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.
Data-Centric Long-Tailed Image Recognition
Are LSTMs Good Few-Shot Learners?
Context-Aware Meta-Learning
Subspace Adaptation Prior for Few-Shot Learning
A Unified Generalization Analysis of Re-Weighting and Logit-Adjustment for Imbalanced Learning. paper with code
PrototypeFormer: Learning to Explore Prototype Relationships for Few-shot Image Classification
SemiReward: A General Reward Model for Semi-supervised Learning
Logarithm-transform aided Gaussian Sampling for Few-Shot Learning
Long-Tail Learning with Foundation Model: Heavy Fine-Tuning Hurts
MVP: Meta Visual Prompt Tuning for Few-Shot Remote Sensing Image Scene Classification
PRE: Vision-Language Prompt Learning with Reparameterization Encoder
Language Models as Black-Box Optimizers for Vision-Language Models
Support-Set Context Matters for Bongard Problems
Knowledge-Aware Prompt Tuning for Generalizable Vision-Language Models
MDCS: More Diverse Experts with Consistency Self-distillation for Long-tailed Recognition
DiffKendall: A Novel Approach for Few-Shot Learning with Differentiable Kendall's Rank Correlation
Few-shot Image Classification based on Gradual Machine Learning
Feature Activation Map: Visual Explanation of Deep Learning Models for Image Classification
FILM: How can Few-Shot Image Classification Benefit from Pre-Trained Language Models?
Distilling Self-Supervised Vision Transformers for Weakly-Supervised Few-Shot Classification & Segmentation
Multi-Similarity Contrastive Learning
Proto-CLIP: Vision-Language Prototypical Network for Few-Shot Learning
Distilling Large Vision-Language Model with Out-of-Distribution Generalizability
Variance-Covariance Regularization Improves Representation Learning
Comparing the Efficacy of Fine-Tuning and Meta-Learning for Few-Shot Policy Imitation
Norm-guided latent space exploration for text-to-image generation
On the Effectiveness of Out-of-Distribution Data in Self-Supervised Long-Tail Learning
Data Augmentation for Improving Tail-traffic Robustness in Skill-routing for Dialogue Systems
Long-tailed Visual Recognition via Gaussian Clouded Logit Adjustment
Feature-Balanced Loss for Long-Tailed Visual Recognition
Global and Local Mixture Consistency Cumulative Learning for Long-tailed Visual Recognitions
SuSana Distancia is all you need: Enforcing class separability in metric learning via two novel distance-based loss functions for few-shot image classification
Meta-DM: Applications of Diffusion Models on Few-Shot Learning
LMPT: Prompt Tuning with Class-Specific Embedding Loss for Long-tailed Multi-Label Visual Recognition
Long-Tailed Recognition by Mutual Information Maximization between Latent Features and Ground-Truth Labels
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.