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 151200 of 353 papers

TitleStatusHype
DiffKendall: A Novel Approach for Few-Shot Learning with Differentiable Kendall's Rank CorrelationCode0
Diversity with Cooperation: Ensemble Methods for Few-Shot ClassificationCode0
Edge-labeling Graph Neural Network for Few-shot LearningCode0
Evaluation of Output Embeddings for Fine-Grained Image ClassificationCode0
Graph-based Interpolation of Feature Vectors for Accurate Few-Shot ClassificationCode0
Few and Fewer: Learning Better from Few Examples Using Fewer Base ClassesCode0
Few-Shot Image Recognition by Predicting Parameters from ActivationsCode0
Few-Shot Learning for Image Classification of Common FloraCode0
Few-Shot Learning with Global Class RepresentationsCode0
Gradient-Based Meta-Learning with Learned Layerwise Metric and SubspaceCode0
Harnessing the Power of Infinitely Wide Deep Nets on Small-data TasksCode0
Hierarchically Structured Meta-learningCode0
Hyperspectral image classification via a random patches networkCode0
iCAR: Bridging Image Classification and Image-text Alignment for Visual RecognitionCode0
IDEA: Image Description Enhanced CLIP-AdapterCode0
Improved Few-Shot Visual ClassificationCode0
Enhancing Few-Shot Image Classification with Unlabelled ExamplesCode0
Improving Few-Shot Visual Classification with Unlabelled ExamplesCode0
KGTN-ens: Few-Shot Image Classification with Knowledge Graph EnsemblesCode0
Knowledge Graph Transfer Network for Few-Shot RecognitionCode0
Learning Deep Parsimonious RepresentationsCode0
Learning to learn via Self-CritiqueCode0
Learning to Obstruct Few-Shot Image Classification over Restricted ClassesCode0
Learning to Propagate for Graph Meta-LearningCode0
Learning to Propagate Labels: Transductive Propagation Network for Few-shot LearningCode0
Learning to Remember Rare EventsCode0
Logarithm-transform aided Gaussian Sampling for Few-Shot LearningCode0
Low-Shot Learning for the Semantic Segmentation of Remote Sensing ImageryCode0
Low-shot learning with large-scale diffusionCode0
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
PAC-Bayes meta-learning with implicit task-specific posteriorsCode0
PaLI: A Jointly-Scaled Multilingual Language-Image ModelCode0
PRE: Vision-Language Prompt Learning with Reparameterization EncoderCode0
Privacy Enhancement for Cloud-Based Few-Shot LearningCode0
Show:102550
← PrevPage 4 of 8Next →

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