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 101–150 of 353 papers

TitleStatusHype
Empirical Bayes Transductive Meta-Learning with Synthetic GradientsCode1
Instance Credibility Inference for Few-Shot LearningCode1
Negative Margin Matters: Understanding Margin in Few-shot ClassificationCode1
Rethinking Few-Shot Image Classification: a Good Embedding Is All You Need?Code1
Selecting Relevant Features from a Multi-domain Representation for Few-shot ClassificationCode1
DeepEMD: Differentiable Earth Mover's Distance for Few-Shot LearningCode1
Embedding Propagation: Smoother Manifold for Few-Shot ClassificationCode1
Meta-Learned Confidence for Few-shot LearningCode1
Automated Relational Meta-learningCode1
A Broader Study of Cross-Domain Few-Shot LearningCode1
SimpleShot: Revisiting Nearest-Neighbor Classification for Few-Shot LearningCode1
Multimodal Model-Agnostic Meta-Learning via Task-Aware ModulationCode1
Bayesian Meta-Learning for the Few-Shot Setting via Deep KernelsCode1
Rapid Learning or Feature Reuse? Towards Understanding the Effectiveness of MAMLCode1
Meta-Learning with Implicit GradientsCode1
Charting the Right Manifold: Manifold Mixup for Few-shot LearningCode1
Fast and Flexible Multi-Task Classification Using Conditional Neural Adaptive ProcessesCode1
Meta-Learning with Differentiable Convex OptimizationCode1
Meta-Dataset: A Dataset of Datasets for Learning to Learn from Few ExamplesCode1
Few-Shot Learning via Embedding Adaptation with Set-to-Set FunctionsCode1
Meta-Transfer Learning for Few-Shot LearningCode1
How to train your MAMLCode1
Set Transformer: A Framework for Attention-based Permutation-Invariant Neural NetworksCode1
Dynamic Few-Shot Visual Learning without ForgettingCode1
On First-Order Meta-Learning AlgorithmsCode1
Learning to Compare: Relation Network for Few-Shot LearningCode1
Model-Agnostic Meta-Learning for Fast Adaptation of Deep NetworksCode1
Matching Networks for One Shot LearningCode1
ViT-ProtoNet for Few-Shot Image Classification: A Multi-Benchmark EvaluationCode0
Interpretable Few-Shot Image Classification via Prototypical Concept-Guided Mixture of LoRA Experts—0
Provably Improving Generalization of Few-Shot Models with Synthetic Data—0
Simple Semi-supervised Knowledge Distillation from Vision-Language Models via Dual-Head OptimizationCode0
Brain Inspired Adaptive Memory Dual-Net for Few-Shot Image Classification—0
InPK: Infusing Prior Knowledge into Prompt for Vision-Language Models—0
Augmented Conditioning Is Enough For Effective Training Image Generation—0
Geometric Mean Improves Loss For Few-Shot Learning—0
A Cognitive Paradigm Approach to Probe the Perception-Reasoning Interface in VLMs—0
IDEA: Image Description Enhanced CLIP-AdapterCode0
Cross-Modal Mapping: Mitigating the Modality Gap for Few-Shot Image Classification—0
Task-Specific Preconditioner for Cross-Domain Few-Shot Learning—0
Modelling Multi-modal Cross-interaction for ML-FSIC Based on Local Feature Selection—0
Semi-Supervised Risk Control via Prediction-Powered Inference—0
Multi-Level Correlation Network For Few-Shot Image ClassificationCode0
Neuron Abandoning Attention Flow: Visual Explanation of Dynamics inside CNN Models—0
Self-Supervised Learning in Deep Networks: A Pathway to Robust Few-Shot Classification—0
Semantic Token Reweighting for Interpretable and Controllable Text Embeddings in CLIP—0
Learning to Obstruct Few-Shot Image Classification over Restricted ClassesCode0
Local Descriptors Weighted Adaptive Threshold Filtering For Few-Shot Learning—0
Feature Aligning Few shot Learning Method Using Local Descriptors Weighted Rules—0
A Simple Task-aware Contrastive Local Descriptor Selection Strategy for Few-shot Learning between inter class and intra class—0
Show:102550
← PrevPage 3 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+SOT (transductive)Accuracy85.59—Unverified
6PT+MAP+SF+BPA (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+BPA (transductive)Accuracy91.34—Unverified
9PT+MAP+SF+SOT (transductive)Accuracy91.34—Unverified
10AmdimNetAccuracy90.98—Unverified