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/saurabhsharma1993/prototype-classifier-ltr

공식 코드

Learning Prototype Classifiers for Long-Tailed Recognition

https://github.com/scongl/dirmixe

공식 코드

Harnessing Hierarchical Label Distribution Variations in Test Agnostic Long-tail Recognition

https://github.com/seongmin-kye/MCT

공식 코드

Meta-Learned Confidence for Few-shot Learning

https://github.com/shadealsha/ltr-weight-balancing

공식 코드

Long-Tailed Recognition via Weight Balancing

https://github.com/shangxinyi/fedic

공식 코드

FEDIC: Federated Learning on Non-IID and Long-Tailed Data via Calibrated Distillation

https://github.com/shihongl1998/llm-as-a-blackbox-optimizer

공식 코드

Language Models as Black-Box Optimizers for Vision-Language Models

https://github.com/shijxcs/lift

공식 코드

Long-Tail Learning with Foundation Model: Heavy Fine-Tuning Hurts

https://github.com/shijxcs/lift-plus

공식 코드

LIFT+: Lightweight Fine-Tuning for Long-Tail Learning

https://github.com/shiranzada/pure-noise

공식 코드

Pure Noise to the Rescue of Insufficient Data: Improving Imbalanced Classification by Training on Random Noise Images

https://github.com/shwangtangjun/Diff-ResNet

공식 코드

Diffusion Mechanism in Residual Neural Network: Theory and Applications

https://github.com/sicara/semantic-task-sampling

공식 코드

Few-Shot Image Classification Benchmarks are Too Far From Reality: Build Back Better with Semantic Task Sampling

https://github.com/silverbottlep/meta_curvature

공식 코드

https://github.com/snap-stanford/csr

공식 코드

Few-shot Relational Reasoning via Connection Subgraph Pretraining

https://github.com/ssfootball04/class-balanced-experts

공식 코드

Long-Tailed Recognition Using Class-Balanced Experts

https://github.com/steremma/curr-meta-learning

공식 코드

Curriculum Meta-Learning for Few-shot Classification

https://github.com/stomach-ache/long-tailed-ood-detection

공식 코드

EAT: Towards Long-Tailed Out-of-Distribution Detection

https://github.com/stomachcold/hctransformers

공식 코드

Attribute Surrogates Learning and Spectral Tokens Pooling in Transformers for Few-shot Learning

https://github.com/stypoumic/beclr

공식 코드

BECLR: Batch Enhanced Contrastive Few-Shot Learning

https://github.com/suhyun777/cvpr23-gap

공식 코드

Meta-Learning with a Geometry-Adaptive Preconditioner

https://github.com/sumyeongahn/cuda_ltr

공식 코드

CUDA: Curriculum of Data Augmentation for Long-Tailed Recognition

https://github.com/szc12153/sparse_meta_tuning

공식 코드

Unleashing the Power of Meta-tuning for Few-shot Generalization Through Sparse Interpolated Experts

https://github.com/tankche1/IDeMe-Net

공식 코드

Image Deformation Meta-Networks for One-Shot Learning

https://github.com/tensorflow/models

공식 코드

Learning to Remember Rare Events

https://github.com/tiangeluo/fsl-global

공식 코드

Few-Shot Learning with Global Class Representations

https://github.com/tkasarla/max-separation-as-inductive-bias

공식 코드

Maximum Class Separation as Inductive Bias in One Matrix

https://github.com/tztztztztz/eql.detectron2

공식 코드

Equalization Loss for Long-Tailed Object Recognition

https://github.com/ucbdrive/tafe-net

공식 코드

TAFE-Net: Task-Aware Feature Embeddings for Low Shot Learning

https://github.com/usuyama/ePillID-benchmark

공식 코드

ePillID Dataset: A Low-Shot Fine-Grained Benchmark for Pill Identification

https://github.com/val-iisc/DeiT-LT

공식 코드

DeiT-LT Distillation Strikes Back for Vision Transformer Training on Long-Tailed Datasets

https://github.com/val-iisc/saddle-longtail

공식 코드

Escaping Saddle Points for Effective Generalization on Class-Imbalanced Data

https://github.com/vanint/sade-agnosticlt

공식 코드

Self-Supervised Aggregation of Diverse Experts for Test-Agnostic Long-Tailed Recognition

https://github.com/vgsatorras/few-shot-gnn

공식 코드

Few-Shot Learning with Graph Neural Networks

https://github.com/vinojjayasundara/textcaps

공식 코드

TextCaps : Handwritten Character Recognition with Very Small Datasets

https://github.com/vinuni-vishc/Few-Shot-Cosine-Transformer

공식 코드

Enhancing Few-shot Image Classification with Cosine Transformer

https://github.com/vita-group/longtailcxr

공식 코드

Long-Tailed Classification of Thorax Diseases on Chest X-Ray: A New Benchmark Study

https://github.com/vturrisi/disef

공식 코드

Diversified in-domain synthesis with efficient fine-tuning for few-shot classification

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