https://github.com/shuguoj/hsi-classification
공식 코드A Survey: Deep Learning for Hyperspectral Image Classification with Few Labeled Samples
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/shuolucs/awesome-out-of-distribution-detection
공식 코드https://github.com/shuvenduroy/unmixmatch
공식 코드Scaling Up Semi-supervised Learning with Unconstrained Unlabelled Data
https://github.com/shuyao95/Understanding-NAS
공식 코드Understanding Architectures Learnt by Cell-based Neural Architecture Search
https://github.com/shwai-he/pad-net
공식 코드https://github.com/shwangtangjun/Diff-ResNet
공식 코드Diffusion Mechanism in Residual Neural Network: Theory and Applications
https://github.com/shwetabhardwaj44/RecoveringFrom_RandomPruning_WACV2018
공식 코드Recovering from Random Pruning: On the Plasticity of Deep Convolutional Neural Networks
https://github.com/shyamvarahagiri/3d-convsst
공식 코드3D-Convolution Guided Spectral-Spatial Transformer for Hyperspectral Image Classification
https://github.com/shyhyawJou/ExquisiteNetV2
공식 코드A Novel lightweight Convolutional Neural Network, ExquisiteNetV2
https://github.com/sicara/semantic-task-sampling
공식 코드https://github.com/sigma10010/histo_img_cls
공식 코드https://github.com/sike-wang/low-bit-shampoo
공식 코드https://github.com/silverbottlep/meta_curvature
공식 코드https://github.com/silverriver/ood4nlu
공식 코드Out-of-domain Detection for Natural Language Understanding in Dialog Systems
https://github.com/silviogalesso/dense-ood-knns
공식 코드Far Away in the Deep Space: Dense Nearest-Neighbor-Based Out-of-Distribution Detection
https://github.com/simonbon/fishing
공식 코드FISHing in Uncertainty: Synthetic Contrastive Learning for Genetic Aberration Detection
https://github.com/simonzhou86/evolutionarycomputing
공식 코드Heuristic Hyperparameter Optimization for Convolutional Neural Networks using Genetic Algorithm
https://github.com/sindish/unitedwelearn
공식 코드United We Learn Better: Harvesting Learning Improvements From Class Hierarchies Across Tasks
https://github.com/sing-group/deep-learning-colonoscopy
공식 코드https://github.com/sinhasam/vaal
공식 코드https://github.com/sinzlab/neural_cotraining
공식 코드Towards robust vision by multi-task learning on monkey visual cortex
https://github.com/siomvas/ARIA
공식 코드https://github.com/sipkatom/The-Hitchhiker-s-Guide-to-Prior-Shift-Adaptation
공식 코드https://github.com/sixin-zh/mpiT
공식 코드https://github.com/siyi-wind/mdvit
공식 코드MDViT: Multi-domain Vision Transformer for Small Medical Image Segmentation Datasets
https://github.com/siyuanyan1/pldg
공식 코드Prompt-driven Latent Domain Generalization for Medical Image Classification
https://github.com/siyuhuang/TOD
공식 코드Semi-Supervised Active Learning with Temporal Output Discrepancy
https://github.com/sjames40/smug_journal
공식 코드https://github.com/sjtudyq/fedconcat
공식 코드Exploiting Label Skews in Federated Learning with Model Concatenation
https://github.com/sjyang8/SLAP
공식 코드https://github.com/skddj/loldu
공식 코드LoLDU: Low-Rank Adaptation via Lower-Diag-Upper Decomposition for Parameter-Efficient Fine-Tuning
https://github.com/skeskinen/pairwise_online_learning
공식 코드Task agnostic continual learning with Pairwise layer architecture
https://github.com/skhaki18/optin-transformer-pruning
공식 코드https://github.com/skokec/DAU-ConvNet
공식 코드https://github.com/skokec/DAU-ConvNet-TF
공식 코드Spatially-Adaptive Filter Units for Compact and Efficient Deep Neural Networks
https://github.com/skokec/DAU-ConvNet-caffe
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.