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.
Universal Representation Learning from Multiple Domains for Few-shot Classification
MetaSAug: Meta Semantic Augmentation for Long-Tailed Visual Recognition
Multi-level Metric Learning for Few-shot Image Recognition
Hierarchical Representation based Query-Specific Prototypical Network for Few-Shot Image Classification
How to distribute data across tasks for meta-learning?
Exploring Complementary Strengths of Invariant and Equivariant Representations for Few-Shot Learning
Learning Transferable Visual Models From Natural Language Supervision
MetaDelta: A Meta-Learning System for Few-shot Image Classification
Model-Agnostic Graph Regularization for Few-Shot Learning
Transfer learning based few-shot classification using optimal transport mapping from preprocessed latent space of backbone neural network
Sill-Net: Feature Augmentation with Separated Illumination Representation
Few-shot Image Classification with Multi-Facet Prototypes
CORL: Compositional Representation Learning for Few-Shot Classification
ResLT: Residual Learning for Long-tailed Recognition
Machine learning with limited data
Shallow Bayesian Meta Learning for Real-World Few-Shot Recognition
Few-shot Image Classification: Just Use a Library of Pre-trained Feature Extractors and a Simple Classifier
Extended Few-Shot Learning: Exploiting Existing Resources for Novel Tasks
Few-Shot Classification with Feature Map Reconstruction Networks
Disentangling Label Distribution for Long-tailed Visual Recognition
Multi-scale Adaptive Task Attention Network for Few-Shot Learning
Revisiting Unsupervised Meta-Learning via the Characteristics of Few-Shot Tasks
Match Them Up: Visually Explainable Few-shot Image Classification
Mixture-based Feature Space Learning for Few-shot Image Classification
Confusable Learning for Large-class Few-Shot Classification
How Does the Task Landscape Affect MAML Performance?
Posterior Re-calibration for Imbalanced Datasets
Uncertainty-Aware Few-Shot Image Classification
Variational Feature Disentangling for Fine-Grained Few-Shot Classification
Shot in the Dark: Few-Shot Learning with No Base-Class Labels
Long-tailed Recognition by Routing Diverse Distribution-Aware Experts
Class-Wise Difficulty-Balanced Loss for Solving Class-Imbalance
Robust High-dimensional Memory-augmented Neural Networks
Long-Tailed Classification by Keeping the Good and Removing the Bad Momentum Causal Effect
Region Comparison Network for Interpretable Few-shot Image Classification
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.