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

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 51–100 of 353 papers

TitleStatusHype
The Self-Optimal-Transport Feature TransformCode1
HyperShot: Few-Shot Learning by Kernel HyperNetworksCode1
Attribute Surrogates Learning and Spectral Tokens Pooling in Transformers for Few-shot LearningCode1
Worst Case Matters for Few-Shot RecognitionCode1
EASY: Ensemble Augmented-Shot Y-shaped Learning: State-Of-The-Art Few-Shot Classification with Simple IngredientsCode1
HyperTransformer: Model Generation for Supervised and Semi-Supervised Few-Shot LearningCode1
Debiased Learning from Naturally Imbalanced Pseudo-LabelsCode1
Transformers Can Do Bayesian InferenceCode1
On sensitivity of meta-learning to support dataCode1
Squeezing Backbone Feature Distributions to the Max for Efficient Few-Shot LearningCode1
On the Importance of Firth Bias Reduction in Few-Shot ClassificationCode1
Sparse Spatial Transformers for Few-Shot LearningCode1
Disentangled Feature Representation for Few-shot Image ClassificationCode1
Relational Embedding for Few-Shot ClassificationCode1
Prototype Completion for Few-Shot LearningCode1
Rectifying the Shortcut Learning of Background for Few-Shot LearningCode1
Memory Efficient Meta-Learning with Large ImagesCode1
Cross-domain Few-shot Learning with Task-specific AdaptersCode1
SITTA: Single Image Texture Translation for Data AugmentationCode1
Unsupervised Embedding Adaptation via Early-Stage Feature Reconstruction for Few-Shot ClassificationCode1
Bridging Multi-Task Learning and Meta-Learning: Towards Efficient Training and Effective AdaptationCode1
Scaling Vision with Sparse Mixture of ExpertsCode1
Few-Shot Learning by Integrating Spatial and Frequency RepresentationCode1
Diffusion Mechanism in Residual Neural Network: Theory and ApplicationsCode1
PanGu-α: Large-scale Autoregressive Pretrained Chinese Language Models with Auto-parallel ComputationCode1
ORBIT: A Real-World Few-Shot Dataset for Teachable Object RecognitionCode1
Universal Representation Learning from Multiple Domains for Few-shot ClassificationCode1
Exploring Complementary Strengths of Invariant and Equivariant Representations for Few-Shot LearningCode1
MetaDelta: A Meta-Learning System for Few-shot Image ClassificationCode1
Transfer learning based few-shot classification using optimal transport mapping from preprocessed latent space of backbone neural networkCode1
Sill-Net: Feature Augmentation with Separated Illumination RepresentationCode1
Shallow Bayesian Meta Learning for Real-World Few-Shot RecognitionCode1
Few-shot Image Classification: Just Use a Library of Pre-trained Feature Extractors and a Simple ClassifierCode1
Constellation Nets for Few-Shot LearningCode1
Extended Few-Shot Learning: Exploiting Existing Resources for Novel TasksCode1
Few-Shot Classification with Feature Map Reconstruction NetworksCode1
Match Them Up: Visually Explainable Few-shot Image ClassificationCode1
Mixture-based Feature Space Learning for Few-shot Image ClassificationCode1
Region Comparison Network for Interpretable Few-shot Image ClassificationCode1
GPU-based Self-Organizing Maps for Post-Labeled Few-Shot Unsupervised LearningCode1
Transductive Information Maximization For Few-Shot LearningCode1
Generalized Few-Shot Video Classification with Video Retrieval and Feature GenerationCode1
Laplacian Regularized Few-Shot LearningCode1
Laplacian Regularized Few-Shot LearningCode1
A Universal Representation Transformer Layer for Few-Shot Image ClassificationCode1
Self-supervised Knowledge Distillation for Few-shot LearningCode1
Leveraging the Feature Distribution in Transfer-based Few-Shot LearningCode1
Adaptive Subspaces for Few-Shot LearningCode1
Attentive Weights Generation for Few Shot Learning via Information MaximizationCode1
ePillID Dataset: A Low-Shot Fine-Grained Benchmark for Pill IdentificationCode1
Show:102550
← PrevPage 2 of 8Next →
All datasetsMini-Imagenet 5-way (1-shot)Mini-Imagenet 5-way (5-shot)Tiered ImageNet 5-way (5-shot)Tiered ImageNet 5-way (1-shot)CIFAR-FS 5-way (5-shot)CIFAR-FS 5-way (1-shot)CUB 200 5-way 1-shotCUB 200 5-way 5-shotFC100 5-way (1-shot)FC100 5-way (5-shot)Meta-DatasetOMNIGLOT - 1-Shot, 20-way

Benchmark Results

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