Papers with Code 아카이브
Zero-Shot Image Classification
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 1
- 평가표
- 3
- 보존된 평가 기록
- 3
Zero-shot image classification is a technique in computer vision where a model can classify images into categories that were not present during training. This is achieved by leveraging semantic information about the categories, such as textual descriptions or relationships between classes.
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/ChiShengChen/MUSE_EEG
공식 코드Mind's Eye: Image Recognition by EEG via Multimodal Similarity-Keeping Contrastive Learning
https://github.com/China-UK-ZSL/Resources_for_KZSL
공식 코드https://github.com/Computer-Vision-in-the-Wild/Elevater_Toolkit_IC
공식 코드ELEVATER: A Benchmark and Toolkit for Evaluating Language-Augmented Visual Models
https://github.com/DannielSilva/RS-M-CLIP
공식 코드Multilingual Vision-Language Pre-training for the Remote Sensing Domain
https://github.com/Externalhappy/DPA
공식 코드DPA: Dual Prototypes Alignment for Unsupervised Adaptation of Vision-Language Models
https://github.com/OpenSparseLLMs/CLIP-MoE
공식 코드CLIP-MoE: Towards Building Mixture of Experts for CLIP with Diversified Multiplet Upcycling
https://github.com/WilliamYi96/HGR-Net
공식 코드Exploring Hierarchical Graph Representation for Large-Scale Zero-Shot Image Classification
https://github.com/YangYongJin/APEX
공식 코드Towards Difficulty-Agnostic Efficient Transfer Learning for Vision-Language Models
https://github.com/Z-Zheng/pytorch-change-models
공식 코드https://github.com/acmi-lab/chils
공식 코드CHiLS: Zero-Shot Image Classification with Hierarchical Label Sets
https://github.com/akshitac8/Generative_MLZSL
공식 코드https://github.com/andron00e/sparsecbm
공식 코드Sparse Concept Bottleneck Models: Gumbel Tricks in Contrastive Learning
https://github.com/cdb342/ijcai-2022-zla
공식 코드https://github.com/chendelong1999/remoteclip
공식 코드RemoteCLIP: A Vision Language Foundation Model for Remote Sensing
https://github.com/chris210634/ice
공식 코드Image-Caption Encoding for Improving Zero-Shot Generalization
https://github.com/computer-vision-in-the-wild/cvinw_readings
공식 코드ELEVATER: A Benchmark and Toolkit for Evaluating Language-Augmented Visual Models
https://github.com/drlxj/camdiff
공식 코드https://github.com/facebookresearch/metaclip
공식 코드https://github.com/fawazsammani/clip-interpret-mutual-knowledge
공식 코드Interpreting and Analysing CLIP's Zero-Shot Image Classification via Mutual Knowledge
https://github.com/flagai-open/flagai
공식 코드AltCLIP: Altering the Language Encoder in CLIP for Extended Language Capabilities
https://github.com/google-research/big_vision
공식 코드https://github.com/google-research/vision_transformer
공식 코드https://github.com/gregor-ge/babel-imagenet
공식 코드Babel-ImageNet: Massively Multilingual Evaluation of Vision-and-Language Representations
https://github.com/hayyubi/cur_vl
공식 코드Learning from Children: Improving Image-Caption Pretraining via Curriculum
https://github.com/hongrachel/clip-filtering-bias
공식 코드Who's in and who's out? A case study of multimodal CLIP-filtering in DataComp
https://github.com/icml24/sparsecbm
공식 코드Sparse Concept Bottleneck Models: Gumbel Tricks in Contrastive Learning
https://github.com/ivanaer/g-universal-clip
공식 코드General Image Descriptors for Open World Image Retrieval using ViT CLIP
https://github.com/jaisidhsingh/con-clip
공식 코드Learn "No" to Say "Yes" Better: Improving Vision-Language Models via Negations
https://github.com/jessemelpolio/anytimecl
공식 코드Anytime Continual Learning for Open Vocabulary Classification
https://github.com/jessemelpolio/treeprobe
공식 코드Continual Learning in Open-vocabulary Classification with Complementary Memory Systems
https://github.com/jxliu-ai/kpl
공식 코드KPL: Training-Free Medical Knowledge Mining of Vision-Language Models
https://github.com/laion-ai/scaling-laws-openclip
공식 코드Reproducible scaling laws for contrastive language-image learning
https://github.com/lezhang7/Enhance-FineGrained
공식 코드https://github.com/lixiaothu/laat
공식 코드Language-Driven Anchors for Zero-Shot Adversarial Robustness
https://github.com/magiccircuit/enhance-finegrained
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.