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/wangck20/idml
공식 코드https://github.com/wangck20/opera
공식 코드OPERA: Omni-Supervised Representation Learning with Hierarchical Supervisions
https://github.com/wanggrun/Adaptively-Connected-Neural-Networks
공식 코드https://github.com/wanggrun/triplet
공식 코드Solving Inefficiency of Self-supervised Representation Learning
https://github.com/wangguanan/denoiserep
공식 코드https://github.com/wanggynpuer/3d-rcnet
공식 코드https://github.com/wanghangpsu/acgan-ada
공식 코드Anomaly Detection of Adversarial Examples using Class-conditional Generative Adversarial Networks
https://github.com/wanghangpsu/mmac
공식 코드Improved Activation Clipping for Universal Backdoor Mitigation and Test-Time Detection
https://github.com/wangke97/clad
공식 코드CLAD: A Contrastive Learning based Approach for Background Debiasing
https://github.com/wangren09/RAILS
공식 코드https://github.com/wangsr126/mae-lite
공식 코드A Closer Look at Self-Supervised Lightweight Vision Transformers
https://github.com/wangwenhao0716/transhp
공식 코드https://github.com/wangye8899/bmec
공식 코드https://github.com/wangyi111/cvppa2023-dnd-challenge
공식 코드Boosting High Resolution Image Classification with Scaling-up Transformers
https://github.com/wanifarooq/ncod
공식 코드Learning with Noisy Labels through Learnable Weighting and Centroid Similarity
https://github.com/warisgill/FedDefender
공식 코드https://github.com/warisgill/tracefl
공식 코드TraceFL: Interpretability-Driven Debugging in Federated Learning via Neuron Provenance
https://github.com/waveboo/clis
공식 코드https://github.com/wbw520/MTUNet
공식 코드Match Them Up: Visually Explainable Few-shot Image Classification
https://github.com/wbw520/botcl
공식 코드https://github.com/we1pingyu/CALD
공식 코드https://github.com/webstorms/fastsnn
공식 코드https://github.com/weeknan/dr-tune
공식 코드https://github.com/weihua916/imsat
공식 코드Learning Discrete Representations via Information Maximizing Self-Augmented Training
https://github.com/weijiaheng/Robust-f-divergence-measures
공식 코드https://github.com/weijiemax/cpc-trans
공식 코드https://github.com/weiwenjiang/QML_tutorial
공식 코드https://github.com/wen-yan-lin/Image-Distance-Classification
공식 코드Distance Based Image Classification: A solution to generative classification's conundrum?
https://github.com/wenbinlee/trip-roma
공식 코드Trip-ROMA: Self-Supervised Learning with Triplets and Random Mappings
https://github.com/wenchen-chen/s4l-fsc
공식 코드Spectral-Spatial Self-Supervised Learning for Few-Shot Hyperspectral Image Classification
https://github.com/wencheng-zhu/ckd
공식 코드CKD: Contrastive Knowledge Distillation from A Sample-wise Perspective
https://github.com/wengzejia1/semiformer
공식 코드https://github.com/wenhui0206/MeanTeacher-DeepMedic
공식 코드Semi-Supervised Brain Lesion Segmentation with an Adapted Mean Teacher Model
https://github.com/wenhui0206/Robust-TransBTS
공식 코드https://github.com/wenjiaxu/rs_scene_zsl
공식 코드Deep Semantic-Visual Alignment for Zero-Shot Remote Sensing Image Scene Classification
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.