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/vuoristo/MMAML

공식 코드

Multimodal Model-Agnostic Meta-Learning via Task-Aware Modulation

https://github.com/wbw520/MTUNet

공식 코드

Match Them Up: Visually Explainable Few-shot Image Classification

https://github.com/wenbinlee/trip-roma

공식 코드

Trip-ROMA: Self-Supervised Learning with Triplets and Random Mappings

https://github.com/whut-yirong/espt

공식 코드

ESPT: A Self-Supervised Episodic Spatial Pretext Task for Improving Few-Shot Learning

https://github.com/wutong16/DistributionBalancedLoss

공식 코드

Distribution-Balanced Loss for Multi-Label Classification in Long-Tailed Datasets

https://github.com/wyharveychen/CloserLookFewShot

공식 코드

A Closer Look at Few-shot Classification

https://github.com/xiangly55/LFME

공식 코드

Learning From Multiple Experts: Self-paced Knowledge Distillation for Long-tailed Classification

https://github.com/xiangyu8/PT-MAP-sf

공식 코드

Few-Shot Learning by Integrating Spatial and Frequency Representation

https://github.com/xianyongqin/few-shot-video-classification

공식 코드

Generalized Few-Shot Video Classification with Video Retrieval and Feature Generation

https://github.com/xiaohua-chen/risda

공식 코드

Imagine by Reasoning: A Reasoning-Based Implicit Semantic Data Augmentation for Long-Tailed Classification

https://github.com/xingpingdong/pl-cfe

공식 코드

Rethinking Clustering-Based Pseudo-Labeling for Unsupervised Meta-Learning

https://github.com/xinzheli1217/learning-to-self-train

공식 코드

Learning to Self-Train for Semi-Supervised Few-Shot Classification

https://github.com/xuanlinli17/large_vlm_distillation_ood

공식 코드

Distilling Large Vision-Language Model with Out-of-Distribution Generalizability

https://github.com/xuzhengzhuo/livt

공식 코드

Learning Imbalanced Data with Vision Transformers

https://github.com/yaoyao-liu/meta-transfer-learning

공식 코드

Meta-Transfer Learning for Few-Shot Learning

https://github.com/ybendou/easy

공식 코드

EASY: Ensemble Augmented-Shot Y-shaped Learning: State-Of-The-Art Few-Shot Classification with Simple Ingredients

https://github.com/ycaigogogo/cvpr24-coder

공식 코드

Leveraging Cross-Modal Neighbor Representation for Improved CLIP Classification

https://github.com/yhu01/PT-MAP

공식 코드

Leveraging the Feature Distribution in Transfer-based Few-Shot Learning

https://github.com/yhu01/bms

공식 코드

Squeezing Backbone Feature Distributions to the Max for Efficient Few-Shot Learning

https://github.com/yhu01/transfer-sgc

공식 코드

Graph-based Interpolation of Feature Vectors for Accurate Few-Shot Classification

https://github.com/ynu-yangpeng/GLMC

공식 코드

Global and Local Mixture Consistency Cumulative Learning for Long-tailed Visual Recognitions

https://github.com/yoonholee/MT-net

공식 코드

Gradient-Based Meta-Learning with Learned Layerwise Metric and Subspace

https://github.com/yunkai696/mlcn

공식 코드

Multi-Level Correlation Network For Few-Shot Image Classification

https://github.com/zhangbq-research/Prototype_Completion_for_FSL

공식 코드

Prototype Completion for Few-Shot Learning

https://github.com/zhangdoudou123/semfew

공식 코드

Simple Semantic-Aided Few-Shot Learning

https://github.com/zhangxueting/DCN

공식 코드

RelationNet2: Deep Comparison Columns for Few-Shot Learning

https://github.com/zhaohengz/llamp

공식 코드

Large Language Models are Good Prompt Learners for Low-Shot Image Classification

https://github.com/zhihou7/batchformer

공식 코드

BatchFormer: Learning to Explore Sample Relationships for Robust Representation Learning

https://github.com/zhoudw-zdw/tpami-leadnet

공식 코드

Contextualizing Meta-Learning via Learning to Decompose

https://github.com/zhouzihao11/ccl

공식 코드

Continuous Contrastive Learning for Long-Tailed Semi-Supervised Recognition

https://github.com/zihangm/neural-tmd-layer

공식 코드

Neural TMDlayer: Modeling Instantaneous flow of features via SDE Generators

https://github.com/2023-MindSpore-1/ms-code-14/tree/main/Pangu_alpha

PanGu-$α$: Large-scale Autoregressive Pretrained Chinese Language Models with Auto-parallel Computation

https://github.com/2023-MindSpore-1/ms-code-162

PanGu-$α$: Large-scale Autoregressive Pretrained Chinese Language Models with Auto-parallel Computation

https://github.com/2023-MindSpore-1/ms-code-215/tree/main/ProtoNet

Improving ProtoNet for Few-Shot Video Object Recognition: Winner of ORBIT Challenge 2022

https://github.com/2023-MindSpore-1/ms-code-216/tree/main/relationnet

RelationNet2: Deep Comparison Columns for Few-Shot Learning

https://github.com/2023-MindSpore-1/ms-code-216/tree/main/retinanet_resnet101

Focal Loss for Dense Object Detection

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