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/fewclassarena/fca
공식 코드https://github.com/feyzaakyurek/subspace-reg
공식 코드Subspace Regularizers for Few-Shot Class Incremental Learning
https://github.com/ffiirree/cv-models/blob/master/cvm/models/vgnet.py
공식 코드https://github.com/ffyyytt/defactify4
공식 코드Scalable Framework for Classifying AI-Generated Content Across Modalities
https://github.com/fgnt/pb_chime5
공식 코드https://github.com/fhn98/dac
공식 코드Decompose-and-Compose: A Compositional Approach to Mitigating Spurious Correlation
https://github.com/filipe-research/LongReMix
공식 코드LongReMix: Robust Learning with High Confidence Samples in a Noisy Label Environment
https://github.com/filipe-research/anne
공식 코드https://github.com/filipe-research/propmix
공식 코드PropMix: Hard Sample Filtering and Proportional MixUp for Learning with Noisy Labels
https://github.com/filipgdorm/binary_range_maps
공식 코드https://github.com/fillassuncao/denser-models
공식 코드https://github.com/fir-lat/hamos_ood
공식 코드Outlier Synthesis via Hamiltonian Monte Carlo for Out-of-Distribution Detection
https://github.com/firojalam/medic
공식 코드MEDIC: A Multi-Task Learning Dataset for Disaster Image Classification
https://github.com/fistyee/LTRL
공식 코드LTRL: Boosting Long-tail Recognition via Reflective Learning
https://github.com/fistyee/mdcs
공식 코드MDCS: More Diverse Experts with Consistency Self-distillation for Long-tailed Recognition
https://github.com/fistyee/mixpro
공식 코드MixPro: Data Augmentation with MaskMix and Progressive Attention Labeling for Vision Transformer
https://github.com/fiveai/making-better-mistakes
공식 코드Making Better Mistakes: Leveraging Class Hierarchies with Deep Networks
https://github.com/fjelenic/between-layer-ood
공식 코드Out-of-Distribution Detection by Leveraging Between-Layer Transformation Smoothness
https://github.com/flagai-open/flagai
공식 코드AltCLIP: Altering the Language Encoder in CLIP for Extended Language Capabilities
https://github.com/flamiezhu/bcl
공식 코드Balanced Contrastive Learning for Long-Tailed Visual Recognition
https://github.com/florentinguth/rainbow
공식 코드https://github.com/flowersteam/picture-word-interference
공식 코드Language-biased image classification: evaluation based on semantic representations
https://github.com/fmcarlucci/JigenDG
공식 코드https://github.com/fmorenovr/WSAM_Style
공식 코드https://github.com/foiv0s/imc-swav-pub
공식 코드Information Maximization Clustering via Multi-View Self-Labelling
https://github.com/forAcadamic/T-CAD
공식 코드TAD: A Large-Scale Benchmark for Traffic Accidents Detection from Video Surveillance
https://github.com/foreverzyh/defend_framework
공식 코드https://github.com/fostiropoulos/stream_benchmark
공식 코드Batch Model Consolidation: A Multi-Task Model Consolidation Framework
https://github.com/fourierai/idea
공식 코드https://github.com/fpoms/background-splitting
공식 코드Background Splitting: Finding Rare Classes in a Sea of Background
https://github.com/fpsluozi/smd-smos-proj
공식 코드https://github.com/fra31/evaluating-adaptive-test-time-defenses
공식 코드Evaluating the Adversarial Robustness of Adaptive Test-time Defenses
https://github.com/francesc0de/holmes
공식 코드HOLMES: HOLonym-MEronym based Semantic inspection for Convolutional Image Classifiers
https://github.com/frank-xwang/CLD-UnsupervisedLearning
공식 코드Unsupervised Feature Learning by Cross-Level Instance-Group Discrimination
https://github.com/frank-xwang/RIDE-LongTailRecognition
공식 코드Long-tailed Recognition by Routing Diverse Distribution-Aware Experts
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.