Papers with Code 아카이브
Image Classification
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 33
- 평가표
- 177
- 보존된 평가 기록
- 2,906
Image Classification is a fundamental task in vision recognition that aims to understand and categorize an image as a whole under a specific label. Unlike object detection, which involves classification and location of multiple objects within an image, image classification typically pertains to single-object images. When the classification becomes highly detailed or reaches instance-level, it is often referred to as image retrieval, which also involves finding similar images in a large database.
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/ytaek-oh/daso
공식 코드DASO: Distribution-Aware Semantics-Oriented Pseudo-label for Imbalanced Semi-Supervised Learning
https://github.com/ytongxie/pairaug
공식 코드PairAug: What Can Augmented Image-Text Pairs Do for Radiology?
https://github.com/ytongxie/unimiss-code
공식 코드UniMiSS: Universal Medical Self-Supervised Learning via Breaking Dimensionality Barrier
https://github.com/yu-gi-oh-leilei/sadcl
공식 코드Semantic-Aware Dual Contrastive Learning for Multi-label Image Classification
https://github.com/yu-gi-oh-leilei/trm-ml
공식 코드Text-Region Matching for Multi-Label Image Recognition with Missing Labels
https://github.com/yuanpengtu/DMLP
공식 코드Learning from Noisy Labels with Decoupled Meta Label Purifier
https://github.com/yuanpengtu/SANM
공식 코드Learning with Noisy labels via Self-supervised Adversarial Noisy Masking
https://github.com/yueatsprograms/Stochastic_Depth
공식 코드https://github.com/yueatsprograms/ttt_cifar_release
공식 코드Test-Time Training with Self-Supervision for Generalization under Distribution Shifts
https://github.com/yueatsprograms/ttt_imagenet_release
공식 코드Test-Time Training with Self-Supervision for Generalization under Distribution Shifts
https://github.com/yueliukth/patchdropout
공식 코드PatchDropout: Economizing Vision Transformers Using Patch Dropout
https://github.com/yuexy/PS-ViT
공식 코드https://github.com/yueyang1996/labo
공식 코드https://github.com/yuezuegu/UBoostNAS
공식 코드U-Boost NAS: Utilization-Boosted Differentiable Neural Architecture Search
https://github.com/yuhao318/mwh
공식 코드https://github.com/yuhaozhang/convirt
공식 코드Contrastive Learning of Medical Visual Representations from Paired Images and Text
https://github.com/yuhengsss/vssd
공식 코드https://github.com/yuhuan-wu/P2T
공식 코드https://github.com/yuhui-zh15/vlmclassifier
공식 코드Why are Visually-Grounded Language Models Bad at Image Classification?
https://github.com/yukimasano/self-label
공식 코드Self-labelling via simultaneous clustering and representation learning
https://github.com/yulearningg/LRDG
공식 코드Domain Generalization by Learning and Removing Domain-specific Features
https://github.com/yulu0724/EmbeddingDistillation
공식 코드Learning Metrics from Teachers: Compact Networks for Image Embedding
https://github.com/yun-liu/hat-net
공식 코드https://github.com/yun-liu/tuberculosis
공식 코드https://github.com/yunblak/standalone_16bits_nn
공식 코드Revisiting 16-bit Neural Network Training: A Practical Approach for Resource-Limited Learning
https://github.com/yunkai696/mlcn
공식 코드Multi-Level Correlation Network For Few-Shot Image Classification
https://github.com/yunkun-zhang/cite
공식 코드Text-guided Foundation Model Adaptation for Pathological Image Classification
https://github.com/yupei-wang/uninl
공식 코드https://github.com/yuvalgrin/DetectAndCorrect-Net
공식 코드Detect and Correct: A Selective Noise Correction Method for Learning with Noisy Labels
https://github.com/yuweihao/mambaout
공식 코드https://github.com/yuweisunn/ADA
공식 코드Semi-Targeted Model Poisoning Attack on Federated Learning via Backward Error Analysis
https://github.com/yuweisunn/associative-transformer
공식 코드https://github.com/yuweisunn/federated-knowledge-alignment
공식 코드Feature Distribution Matching for Federated Domain Generalization
https://github.com/yuweisunn/homogeneous-learning
공식 코드Homogeneous Learning: Self-Attention Decentralized Deep Learning
https://github.com/yuxiaoleemarks/cma
공식 코드Concept Matching with Agent for Out-of-Distribution Detection
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.