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.
Neural TMDlayer: Modeling Instantaneous flow of features via SDE Generators
Prototype Completion for Few-Shot Learning
ACE: Ally Complementary Experts for Solving Long-Tailed Recognition in One-Shot
Parametric Contrastive Learning
Trip-ROMA: Self-Supervised Learning with Triplets and Random Mappings
Self-Supervised Aggregation of Diverse Experts for Test-Agnostic Long-Tailed Recognition
Rectifying the Shortcut Learning of Background for Few-Shot Learning
Memory Efficient Meta-Learning with Large Images
Cross-domain Few-shot Learning with Task-specific Adapters
SITTA: Single Image Texture Translation for Data Augmentation
Unsupervised Embedding Adaptation via Early-Stage Feature Reconstruction for Few-Shot Classification
Trainable Class Prototypes for Few-Shot Learning
RSG: A Simple but Effective Module for Learning Imbalanced Datasets
Bridging Multi-Task Learning and Meta-Learning: Towards Efficient Training and Effective Adaptation
Contextualizing Meta-Learning via Learning to Decompose
Scaling Vision with Sparse Mixture of Experts
Scaling Vision Transformers
Few-Shot Learning with Part Discovery and Augmentation from Unlabeled Images
Deep Metric Learning for Few-Shot Image Classification: A Review of Recent Developments
Few-Shot Learning by Integrating Spatial and Frequency Representation
MetaKernel: Learning Variational Random Features with Limited Labels
Few-Shot Learning for Image Classification of Common Flora
Diffusion Mechanism in Residual Neural Network: Theory and Applications
Subspace Representation Learning for Few-shot Image Classification
UVStyle-Net: Unsupervised Few-shot Learning of 3D Style Similarity Measure for B-Reps
PanGu-$α$: Large-scale Autoregressive Pretrained Chinese Language Models with Auto-parallel Computation
Rich Semantics Improve Few-shot Learning
Class-Balanced Distillation for Long-Tailed Visual Recognition
Prototypical Region Proposal Networks for Few-Shot Localization and Classification
Few-Shot Action Recognition with Compromised Metric via Optimal Transport
ORBIT: A Real-World Few-Shot Dataset for Teachable Object Recognition
Distributional Robustness Loss for Long-tail Learning
Improving Calibration for Long-Tailed Recognition
Distribution Alignment: A Unified Framework for Long-tail Visual Recognition
Distilling Virtual Examples for Long-tailed Recognition
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.