Papers with Code 아카이브
Few-Shot Image Classification
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 3
- 평가표
- 89
- 보존된 평가 기록
- 913
Few-Shot Image Classification is a computer vision task that involves training machine learning models to classify images into predefined categories using only a few labeled examples of each category (typically < 6 examples). The goal is to enable models to recognize and classify new images with minimal supervision and limited data, without having to train on large datasets. (typically < 6 examples)
<span style="color:grey; opacity: 0.6">( Image credit: Learning Embedding Adaptation for Few-Shot Learning )</span>
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/indy-lab/ProtoTransfer
공식 코드Self-Supervised Prototypical Transfer Learning for Few-Shot Classification
https://github.com/istarjun/TapNet
공식 코드TapNet: Neural Network Augmented with Task-Adaptive Projection for Few-Shot Learning
https://github.com/jaeill/CVPR23-VNE
공식 코드VNE: An Effective Method for Improving Deep Representation by Manipulating Eigenvalue Distribution
https://github.com/jakesnell/prototypical-networks
공식 코드https://github.com/jayanthkoushik/alphanet
공식 코드AlphaNet: Improving Long-Tail Classification By Combining Classifiers
https://github.com/jianhongbai/colt
공식 코드On the Effectiveness of Out-of-Distribution Data in Self-Supervised Long-Tail Learning
https://github.com/jiawei-ren/BalancedMetaSoftmax
공식 코드https://github.com/jiequancui/Parametric-Contrastive-Learning
공식 코드https://github.com/jiequancui/ResLT
공식 코드https://github.com/jingchensun/prompt_adapter
공식 코드Prompt Tuning based Adapter for Vision-Language Model Adaption
https://github.com/jinxu06/metafun-tensorflow
공식 코드https://github.com/jjongyn/cml
공식 코드https://github.com/juho-lee/set_transformer
공식 코드Set Transformer: A Framework for Attention-based Permutation-Invariant Neural Networks
https://github.com/juyongjiang/fbl
공식 코드https://github.com/kaidic/LDAM-DRW
공식 코드Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss
https://github.com/kaihuatang/generalized-long-tailed-benchmarks.pytorch
공식 코드Invariant Feature Learning for Generalized Long-Tailed Classification
https://github.com/kaipengm2/DiffKendall
공식 코드DiffKendall: A Novel Approach for Few-Shot Learning with Differentiable Kendall's Rank Correlation
https://github.com/keke921/gclloss
공식 코드Long-tailed Visual Recognition via Gaussian Clouded Logit Adjustment
https://github.com/keke921/gnm-pt
공식 코드https://github.com/khy0809/fewshot-egnn
공식 코드https://github.com/kjunelee/MetaOptNet
공식 코드https://github.com/kkalais/stochlwta-ml
공식 코드Stochastic Deep Networks with Linear Competing Units for Model-Agnostic Meta-Learning
https://github.com/kostas1515/aglu
공식 코드https://github.com/lanfenghuanyu/Sill-Net
공식 코드Sill-Net: Feature Augmentation with Separated Illumination Representation
https://github.com/lblaoke/tlc
공식 코드https://github.com/leaplabthu/proco
공식 코드Probabilistic Contrastive Learning for Long-Tailed Visual Recognition
https://github.com/leesb7426/cvpr2022-task-discrepancy-maximization-for-fine-grained-few-shot-classification
공식 코드Task Discrepancy Maximization for Fine-grained Few-Shot Classification
https://github.com/leymir/hyperbolic-image-embeddings
공식 코드https://github.com/liulu112601/Gated-Propagation-Net
공식 코드https://github.com/liulu112601/URT
공식 코드A Universal Representation Transformer Layer for Few-Shot Image Classification
https://github.com/lth14/targeted-supcon
공식 코드Targeted Supervised Contrastive Learning for Long-Tailed Recognition
https://github.com/lumia-group/lot-insts
공식 코드Text Classification in the Wild: a Large-scale Long-tailed Name Normalization Dataset
https://github.com/marclafon/gallop
공식 코드GalLoP: Learning Global and Local Prompts for Vision-Language Models
https://github.com/mayanbiao1234/geometric-metrics-for-perceptual-manifolds
공식 코드Predicting and Enhancing the Fairness of DNNs with the Curvature of Perceptual Manifolds
https://github.com/mayanbiao1234/geometric-metrics-for-perceptual-manifolds-in-deep-neural-networks
공식 코드Predicting and Enhancing the Fairness of DNNs with the Curvature of Perceptual Manifolds
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.