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.
Bongard-HOI: Benchmarking Few-Shot Visual Reasoning for Human-Object Interactions
Uncertainty-based Network for Few-shot Image Classification
Few-Shot Image Classification Benchmarks are Too Far From Reality: Build Back Better with Semantic Task Sampling
Privacy Enhancement for Cloud-Based Few-Shot Learning
FEDIC: Federated Learning on Non-IID and Long-Tailed Data via Calibrated Distillation
ELM: Embedding and Logit Margins for Long-Tail Learning
Realistic Evaluation of Transductive Few-Shot Learning
iCAR: Bridging Image Classification and Image-text Alignment for Visual Recognition
ELEVATER: A Benchmark and Toolkit for Evaluating Language-Augmented Visual Models
Pushing the Limits of Simple Pipelines for Few-Shot Learning: External Data and Fine-Tuning Make a Difference
A Simple Approach to Adversarial Robustness in Few-shot Image Classification
Joint Distribution Matters: Deep Brownian Distance Covariance for Few-Shot Classification
The Self-Optimal-Transport Feature Transform
Attribute Prototype Network for Any-Shot Learning
Matching Feature Sets for Few-Shot Image Classification
Nested Collaborative Learning for Long-Tailed Visual Recognition
Long-Tailed Recognition via Weight Balancing
Visual Prompt Tuning
Multidimensional Belief Quantification for Label-Efficient Meta-Learning
Rebalanced Siamese Contrastive Mining for Long-Tailed Recognition
HyperShot: Few-Shot Learning by Kernel HyperNetworks
Do Deep Networks Transfer Invariances Across Classes?
Attribute Surrogates Learning and Spectral Tokens Pooling in Transformers for Few-shot Learning
Inducing Neural Collapse in Imbalanced Learning: Do We Really Need a Learnable Classifier at the End of Deep Neural Network?
Worst Case Matters for Few-Shot Recognition
BatchFormer: Learning to Explore Sample Relationships for Robust Representation Learning
Continuous-Time Meta-Learning with Forward Mode Differentiation
Long-Tailed Classification with Gradual Balanced Loss and Adaptive Feature Generation
Retrieval Augmented Classification for Long-Tail Visual Recognition
Balancing Domain Experts for Long-Tailed Camera-Trap Recognition
Self-Supervised Class-Cognizant Few-Shot Classification
EASY: Ensemble Augmented-Shot Y-shaped Learning: State-Of-The-Art Few-Shot Classification with Simple Ingredients
Visual Representation Learning with Self-Supervised Attention for Low-Label High-data Regime
Multi-level Second-order Few-shot Learning
HyperTransformer: Model Generation for Supervised and Semi-Supervised Few-Shot Learning
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.