https://github.com/ShimSoonYong/ZClassifier
공식 코드ZClassifier: Temperature Tuning and Manifold Approximation via KL Divergence on Logit Space
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/Shiweiliuiiiiiii/FreeTickets
공식 코드https://github.com/ShoufaChen/CycleMLP
공식 코드https://github.com/Shounak-D/LexiBoost
공식 코드Boosting with Lexicographic Programming: Addressing Class Imbalance without Cost Tuning
https://github.com/Shrey-55/MalwareClassification
공식 코드Accelerating Malware Classification: A Vision Transformer Solution
https://github.com/Shu1L0n9/SemiOccam
공식 코드ViTSGMM: A Robust Semi-Supervised Image Recognition Network Using Sparse Labels
https://github.com/Shuangfei/s3pool
공식 코드https://github.com/ShuvozitGhose/Ground-Terrain-EoT
공식 코드Modeling Extent-of-Texture Information for Ground Terrain Recognition
https://github.com/SinaHonari/RCN
공식 코드Recombinator Networks: Learning Coarse-to-Fine Feature Aggregation
https://github.com/Singular-Brain/BioLCNet
공식 코드BioLCNet: Reward-modulated Locally Connected Spiking Neural Networks
https://github.com/SmartEngines/bipolar-morphological-resnet
공식 코드https://github.com/So-Cool/bLIMEy
공식 코드https://github.com/Spark001/AsymmNet
공식 코드AsymmNet: Towards ultralight convolution neural networks using asymmetrical bottlenecks
https://github.com/Sparkier/Classifier-Guided-Correction
공식 코드Classifier-Guided Visual Correction of Noisy Labels for Image Classification Tasks
https://github.com/Sprakbanken/CHR24-image-retrieval
공식 코드https://github.com/StanfordASL/moca
공식 코드https://github.com/StanfordASL/rover-meta-learning
공식 코드Adaptive Meta-Learning for Identification of Rover-Terrain Dynamics
https://github.com/Starscream-11813/HaSPeR
공식 코드HaSPeR: An Image Repository for Hand Shadow Puppet Recognition
https://github.com/StephenEkaputra/Swapped-Logit-Distillation
공식 코드https://github.com/Sufianlab/BDNet
공식 코드https://github.com/Sulam-Group/IBYDMT
공식 코드I Bet You Did Not Mean That: Testing Semantic Importance via Betting
https://github.com/Sulam-Group/h-shap
공식 코드https://github.com/Sulam-Group/pragmatixs
공식 코드https://github.com/Sunnydreamrain/IndRNN_Theano_Lasagne
공식 코드Independently Recurrent Neural Network (IndRNN): Building A Longer and Deeper RNN
https://github.com/Sunnydreamrain/IndRNN_pytorch
공식 코드https://github.com/SwinTransformer/Feature-Distillation
공식 코드Contrastive Learning Rivals Masked Image Modeling in Fine-tuning via Feature Distillation
https://github.com/SwinTransformer/Transformer-SSL
공식 코드https://github.com/SymbioticLab/FedScale
공식 코드FedScale: Benchmarking Model and System Performance of Federated Learning at Scale
https://github.com/T-Ratchatorn/AACE
공식 코드Adaptive Adversarial Cross-Entropy Loss for Sharpness-Aware Minimization
https://github.com/TACJu/TransFG
공식 코드TransFG: A Transformer Architecture for Fine-grained Recognition
https://github.com/TAMU-VITA/AutoGAN
공식 코드AutoGAN: Neural Architecture Search for Generative Adversarial Networks
https://github.com/TAMU-VITA/AutoSpeech
공식 코드AutoSpeech: Neural Architecture Search for Speaker Recognition
https://github.com/TAMU-VITA/Focus-Longer-to-See-Better
공식 코드Focus Longer to See Better:Recursively Refined Attention for Fine-Grained Image Classification
https://github.com/TAMU-VITA/MAD
공식 코드I Am Going MAD: Maximum Discrepancy Competition for Comparing Classifiers Adaptively
https://github.com/THUYimingLi/Open-sourced_Dataset_Protection
공식 코드https://github.com/TIBHannover/VisE
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.