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 301350 of 353 papers

TitleStatusHype
Learning to learn via Self-CritiqueCode0
Hierarchically Structured Meta-learningCode0
Edge-labeling Graph Neural Network for Few-shot LearningCode0
Amortized Bayesian Meta-Learning0
TextCaps : Handwritten Character Recognition with Very Small DatasetsCode0
Meta-Learning with Differentiable Convex OptimizationCode1
Revisiting Local Descriptor based Image-to-Class Measure for Few-shot LearningCode0
Diversity with Cooperation: Ensemble Methods for Few-Shot ClassificationCode0
Enhancing Generalization of First-Order Meta-Learning0
Meta-Dataset: A Dataset of Datasets for Learning to Learn from Few ExamplesCode1
Adaptive Cross-Modal Few-Shot LearningCode0
Meta-CurvatureCode0
Centroid-based deep metric learning for speaker recognition0
Toward Multimodal Model-Agnostic Meta-Learning0
Few-Shot Learning via Embedding Adaptation with Set-to-Set FunctionsCode1
Meta-Transfer Learning for Few-Shot LearningCode1
MetaGAN: An Adversarial Approach to Few-Shot Learning0
Unsupervised Meta-Learning For Few-Shot Image Classification0
RelationNet2: Deep Comparison Columns for Few-Shot LearningCode0
How to train your MAMLCode1
Set Transformer: A Framework for Attention-based Permutation-Invariant Neural NetworksCode1
Model-Agnostic Meta-Learning for Multimodal Task Distributions0
Delta-encoder: an effective sample synthesis method for few-shot object recognitionCode0
Probabilistic Model-Agnostic Meta-Learning0
Object-Level Representation Learning for Few-Shot Image Classification0
Learning to Propagate Labels: Transductive Propagation Network for Few-shot LearningCode0
Meta-Learning Probabilistic Inference For PredictionCode0
TADAM: Task dependent adaptive metric for improved few-shot learningCode0
Hyperspectral image classification via a random patches networkCode0
Unsupervised Learning using Pretrained CNN and Associative Memory Bank0
Dynamic Few-Shot Visual Learning without ForgettingCode1
Low-Shot Learning for the Semantic Segmentation of Remote Sensing ImageryCode0
On First-Order Meta-Learning AlgorithmsCode1
Gradient-Based Meta-Learning with Learned Layerwise Metric and SubspaceCode0
Transfer Learning on Manifolds via Learned Transport Operators0
Rapid Adaptation with Conditionally Shifted Neurons0
Learning to Compare: Relation Network for Few-Shot LearningCode1
A Simple Neural Attentive Meta-LearnerCode0
Few-Shot Image Recognition by Predicting Parameters from ActivationsCode0
Low-shot learning with large-scale diffusionCode0
Discriminative k-shot learning using probabilistic models0
Prototypical Networks for Few-shot LearningCode2
Learning to Remember Rare EventsCode0
Model-Agnostic Meta-Learning for Fast Adaptation of Deep NetworksCode1
Spectral–Spatial Classification of Hyperspectral Imagery with 3D Convolutional Neural NetworkCode0
Learning Deep Parsimonious RepresentationsCode0
Matching Networks for One Shot LearningCode1
Low-shot Visual Recognition by Shrinking and Hallucinating FeaturesCode0
Towards a Neural StatisticianCode0
Deep supervised learning for hyperspectral data classification through convolutional neural networksCode0
Show:102550
← PrevPage 7 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