SOTAVerified

Few-Shot Image Classification

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 ( Image credit: Learning Embedding Adaptation for Few-Shot Learning )

Papers

Showing 176200 of 353 papers

TitleStatusHype
Low-shot Visual Recognition by Shrinking and Hallucinating FeaturesCode0
MaxUp: A Simple Way to Improve Generalization of Neural Network TrainingCode0
MergedNET: A simple approach for one-shot learning in siamese networks based on similarity layersCode0
Meta-CurvatureCode0
MetaFun: Meta-Learning with Iterative Functional UpdatesCode0
MetaKernel: Learning Variational Random Features with Limited LabelsCode0
Meta-learning algorithms for Few-Shot Computer VisionCode0
Meta-Learning Initializations for Image SegmentationCode0
Meta-Learning Probabilistic Inference For PredictionCode0
Meta-Learning without MemorizationCode0
Multidimensional Belief Quantification for Label-Efficient Meta-LearningCode0
Multi-Level Correlation Network For Few-Shot Image ClassificationCode0
Multi-level Metric Learning for Few-shot Image RecognitionCode0
Multi-level Second-order Few-shot LearningCode0
Simultaneous Perturbation Method for Multi-Task Weight Optimization in One-Shot Meta-LearningCode0
Neural TMDlayer: Modeling Instantaneous flow of features via SDE GeneratorsCode0
On the Efficacy of Differentially Private Few-shot Image ClassificationCode0
PRE: Vision-Language Prompt Learning with Reparameterization EncoderCode0
Privacy Enhancement for Cloud-Based Few-Shot LearningCode0
RAFIC: Retrieval-Augmented Few-shot Image ClassificationCode0
Revisiting Local Descriptor based Image-to-Class Measure for Few-shot LearningCode0
Revisiting Unsupervised Meta-Learning via the Characteristics of Few-Shot TasksCode0
Adversarially Robust Few-Shot Learning: A Meta-Learning ApproachCode0
Self-Supervised Learning For Few-Shot Image ClassificationCode0
SgVA-CLIP: Semantic-guided Visual Adapting of Vision-Language Models for Few-shot Image ClassificationCode0
Show:102550
← PrevPage 8 of 15Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1SgVA-CLIPAccuracy97.95Unverified
2CAML [Laion-2b]Accuracy96.2Unverified
3P>M>F (P=DINO-ViT-base, M=ProtoNet)Accuracy95.3Unverified
4TRIDENTAccuracy86.11Unverified
5PT+MAP+SF+SOT (transductive)Accuracy85.59Unverified
6PT+MAP+SF+BPA (transductive)Accuracy85.59Unverified
7PEMnE-BMS* (transductive)Accuracy85.54Unverified
8PT+MAP (s+f) (transductive)Accuracy84.81Unverified
9BAVARDAGEAccuracy84.8Unverified
10EASY 3xResNet12 (transductive)Accuracy84.04Unverified
#ModelMetricClaimedVerifiedStatus
1SgVA-CLIPAccuracy98.72Unverified
2CAML [Laion-2b]Accuracy98.6Unverified
3P>M>F (P=DINO-ViT-base, M=ProtoNet)Accuracy98.4Unverified
4TRIDENTAccuracy95.95Unverified
5BAVARDAGEAccuracy91.65Unverified
6PEMnE-BMS*(transductive)Accuracy91.53Unverified
7Transductive CNAPS + FETIAccuracy91.5Unverified
8PT+MAP+SF+BPA (transductive)Accuracy91.34Unverified
9PT+MAP+SF+SOT (transductive)Accuracy91.34Unverified
10AmdimNetAccuracy90.98Unverified