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/AI-secure/multi-task-learning

공식 코드

Bridging Multi-Task Learning and Meta-Learning: Towards Efficient Training and Effective Adaptation

https://github.com/AceChuse/TaskLevelAug

공식 코드

Task Augmentation by Rotating for Meta-Learning

https://github.com/Alibaba-AAIG/SSL-FEW-SHOT

공식 코드

Self-Supervised Learning For Few-Shot Image Classification

https://github.com/ArchitParnami/Few-Shot-Privacy

공식 코드

Privacy Enhancement for Cloud-Based Few-Shot Learning

https://github.com/AutoVision-cloud/SSL-ViT-lowlabel-highdata

공식 코드

Visual Representation Learning with Self-Supervised Attention for Low-Label High-data Regime

https://github.com/AutodeskAILab/UVStyle-Net

공식 코드

UVStyle-Net: Unsupervised Few-shot Learning of 3D Style Similarity Measure for B-Reps

https://github.com/BIT-DA/MetaSAug

공식 코드

MetaSAug: Meta Semantic Augmentation for Long-Tailed Visual Recognition

https://github.com/BatsResearch/efsl

공식 코드

Extended Few-Shot Learning: Exploiting Existing Resources for Novel Tasks

https://github.com/BayesWatch/deep-kernel-transfer

공식 코드

Bayesian Meta-Learning for the Few-Shot Setting via Deep Kernels

https://github.com/Boyiliee/SITT

공식 코드

SITTA: Single Image Texture Translation for Data Augmentation

https://github.com/ChangyaoTian/VL-LTR

공식 코드

VL-LTR: Learning Class-wise Visual-Linguistic Representation for Long-Tailed Visual Recognition

https://github.com/Computer-Vision-in-the-Wild/Elevater_Toolkit_IC

공식 코드

ELEVATER: A Benchmark and Toolkit for Evaluating Language-Augmented Visual Models

https://github.com/DominikFilipiak/KGTN-ens

공식 코드

KGTN-ens: Few-Shot Image Classification with Knowledge Graph Ensembles

https://github.com/ElementAI/embedding-propagation

공식 코드

Embedding Propagation: Smoother Manifold for Few-Shot Classification

https://github.com/EliSchwartz/DeltaEncoder

공식 코드

Delta-encoder: an effective sample synthesis method for few-shot object recognition

https://github.com/FannierPeng/SgVA-CLIP

공식 코드

SgVA-CLIP: Semantic-guided Visual Adapting of Vision-Language Models for Few-shot Image Classification

https://github.com/FatemehAskari/MSENet

공식 코드

Enhancing Few-Shot Image Classification through Learnable Multi-Scale Embedding and Attention Mechanisms

https://github.com/Fei-Long121/DeepBDC

공식 코드

Joint Distribution Matters: Deep Brownian Distance Covariance for Few-Shot Classification

https://github.com/Frankluox/Channel_Importance_FSL

공식 코드

Channel Importance Matters in Few-Shot Image Classification

https://github.com/Frankluox/FewShotCodeBase

공식 코드

Rectifying the Shortcut Learning of Background for Few-Shot Learning

https://github.com/Frozenmad/MetaDelta

공식 코드

MetaDelta: A Meta-Learning System for Few-shot Image Classification

https://github.com/Gordonjo/versa

공식 코드

Meta-Learning Probabilistic Inference For Prediction

https://github.com/HIK-LAB/Unsupervised-Image-Classification

공식 코드

Unsupervised Image Classification for Deep Representation Learning

https://github.com/IRVLUTD/Proto-CLIP

공식 코드

Proto-CLIP: Vision-Language Prototypical Network for Few-Shot Learning

https://github.com/JBall1/Few-Shot-Limited-Data

공식 코드

Few-Shot Learning for Image Classification of Common Flora

https://github.com/Jia-Research-Lab/MiSLAS

공식 코드

Improving Calibration for Long-Tailed Recognition

https://github.com/Jianf-Wang/RSG

공식 코드

RSG: A Simple but Effective Module for Learning Imbalanced Datasets

https://github.com/KMnP/vpt

공식 코드

Visual Prompt Tuning

https://github.com/KaihuaTang/Long-Tailed-Recognition.pytorch

공식 코드

Long-Tailed Classification by Keeping the Good and Removing the Bad Momentum Causal Effect

https://github.com/KhrulkovV/hyperbolic-image-embeddings

공식 코드

Hyperbolic Image Embeddings

https://github.com/LeoYu/neural-tangent-kernel-UCI

공식 코드

Harnessing the Power of Infinitely Wide Deep Nets on Small-data Tasks

https://github.com/MCG-NJU/AWT

공식 코드

AWT: Transferring Vision-Language Models via Augmentation, Weighting, and Transportation

https://github.com/Megvii-BaseDetection/DisAlign

공식 코드

Distribution Alignment: A Unified Framework for Long-tail Visual Recognition

https://github.com/Megvii-Nanjing/BBN

공식 코드

BBN: Bilateral-Branch Network with Cumulative Learning for Long-Tailed Visual Recognition

https://github.com/MyChocer/KGTN

공식 코드

Knowledge Graph Transfer Network for Few-Shot Recognition

https://github.com/NeuralCollapseApplications/ImbalancedLearning

공식 코드

Inducing Neural Collapse in Imbalanced Learning: Do We Really Need a Learnable Classifier at the End of Deep Neural Network?

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