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/brjathu/SKD

공식 코드

Self-supervised Knowledge Distillation for Few-shot Learning

https://github.com/cambridge-mlg/LITE

공식 코드

Memory Efficient Meta-Learning with Large Images

https://github.com/cambridge-mlg/cnaps

공식 코드

Fast and Flexible Multi-Task Classification Using Conditional Neural Adaptive Processes

https://github.com/cambridge-mlg/dp-few-shot

공식 코드

On the Efficacy of Differentially Private Few-shot Image Classification

https://github.com/cbfinn/maml

공식 코드

Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks

https://github.com/cbfinn/maml_rl

공식 코드

Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks

https://github.com/cfifty/CAML

공식 코드

Context-Aware Meta-Learning

https://github.com/chenfan95/sign-maml

공식 코드

Sign-MAML: Efficient Model-Agnostic Meta-Learning by SignSGD

https://github.com/chengcv/dfrfs

공식 코드

Disentangled Feature Representation for Few-shot Image Classification

https://github.com/chenhaoxing/ssformers

공식 코드

Sparse Spatial Transformers for Few-Shot Learning

https://github.com/chrisyxue/RCN_for_Interpretable_few_shot

공식 코드

Region Comparison Network for Interpretable Few-shot Image Classification

https://github.com/cnguyen10/few_shot_meta_learning

공식 코드

Uncertainty in Model-Agnostic Meta-Learning using Variational Inference

https://github.com/cogentlabs/apl

공식 코드

Adaptive Posterior Learning: few-shot learning with a surprise-based memory module

https://github.com/computer-vision-in-the-wild/cvinw_readings

공식 코드

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

https://github.com/csyanbin/TPN-pytorch

공식 코드

Learning to Propagate Labels: Transductive Propagation Network for Few-shot Learning

https://github.com/ctom2/latent-space-transform

공식 코드

Transfer learning based few-shot classification using optimal transport mapping from preprocessed latent space of backbone neural network

https://github.com/cvlab-stonybrook/ls-sample-quality

공식 코드

Assessing Sample Quality via the Latent Space of Generative Models

https://github.com/dahyun-kang/renet

공식 코드

Relational Embedding for Few-Shot Classification

https://github.com/danielshalam/bpa

공식 코드

The Self-Optimal-Transport Feature Transform

https://github.com/dgshin21/rna

공식 코드

Representation Norm Amplification for Out-of-Distribution Detection in Long-Tail Learning

https://github.com/dongsky/lpt

공식 코드

LPT: Long-tailed Prompt Tuning for Image Classification

https://github.com/dustincarrion/cd-metadl

공식 코드

Meta-Album: Multi-domain Meta-Dataset for Few-Shot Image Classification

https://github.com/dvirsamuel/DRAGON

공식 코드

From Generalized zero-shot learning to long-tail with class descriptors

https://github.com/dvirsamuel/SeedSelect

공식 코드

Norm-guided latent space exploration for text-to-image generation

https://github.com/dvlab-research/parametric-contrastive-learning

공식 코드

Parametric Contrastive Learning

https://github.com/dvlab-research/rescom

공식 코드

Rebalanced Siamese Contrastive Mining for Long-Tailed Recognition

https://github.com/dvornikita/SUR

공식 코드

Selecting Relevant Features from a Multi-domain Representation for Few-shot Classification

https://github.com/ebennequin/FewShotVision

공식 코드

Meta-learning algorithms for Few-Shot Computer Vision

https://github.com/ebennequin/few-shot-open-set

공식 코드

Open-Set Likelihood Maximization for Few-Shot Learning

https://github.com/ehsansaleh/firth_bias_reduction

공식 코드

On the Importance of Firth Bias Reduction in Few-Shot Classification

https://github.com/emasa/balpoe-calibratedlt

공식 코드

Balanced Product of Calibrated Experts for Long-Tailed Recognition

https://github.com/erjui/DHO

공식 코드

Simple Semi-supervised Knowledge Distillation from Vision-Language Models via $\mathbf{\texttt{D}}$ual-$\mathbf{\texttt{H}}$ead $\mathbf{\texttt{O}}$ptimization

https://github.com/facebookresearch/classifier-balancing

공식 코드

Decoupling Representation and Classifier for Long-Tailed Recognition

https://github.com/facebookresearch/detectron

공식 코드

Focal Loss for Dense Object Detection

https://github.com/facebookresearch/low-shot-shrink-hallucinate

공식 코드

Low-shot Visual Recognition by Shrinking and Hallucinating Features

https://github.com/facebookresearch/low-shot-with-diffusion

공식 코드

Low-shot learning with large-scale diffusion

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