https://github.com/LeapLabTHU/CheXWorld
공식 코드CheXWorld: Exploring Image World Modeling for Radiograph Representation Learning
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/LeapLabTHU/LearnableISDA
공식 코드Fine-grained Recognition with Learnable Semantic Data Augmentation
https://github.com/LeapLabTHU/MLLA
공식 코드https://github.com/Lee-Gihun/FedSOL
공식 코드FedSOL: Stabilized Orthogonal Learning with Proximal Restrictions in Federated Learning
https://github.com/LeoYu/neural-tangent-kernel-UCI
공식 코드Harnessing the Power of Infinitely Wide Deep Nets on Small-data Tasks
https://github.com/LeungSamWai/Drop-Activation
공식 코드Drop-Activation: Implicit Parameter Reduction and Harmonic Regularization
https://github.com/LiJunnan1992/DivideMix
공식 코드DivideMix: Learning with Noisy Labels as Semi-supervised Learning
https://github.com/LiJunnan1992/MLNT
공식 코드https://github.com/LiQiufu/WaveCNet
공식 코드Wavelet Integrated CNNs for Noise-Robust Image Classification
https://github.com/LiYingwei/AutoNL
공식 코드Neural Architecture Search for Lightweight Non-Local Networks
https://github.com/LiYingwei/ShapeTextureDebiasedTraining
공식 코드https://github.com/LiYinqi/DIVE
공식 코드DIVE: Inverting Conditional Diffusion Models for Discriminative Tasks
https://github.com/LiheYoung/ShrinkMatch
공식 코드Shrinking Class Space for Enhanced Certainty in Semi-Supervised Learning
https://github.com/LinLabNEU/Blackbox_ADMM
공식 코드https://github.com/LinLabNEU/ZO_NGD_blackbox
공식 코드Towards Query-Efficient Black-Box Adversary with Zeroth-Order Natural Gradient Descent
https://github.com/LinShiqi047/PatchAutoAugment
공식 코드https://github.com/Lingkai-Kong/Calibrated-BERT-Fine-Tuning
공식 코드Calibrated Language Model Fine-Tuning for In- and Out-of-Distribution Data
https://github.com/LiyuanLucasLiu/RAdam
공식 코드https://github.com/LucaHermes/DeepView
공식 코드https://github.com/LucasKookUZH/ontram-paper
공식 코드Deep and interpretable regression models for ordinal outcomes
https://github.com/LukasHaas/PIGEON
공식 코드https://github.com/M4xim4l/InNOutRobustness
공식 코드Adversarial Robustness on In- and Out-Distribution Improves Explainability
https://github.com/MCG-NJU/AWT
공식 코드AWT: Transferring Vision-Language Models via Augmentation, Weighting, and Transportation
https://github.com/MECLabTUDA/Lifelong-nnUNet
공식 코드https://github.com/MHmi1/Image_Denoising_Classification
공식 코드Assessing The Impact of CNN Auto Encoder-Based Image Denoising on Image Classification Tasks
https://github.com/MIT-HAN-LAB/ProxylessNAS
공식 코드ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware
https://github.com/MJ10/DEUP
공식 코드https://github.com/ML-GSAI/Revisiting-Dis-vs-Gen-Classifiers
공식 코드Revisiting Discriminative vs. Generative Classifiers: Theory and Implications
https://github.com/MLI-lab/candidate_training
공식 코드Image recognition from raw labels collected without annotators
https://github.com/MStamatis/ALReLU
공식 코드https://github.com/MTLab/MorphMLP
공식 코드MorphMLP: An Efficient MLP-Like Backbone for Spatial-Temporal Representation Learning
https://github.com/MadryLab/ImageNetMultiLabel
공식 코드From ImageNet to Image Classification: Contextualizing Progress on Benchmarks
https://github.com/MadryLab/cifar10_challenge
공식 코드Towards Deep Learning Models Resistant to Adversarial Attacks
https://github.com/MadryLab/mnist_challenge
공식 코드Towards Deep Learning Models Resistant to Adversarial Attacks
https://github.com/MahmudulHasan11085/Vision-Eagle-Attention
공식 코드Vision Eagle Attention: a new lens for advancing image classification
https://github.com/Makbari1997/VAE-KPCA-HDBSCAN
공식 코드A Hybrid Architecture for Out of Domain Intent Detection and Intent Discovery
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.