Papers with Code 아카이브

Few-Shot Image Classification

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

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/mayug/basetransformers

공식 코드

BaseTransformers: Attention over base data-points for One Shot Learning

https://github.com/mboudiaf/TIM

공식 코드

Transductive Information Maximization For Few-Shot Learning

https://github.com/mcg-nju/ssd-lt

공식 코드

Self Supervision to Distillation for Long-Tailed Visual Recognition

https://github.com/microsoft/ORBIT-Dataset

공식 코드

ORBIT: A Real-World Few-Shot Dataset for Teachable Object Recognition

https://github.com/mikehuisman/lstm-fewshotlearning-oplstm

공식 코드

Are LSTMs Good Few-Shot Learners?

https://github.com/mikehuisman/subspace-adaptation-prior

공식 코드

Subspace Adaptation Prior for Few-Shot Learning

https://github.com/mileyan/simple_shot

공식 코드

SimpleShot: Revisiting Nearest-Neighbor Classification for Few-Shot Learning

https://github.com/minhanh151/pre

공식 코드

PRE: Vision-Language Prompt Learning with Reparameterization Encoder

https://github.com/minhanh151/respro

공식 코드

PRE: Vision-Language Prompt Learning with Reparameterization Encoder

https://github.com/ml4ai/mliis

공식 코드

Meta-Learning Initializations for Image Segmentation

https://github.com/movinghoon/ESFR

공식 코드

Unsupervised Embedding Adaptation via Early-Stage Feature Reconstruction for Few-Shot Classification

https://github.com/mpatacchiola/contextual-squeeze-and-excitation

공식 코드

Contextual Squeeze-and-Excitation for Efficient Few-Shot Image Classification

https://github.com/mpatacchiola/imujoco

공식 코드

Comparing the Efficacy of Fine-Tuning and Meta-Learning for Few-Shot Policy Imitation

https://github.com/mrkshllr/FewTURE

공식 코드

Rethinking Generalization in Few-Shot Classification

https://github.com/naver-ai/cmo

공식 코드

The Majority Can Help The Minority: Context-rich Minority Oversampling for Long-tailed Classification

https://github.com/nayeemrizve/invariance-equivariance

공식 코드

Exploring Complementary Strengths of Invariant and Equivariant Representations for Few-Shot Learning

https://github.com/nraghuraman/bongard-context

공식 코드

Support-Set Context Matters for Bongard Problems

https://github.com/nupurkmr9/S2M2_fewshot

공식 코드

Charting the Right Manifold: Manifold Mixup for Few-shot Learning

https://github.com/nvlabs/bongard-hoi

공식 코드

Bongard-HOI: Benchmarking Few-Shot Visual Reasoning for Human-Object Interactions

https://github.com/ojss/c3lr

공식 코드

Self-Supervised Class-Cognizant Few-Shot Classification

https://github.com/ojss/samptransfer

공식 코드

Self-Attention Message Passing for Contrastive Few-Shot Learning

https://github.com/open-debin/bayesian_mqda

공식 코드

Shallow Bayesian Meta Learning for Real-World Few-Shot Recognition

https://github.com/openai/CLIP

공식 코드

Learning Transferable Visual Models From Natural Language Supervision

https://github.com/openai/supervised-reptile

공식 코드

On First-Order Meta-Learning Algorithms

https://github.com/oveilleux/realistic_transductive_few_shot

공식 코드

Realistic Evaluation of Transductive Few-Shot Learning

https://github.com/pandeydeep9/units-ml-cvpr-22

공식 코드

Multidimensional Belief Quantification for Label-Efficient Meta-Learning

https://github.com/pixwse/tiny2

공식 코드

Tiny models from tiny data: Textual and null-text inversion for few-shot distillation

https://github.com/plai-group/simple-cnaps

공식 코드

Improved Few-Shot Visual Classification

https://github.com/pris-cv/bi-frn

공식 코드

Bi-directional Feature Reconstruction Network for Fine-Grained Few-Shot Image Classification

https://github.com/pseulki/ib-loss

공식 코드

Influence-Balanced Loss for Imbalanced Visual Classification

https://github.com/raflaf/few-and-fewer

공식 코드

Few and Fewer: Learning Better from Few Examples Using Fewer Base Classes

https://github.com/rahulvigneswaran/tailcalibx

공식 코드

Feature Generation for Long-tail Classification

https://github.com/remiMZ/HTS-ECCV22

공식 코드

Tree Structure-Aware Few-Shot Image Classification via Hierarchical Aggregation

https://github.com/richard-peng-xia/LMPT

공식 코드

LMPT: Prompt Tuning with Class-Specific Embedding Loss for Long-tailed Multi-Label Visual Recognition

https://github.com/richardaecn/class-balanced-loss

공식 코드

Class-Balanced Loss Based on Effective Number of Samples

https://github.com/rl-vig/libfewshot

공식 코드

LibFewShot: A Comprehensive Library for Few-shot Learning

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.