https://github.com/iCVTEAM/Scob
공식 코드Semantic Contrastive Bootstrapping for Single-positive Multi-label Recognition
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/iCVTEAM/TDRG
공식 코드Transformer-based Dual Relation Graph for Multi-label Image Recognition
https://github.com/iFede94/ArtDL
공식 코드A Data Set and a Convolutional Model for Iconography Classification in Paintings
https://github.com/iQua/CVPR2020-Shoestring
공식 코드Shoestring: Graph-Based Semi-Supervised Learning with Severely Limited Labeled Data
https://github.com/iVMCL/AOGNet-v2
공식 코드https://github.com/iVMCL/AOGNets
공식 코드AOGNets: Compositional Grammatical Architectures for Deep Learning
https://github.com/iamhankai/attribute-aware-attention
공식 코드Attribute-Aware Attention Model for Fine-grained Representation Learning
https://github.com/ianxmason/compositional-robustness
공식 코드https://github.com/ibalazevic/lp-ssl
공식 코드Learning the Prediction Distribution for Semi-Supervised Learning with Normalising Flows
https://github.com/ibcl-anon/ibcl
공식 코드IBCL: Zero-shot Model Generation for Task Trade-offs in Continual Learning
https://github.com/ibm/mimicri
공식 코드https://github.com/ibm/sifar-pytorch
공식 코드https://github.com/ibm/uret
공식 코드https://github.com/ican-szu/lond-drs
공식 코드Learning with Open-world Noisy Data via Class-independent Margin in Dual Representation Space
https://github.com/icgy96/micm
공식 코드MICM: Rethinking Unsupervised Pretraining for Enhanced Few-shot Learning
https://github.com/ichakra2/pca-hybrid
공식 코드https://github.com/iclr-paper/btard
공식 코드https://github.com/iclr2021-paper1937/separation_concentration_deepnets
공식 코드https://github.com/icml24/sparsecbm
공식 코드Sparse Concept Bottleneck Models: Gumbel Tricks in Contrastive Learning
https://github.com/icvteam/part
공식 코드Part-guided Relational Transformers for Fine-grained Visual Recognition
https://github.com/idankdev/helu
공식 코드https://github.com/idegelis/torch-points3d-dc3dcd
공식 코드DC3DCD: unsupervised learning for multiclass 3D point cloud change detection
https://github.com/idelbrid/Randomly-Projected-Additive-GPs
공식 코드Randomly Projected Additive Gaussian Processes for Regression
https://github.com/idiap/importance-sampling
공식 코드Not All Samples Are Created Equal: Deep Learning with Importance Sampling
https://github.com/idsia/automated-cl
공식 코드https://github.com/idstcv/coke
공식 코드Unsupervised Visual Representation Learning by Online Constrained K-Means
https://github.com/idstcv/secu
공식 코드https://github.com/iducvlab/cov19d
공식 코드Deep Learning Based Automated COVID-19 Classification from Computed Tomography Images
https://github.com/iduta/coconv
공식 코드https://github.com/iduta/iresnet
공식 코드https://github.com/iduta/pyconv
공식 코드Pyramidal Convolution: Rethinking Convolutional Neural Networks for Visual Recognition
https://github.com/ieee8023/covid-chestxray-dataset
공식 코드Unveiling COVID-19 from Chest X-ray with deep learning: a hurdles race with small data
https://github.com/ifiaposto/distance_aware_bottleneck
공식 코드https://github.com/ifp-uiuc/an-analysis-of-unsupervised-pre-training-iclr-2015
공식 코드An Analysis of Unsupervised Pre-training in Light of Recent Advances
https://github.com/ifp-uiuc/anna
공식 코드An Analysis of Unsupervised Pre-training in Light of Recent Advances
https://github.com/igor-buzhinsky/latent-space-nn-evaluation
공식 코드Metrics and methods for robustness evaluation of neural networks with generative models
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.