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 101150 of 353 papers

TitleStatusHype
Few-shot Relational Reasoning via Connection Subgraph PretrainingCode1
A Unified Framework with Meta-dropout for Few-shot Learning0
BaseTransformers: Attention over base data-points for One Shot LearningCode1
Improving ProtoNet for Few-Shot Video Object Recognition: Winner of ORBIT Challenge 2022Code1
Adaptive Dimension Reduction and Variational Inference for Transductive Few-Shot Classification0
PaLI: A Jointly-Scaled Multilingual Language-Image ModelCode0
Class-Specific Channel Attention for Few-Shot Learning0
NeurIPS'22 Cross-Domain MetaDL competition: Design and baseline results0
Transductive Decoupled Variational Inference for Few-Shot ClassificationCode1
Stochastic Deep Networks with Linear Competing Units for Model-Agnostic Meta-LearningCode0
Self-Supervision Can Be a Good Few-Shot LearnerCode1
Generative Adversarial Networks Based on Transformer Encoder and Convolution Block for Hyperspectral Image Classification0
Tree Structure-Aware Few-Shot Image Classification via Hierarchical AggregationCode1
Improving Few-Shot Image Classification Using Machine- and User-Generated Natural Language Descriptions0
Task Discrepancy Maximization for Fine-grained Few-Shot ClassificationCode1
Graph Information Aggregation Cross-Domain Few-Shot Learning for Hyperspectral Image ClassificationCode1
p-Meta: Towards On-device Deep Model Adaptation0
Contextual Squeeze-and-Excitation for Efficient Few-Shot Image ClassificationCode1
Channel Importance Matters in Few-Shot Image ClassificationCode1
Rethinking Generalization in Few-Shot ClassificationCode1
Task-Prior Conditional Variational Auto-Encoder for Few-Shot Image Classification0
Bongard-HOI: Benchmarking Few-Shot Visual Reasoning for Human-Object InteractionsCode1
Uncertainty-based Network for Few-shot Image Classification0
Privacy Enhancement for Cloud-Based Few-Shot LearningCode0
Few-Shot Image Classification Benchmarks are Too Far From Reality: Build Back Better with Semantic Task SamplingCode1
iCAR: Bridging Image Classification and Image-text Alignment for Visual RecognitionCode0
ELEVATER: A Benchmark and Toolkit for Evaluating Language-Augmented Visual ModelsCode4
Pushing the Limits of Simple Pipelines for Few-Shot Learning: External Data and Fine-Tuning Make a DifferenceCode1
A Simple Approach to Adversarial Robustness in Few-shot Image ClassificationCode0
Joint Distribution Matters: Deep Brownian Distance Covariance for Few-Shot ClassificationCode1
The Self-Optimal-Transport Feature TransformCode1
Attribute Prototype Network for Any-Shot Learning0
Matching Feature Sets for Few-Shot Image Classification0
Multidimensional Belief Quantification for Label-Efficient Meta-LearningCode0
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
Continuous-Time Meta-Learning with Forward Mode Differentiation0
EASY: Ensemble Augmented-Shot Y-shaped Learning: State-Of-The-Art Few-Shot Classification with Simple IngredientsCode1
Visual Representation Learning with Self-Supervised Attention for Low-Label High-data RegimeCode0
Multi-level Second-order Few-shot LearningCode0
HyperTransformer: Model Generation for Supervised and Semi-Supervised Few-Shot LearningCode1
Debiased Learning from Naturally Imbalanced Pseudo-LabelsCode1
Improving Adversarially Robust Few-Shot Image Classification With Generalizable Representations0
Transformers Can Do Bayesian InferenceCode1
Exploring Category-correlated Feature for Few-shot Image Classification0
Few-Shot Image Classification Along Sparse Graphs0
Curriculum Meta-Learning for Few-shot ClassificationCode0
Inferring Prototypes for Multi-Label Few-Shot Image Classification with Word Vector Guided Attention0
argmax centroid0
Show:102550
← PrevPage 3 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