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.
Interpretable Few-Shot Image Classification via Prototypical Concept-Guided Mixture of LoRA Experts
Provably Improving Generalization of Few-Shot Models with Synthetic Data
Mitigating Spurious Correlations with Causal Logit Perturbation
Simple Semi-supervised Knowledge Distillation from Vision-Language Models via $\mathbf{\texttt{D}}$ual-$\mathbf{\texttt{H}}$ead $\mathbf{\texttt{O}}$ptimization
LIFT+: Lightweight Fine-Tuning for Long-Tail Learning
Brain Inspired Adaptive Memory Dual-Net for Few-Shot Image Classification
InPK: Infusing Prior Knowledge into Prompt for Vision-Language Models
Augmented Conditioning Is Enough For Effective Training Image Generation
Geometric Mean Improves Loss For Few-Shot Learning
A Cognitive Paradigm Approach to Probe the Perception-Reasoning Interface in VLMs
IDEA: Image Description Enhanced CLIP-Adapter
Cross-Modal Mapping: Mitigating the Modality Gap for Few-Shot Image Classification
Task-Specific Preconditioner for Cross-Domain Few-Shot Learning
Modelling Multi-modal Cross-interaction for ML-FSIC Based on Local Feature Selection
Semi-Supervised Risk Control via Prediction-Powered Inference
Multi-Level Correlation Network For Few-Shot Image Classification
Neuron Abandoning Attention Flow: Visual Explanation of Dynamics inside CNN Models
Self-Supervised Learning in Deep Networks: A Pathway to Robust Few-Shot Classification
Improving Visual Prompt Tuning by Gaussian Neighborhood Minimization for Long-Tailed Visual Recognition
FewVS: A Vision-Semantics Integration Framework for Few-Shot Image Classification
Learning from Neighbors: Category Extrapolation for Long-Tail Learning
Semantic Token Reweighting for Interpretable and Controllable Text Embeddings in CLIP
Continuous Contrastive Learning for Long-Tailed Semi-Supervised Recognition
AUCSeg: AUC-oriented Pixel-level Long-tail Semantic Segmentation
Learning to Obstruct Few-Shot Image Classification over Restricted Classes
Enhancing Few-Shot Image Classification through Learnable Multi-Scale Embedding and Attention Mechanisms
Local Descriptors Weighted Adaptive Threshold Filtering For Few-Shot Learning
Feature Aligning Few shot Learning Method Using Local Descriptors Weighted Rules
MICM: Rethinking Unsupervised Pretraining for Enhanced Few-shot Learning
Representation Norm Amplification for Out-of-Distribution Detection in Long-Tail Learning
A Simple Task-aware Contrastive Local Descriptor Selection Strategy for Few-shot Learning between inter class and intra class
Improved Few-Shot Image Classification Through Multiple-Choice Questions
Assessing Sample Quality via the Latent Space of Generative Models
LTRL: Boosting Long-tail Recognition via Reflective Learning
Siamese Transformer Networks for Few-shot Image Classification
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.