https://github.com/skrantidatta/Attention-based-Skin-Cancer-Classification
공식 코드Soft-Attention Improves Skin Cancer Classification Performance
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/skyoux/SemAIM
공식 코드Semantic-Aware Autoregressive Image Modeling for Visual Representation Learning
https://github.com/skyz215/proco
공식 코드ProCo: Prototype-aware Contrastive Learning for Long-tailed Medical Image Classification
https://github.com/slavikkom/focal_temperature_scaling
공식 코드Improving Calibration by Relating Focal Loss, Temperature Scaling, and Properness
https://github.com/sldgroup/gradientfilter-cvpr23
공식 코드https://github.com/sldgroup/mobilevig
공식 코드MobileViG: Graph-Based Sparse Attention for Mobile Vision Applications
https://github.com/sldgroup/mobilevigv2
공식 코드https://github.com/slds-lmu/wildlife-experiments
공식 코드Automated wildlife image classification: An active learning tool for ecological applications
https://github.com/slds-lmu/wildlife-ml
공식 코드Automated wildlife image classification: An active learning tool for ecological applications
https://github.com/sli057/Geo-TRAP
공식 코드https://github.com/smahdavi4/attention-memorization
공식 코드Memorization Capacity of Multi-Head Attention in Transformers
https://github.com/smilelab-fl/fednoisy
공식 코드https://github.com/smlab-niser/23retinald
공식 코드https://github.com/smlaine2/tempens
공식 코드https://github.com/snap-stanford/comet
공식 코드https://github.com/snap-stanford/csr
공식 코드Few-shot Relational Reasoning via Connection Subgraph Pretraining
https://github.com/snap-stanford/orca
공식 코드https://github.com/sndnyang/Diffusion_ViT
공식 코드Your ViT is Secretly a Hybrid Discriminative-Generative Diffusion Model
https://github.com/sndnyang/GMMC
공식 코드Generative Max-Mahalanobis Classifiers for Image Classification, Generation and More
https://github.com/sndnyang/sadajem
공식 코드Towards Bridging the Performance Gaps of Joint Energy-based Models
https://github.com/snowood1/BERT-ENN
공식 코드https://github.com/snowood1/wenn
공식 코드Multidimensional Uncertainty-Aware Evidential Neural Networks
https://github.com/snu-mllab/PuzzleMix
공식 코드Puzzle Mix: Exploiting Saliency and Local Statistics for Optimal Mixup
https://github.com/snu-mllab/layermerge
공식 코드LayerMerge: Neural Network Depth Compression through Layer Pruning and Merging
https://github.com/snu-mllab/neural-relation-graph
공식 코드Neural Relation Graph: A Unified Framework for Identifying Label Noise and Outlier Data
https://github.com/softsys4ai/cl-robustness
공식 코드Rethinking Robust Contrastive Learning from the Adversarial Perspective
https://github.com/soham-chitnis10/WSI-domain-specific
공식 코드Domain-Specific Pre-training Improves Confidence in Whole Slide Image Classification
https://github.com/soheilb/multimodal_dictionary_learning
공식 코드Multimodal Task-Driven Dictionary Learning for Image Classification
https://github.com/solarlee/fewsar
공식 코드https://github.com/solgaardlab/neurophox
공식 코드https://github.com/solicucu/ReID
공식 코드Combined Depth Space based Architecture Search For Person Re-identification
https://github.com/somepago/AMA
공식 코드Unsupervised Anomaly Detection with Adversarial Mirrored AutoEncoders
https://github.com/songheony/TAkS
공식 코드https://github.com/sonycslparis/deep_srda
공식 코드Continual Learning with Deep Streaming Regularized Discriminant Analysis
https://github.com/soochan-lee/CN-DPM
공식 코드A Neural Dirichlet Process Mixture Model for Task-Free Continual Learning
https://github.com/sooperset/boss
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.