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 111–120 of 353 papers

Title	Date	Tasks	Status	Hype	Score
Rapid Learning or Feature Reuse? Towards Understanding the Effectiveness of MAML	Sep 19, 2019	Few-Shot Image ClassificationFew-Shot Learning	CodeCode Available	1	5
Few-shot Image Classification: Just Use a Library of Pre-trained Feature Extractors and a Simple Classifier	Jan 3, 2021	ClassificationCross-Domain Few-Shot	CodeCode Available	1	5
Match Them Up: Visually Explainable Few-shot Image Classification	Nov 25, 2020	ClassificationFew-Shot Image Classification	CodeCode Available	1	5
Sill-Net: Feature Augmentation with Separated Illumination Representation	Feb 6, 2021	Few-Shot Image ClassificationImage Classification	CodeCode Available	1	5
BECLR: Batch Enhanced Contrastive Few-Shot Learning	Feb 4, 2024	Contrastive LearningFew-Shot Image Classification	CodeCode Available	1	5
Matching Networks for One Shot Learning	Jun 13, 2016	Few-Shot Image ClassificationFew-Shot Learning	CodeCode Available	1	5
Few-Shot Learning by Integrating Spatial and Frequency Representation	May 11, 2021	ClassificationFew-Shot Image Classification	CodeCode Available	1	5
Sparse Spatial Transformers for Few-Shot Learning	Sep 27, 2021	Few-Shot Image ClassificationFew-Shot Learning	CodeCode Available	1	5
Bi-directional Feature Reconstruction Network for Fine-Grained Few-Shot Image Classification	Nov 30, 2022	Few-Shot Image ClassificationFew-Shot Learning	CodeCode Available	1	5
Transfer learning based few-shot classification using optimal transport mapping from preprocessed latent space of backbone neural network	Feb 9, 2021	Few-Shot Image ClassificationFew-Shot Learning	CodeCode Available	1	5

Show:10 25 50

← PrevPage 12 of 36Next →

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+BPA (transductive)	Accuracy	85.59	—	Unverified
6	PT+MAP+SF+SOT (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+SOT (transductive)	Accuracy	91.34	—	Unverified
9	PT+MAP+SF+BPA (transductive)	Accuracy	91.34	—	Unverified
10	AmdimNet	Accuracy	90.98	—	Unverified