Papers with Code 아카이브
Few-Shot Image Classification
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 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>
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Few-Shot Classification in Unseen Domains by Episodic Meta-Learning Across Visual Domains
Transformers Can Do Bayesian Inference
Pure Noise to the Rescue of Insufficient Data: Improving Imbalanced Classification by Training on Random Noise Images
Imagine by Reasoning: A Reasoning-Based Implicit Semantic Data Augmentation for Long-Tailed Classification
Exploring Category-correlated Feature for Few-shot Image Classification
Few-Shot Image Classification Along Sparse Graphs
Curriculum Meta-Learning for Few-shot Classification
Inferring Prototypes for Multi-Label Few-Shot Image Classification with Word Vector Guided Attention
The Majority Can Help The Minority: Context-rich Minority Oversampling for Long-tailed Classification
A Simple Long-Tailed Recognition Baseline via Vision-Language Model
Targeted Supervised Contrastive Learning for Long-Tailed Recognition
VL-LTR: Learning Class-wise Visual-Linguistic Representation for Long-Tailed Visual Recognition
Trustworthy Long-Tailed Classification
Feature Generation for Long-tail Classification
Enhancing Prototypical Few-Shot Learning by Leveraging the Local-Level Strategy
Towards Calibrated Model for Long-Tailed Visual Recognition from Prior Perspective
On sensitivity of meta-learning to support data
Simultaneous Perturbation Method for Multi-Task Weight Optimization in One-Shot Meta-Learning
GCCN: Global Context Convolutional Network
Improving Tail-Class Representation with Centroid Contrastive Learning
Squeezing Backbone Feature Distributions to the Max for Efficient Few-Shot Learning
Self-supervised Learning is More Robust to Dataset Imbalance
A Closer Look at Prototype Classifier for Few-shot Image Classification
Influence-Balanced Loss for Imbalanced Visual Classification
On the Importance of Firth Bias Reduction in Few-Shot Classification
Sparse Spatial Transformers for Few-Shot Learning
ST-MAML: A Stochastic-Task based Method for Task-Heterogeneous Meta-Learning
Disentangled Feature Representation for Few-shot Image Classification
Multi-Domain Few-Shot Learning and Dataset for Agricultural Applications
Fairness-aware Class Imbalanced Learning
Ontology-based n-ball Concept Embeddings Informing Few-shot Image Classification
Sign-MAML: Efficient Model-Agnostic Meta-Learning by SignSGD
Partner-Assisted Learning for Few-Shot Image Classification
LibFewShot: A Comprehensive Library for Few-shot Learning
Self Supervision to Distillation for Long-Tailed Visual Recognition
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.