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.
ESPT: A Self-Supervised Episodic Spatial Pretext Task for Improving Few-Shot Learning
Improving Image Recognition by Retrieving from Web-Scale Image-Text Data
VNE: An Effective Method for Improving Deep Representation by Manipulating Eigenvalue Distribution
Meta-Learning with a Geometry-Adaptive Preconditioner
Strong Baselines for Parameter Efficient Few-Shot Fine-tuning
Boosting Few-Shot Text Classification via Distribution Estimation
Prompt Tuning based Adapter for Vision-Language Model Adaption
The effectiveness of MAE pre-pretraining for billion-scale pretraining
Predicting and Enhancing the Fairness of DNNs with the Curvature of Perceptual Manifolds
RotoGBML: Towards Out-of-Distribution Generalization for Gradient-Based Meta-Learning
Understanding and Constructing Latent Modality Structures in Multi-modal Representation Learning
Pseudo Labels Regularization for Imbalanced Partial-Label Learning
Unsupervised Meta-Learning via Few-shot Pseudo-supervised Contrastive Learning
CMVAE: Causal Meta VAE for Unsupervised Meta-Learning
Text Classification in the Wild: a Large-scale Long-tailed Name Normalization Dataset
CovidExpert: A Triplet Siamese Neural Network framework for the detection of COVID-19
Meta-Album: Multi-domain Meta-Dataset for Few-Shot Image Classification
CUDA: Curriculum of Data Augmentation for Long-Tailed Recognition
Delving Deep into Simplicity Bias for Long-Tailed Image Recognition
Effective Data Augmentation With Diffusion Models
Weight-guided class complementing for long-tailed image recognition
Revisiting Long-tailed Image Classification: Survey and Benchmarks with New Evaluation Metrics
Language Quantized AutoEncoders: Towards Unsupervised Text-Image Alignment
On the Efficacy of Differentially Private Few-shot Image Classification
Learning Prototype Classifiers for Long-Tailed Recognition
Explore the Power of Dropout on Few-shot Learning
Open-Set Likelihood Maximization for Few-Shot Learning
Escaping Saddle Points for Effective Generalization on Class-Imbalanced Data
Learning Imbalanced Data with Vision Transformers
Leveraging Angular Information Between Feature and Classifier for Long-tailed Learning: A Prediction Reformulation Approach
Bi-directional Feature Reconstruction Network for Fine-Grained Few-Shot Image Classification
Exploiting Category Names for Few-Shot Classification with Vision-Language Models
SgVA-CLIP: Semantic-guided Visual Adapting of Vision-Language Models for Few-shot Image Classification
Supervised Contrastive Learning on Blended Images for Long-tailed Recognition
Enhancing Few-shot Image Classification with Cosine Transformer
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.