parameter Efficiency Accuracy Tradeoff for Out-of-Distribution Few-shot Learning
2. Adversarially Robust Few-shot Learning via Parameter Co-distillation of Similarity and Class Concept Learners
3. OrCo: Towards Better Generalization via Orthogonality and Contrast for Few-Shot Class-Incremental Learning
4. Discriminative Sample-Guided and Parameter-Efficient Feature Space Adaptation for Cross-Domain Few-Shot Learning
5. Progressive Semantic-Guided Vision Transformer for Zero-Shot Learning
6. Visual-Augmented Dynamic Semantic Prototype for Generative Zero-Shot Learning
7. Large Language Models are Good Prompt Learners for Low-Shot Image Classification

扩散模型（Diffusion Model）

1. GenTron: Diffusion Transformers for Image and Video Generation。
2. DiffuseMix: Label-Preserving Data Augmentation with Diffusion Models
   全文地址：DiffuseMix
3. Lodge: A Coarse to Fine Diffusion Network for Long Dance Generation Guided by the Characteristic Dance Primitives
   全文地址：Lodge (li-ronghui.github.io)
4. TokenCompose: Text-to-Image Diffusion with Token-level Supervision
   全文地址：TokenCompose: Grounding Diffusion with Token-level Supervision (mlpc-ucsd.github.io)
5. FreeControl: Training-Free Spatial Control of Any Text-to-Image Diffusion Model with Any Condition
6. LAKE-RED: Camouflaged Images Generation by Latent Background Knowledge Retrieval-Augmented Diffusion
7. FlashEval: Towards Fast and Accurate Evaluation of Text-to-image Diffusion Generative Models
8. Attention-Driven Training-Free Efficiency Enhancement of Diffusion Models
9. CAT-DM: Controllable Accelerated Virtual Try-on with Diffusion Model
10. Towards Understanding Cross and Self-Attention in Stable Diffusion for Text-Guided Image Editing
11. L-MAGIC: Language Model Assisted Generation of Images with Consistency
12. InteractDiffusion: Interaction Control in Text-to-Image Diffusion Models

类增量学习（Class Incremental Learning）

1. Class Incremental Learning with Multi-Teacher Distillation
2. Dual-Enhanced Coreset Selection with Class-wise Collaboration for Online Blurry Class Incremental Learning
3. Generative Multi-modal Models are Good Class Incremental Learners
4. Text-Enhanced Data-free Approach for Federated Class-Incremental Learning

噪声标签（Noisy Label Learning）

1. Estimating Noisy Class Posterior with Part-level Labels for Noisy Label Learning