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 Added Most Hyped Most Active Needs Verification Most Verified

Showing 276–300 of 353 papers

Title	Date	Tasks	Status
Unsupervised Image Classification for Deep Representation Learning	Jun 20, 2020	ClassificationClustering	CodeCode Available
Adversarially Robust Few-Shot Learning: A Meta-Learning Approach	Oct 2, 2019	ClassificationFew-Shot Image Classification	CodeCode Available
Towards a Neural Statistician	Jun 7, 2016	ClusteringFew-Shot Image Classification	CodeCode Available
Cooperative Meta-Learning with Gradient Augmentation	Jun 7, 2024	Few-Shot Image Classificationimage-classification	CodeCode Available
Contextualizing Meta-Learning via Learning to Decompose	Jun 15, 2021	AttributeFew-Shot Image Classification	CodeCode Available
Gradient-Based Meta-Learning with Learned Layerwise Metric and Subspace	Jan 17, 2018	Few-Shot Image ClassificationMeta-Learning	CodeCode Available
Few-Shot Learning with Global Class Representations	Aug 14, 2019	Few-Shot Image ClassificationFew-Shot Learning	CodeCode Available
Complementing Representation Deficiency in Few-shot Image Classification: A Meta-Learning Approach	Jul 21, 2020	Few-Shot Image ClassificationFew-Shot Learning	CodeCode Available
Few-Shot Learning for Image Classification of Common Flora	May 7, 2021	ClassificationFew-Shot Image Classification	CodeCode Available
Self-Supervised Learning For Few-Shot Image Classification	Nov 14, 2019	ClassificationCross-Domain Few-Shot	CodeCode Available
Comparing the Efficacy of Fine-Tuning and Meta-Learning for Few-Shot Policy Imitation	Jun 23, 2023	Few-Shot Image ClassificationFew-Shot Imitation Learning	CodeCode Available
CMVAE: Causal Meta VAE for Unsupervised Meta-Learning	Feb 20, 2023	Few-Shot Image Classificationimage-classification	CodeCode Available
Few-Shot Image Recognition by Predicting Parameters from Activations	Jun 12, 2017	Few-Shot Image ClassificationFew-Shot Learning	CodeCode Available
Image Deformation Meta-Networks for One-Shot Learning	May 28, 2019	Few-Shot Image ClassificationMeta-Learning	CodeCode Available
Few and Fewer: Learning Better from Few Examples Using Fewer Base Classes	Jan 29, 2024	Cross-Domain Few-ShotFew-Shot Image Classification	CodeCode Available
Clustered Task-Aware Meta-Learning by Learning from Learning Paths	Sep 29, 2021	ClusteringFew-Shot Image Classification	CodeCode Available
Graph-based Interpolation of Feature Vectors for Accurate Few-Shot Classification	Jan 27, 2020	Few-Shot Image ClassificationGeneral Classification	CodeCode Available
SgVA-CLIP: Semantic-guided Visual Adapting of Vision-Language Models for Few-shot Image Classification	Nov 28, 2022	Few-Shot Image ClassificationFew-Shot Learning	CodeCode Available
Evaluation of Output Embeddings for Fine-Grained Image Classification	Sep 30, 2014	ClassificationFew-Shot Image Classification	CodeCode Available
Associative Alignment for Few-shot Image Classification	Dec 11, 2019	ClassificationDomain Adaptation	CodeCode Available
Sign-MAML: Efficient Model-Agnostic Meta-Learning by SignSGD	Sep 15, 2021	Bilevel OptimizationFew-Shot Image Classification	CodeCode Available
Meta-Learning Probabilistic Inference For Prediction	May 24, 2018	Few-Shot Image ClassificationFew-Shot Learning	CodeCode Available
Meta-Learning without Memorization	Dec 9, 2019	Few-Shot Image Classificationimage-classification	CodeCode Available
Edge-labeling Graph Neural Network for Few-shot Learning	May 4, 2019	ClusteringFew-Shot Image Classification	CodeCode Available
Meta-Learning Initializations for Image Segmentation	Dec 13, 2019	Bayesian OptimizationFew-Shot Image Classification	CodeCode Available

Show:10 25 50

← PrevPage 12 of 15Next →

All datasets Mini-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-shot CUB 200 5-way 5-shot FC100 5-way (1-shot)FC100 5-way (5-shot)Meta-Dataset OMNIGLOT - 1-Shot, 20-way

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	SgVA-CLIP	Accuracy	97.95	—	Unverified
2	CAML [Laion-2b]	Accuracy	96.2	—	Unverified
3	P>M>F (P=DINO-ViT-base, M=ProtoNet)	Accuracy	95.3	—	Unverified
4	TRIDENT	Accuracy	86.11	—	Unverified
5	PT+MAP+SF+SOT (transductive)	Accuracy	85.59	—	Unverified
6	PT+MAP+SF+BPA (transductive)	Accuracy	85.59	—	Unverified
7	PEMnE-BMS* (transductive)	Accuracy	85.54	—	Unverified
8	PT+MAP (s+f) (transductive)	Accuracy	84.81	—	Unverified
9	BAVARDAGE	Accuracy	84.8	—	Unverified
10	EASY 3xResNet12 (transductive)	Accuracy	84.04	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	SgVA-CLIP	Accuracy	98.72	—	Unverified
2	CAML [Laion-2b]	Accuracy	98.6	—	Unverified
3	P>M>F (P=DINO-ViT-base, M=ProtoNet)	Accuracy	98.4	—	Unverified
4	TRIDENT	Accuracy	95.95	—	Unverified
5	BAVARDAGE	Accuracy	91.65	—	Unverified
6	PEMnE-BMS*(transductive)	Accuracy	91.53	—	Unverified
7	Transductive CNAPS + FETI	Accuracy	91.5	—	Unverified
8	PT+MAP+SF+BPA (transductive)	Accuracy	91.34	—	Unverified
9	PT+MAP+SF+SOT (transductive)	Accuracy	91.34	—	Unverified
10	AmdimNet	Accuracy	90.98	—	Unverified