Learning from few examples: A summary of approaches to few-shot learning

A Parnami, M Lee - arxiv preprint arxiv:2203.04291, 2022‏ - arxiv.org
Few-Shot Learning refers to the problem of learning the underlying pattern in the data just
from a few training samples. Requiring a large number of data samples, many deep learning …

[HTML][HTML] A survey on few-shot class-incremental learning

S Tian, L Li, W Li, H Ran, X Ning, P Tiwari - Neural Networks, 2024‏ - Elsevier
Large deep learning models are impressive, but they struggle when real-time data is not
available. Few-shot class-incremental learning (FSCIL) poses a significant challenge for …

Visual prompting via image inpainting

A Bar, Y Gandelsman, T Darrell… - Advances in Neural …, 2022‏ - proceedings.neurips.cc
How does one adapt a pre-trained visual model to novel downstream tasks without task-
specific finetuning or any model modification? Inspired by prompting in NLP, this paper …

Grounded language-image pre-training

LH Li, P Zhang, H Zhang, J Yang, C Li… - Proceedings of the …, 2022‏ - openaccess.thecvf.com
This paper presents a grounded language-image pre-training (GLIP) model for learning
object-level, language-aware, and semantic-rich visual representations. GLIP unifies object …

Base and meta: A new perspective on few-shot segmentation

C Lang, G Cheng, B Tu, C Li… - IEEE Transactions on …, 2023‏ - ieeexplore.ieee.org
Despite the progress made by few-shot segmentation (FSS) in low-data regimes, the
generalization capability of most previous works could be fragile when countering hard …

Self-support few-shot semantic segmentation

Q Fan, W Pei, YW Tai, CK Tang - European Conference on Computer …, 2022‏ - Springer
Existing few-shot segmentation methods have achieved great progress based on the
support-query matching framework. But they still heavily suffer from the limited coverage of …

A comprehensive survey on source-free domain adaptation

J Li, Z Yu, Z Du, L Zhu, HT Shen - IEEE Transactions on Pattern …, 2024‏ - ieeexplore.ieee.org
Over the past decade, domain adaptation has become a widely studied branch of transfer
learning which aims to improve performance on target domains by leveraging knowledge …

Fsce: Few-shot object detection via contrastive proposal encoding

B Sun, B Li, S Cai, Y Yuan… - Proceedings of the IEEE …, 2021‏ - openaccess.thecvf.com
Emerging interests have been brought to recognize previously unseen objects given very
few training examples, known as few-shot object detection (FSOD). Recent researches …

Defrcn: Decoupled faster r-cnn for few-shot object detection

L Qiao, Y Zhao, Z Li, X Qiu, J Wu… - Proceedings of the …, 2021‏ - openaccess.thecvf.com
Few-shot object detection, which aims at detecting novel objects rapidly from extremely few
annotated examples of previously unseen classes, has attracted significant research interest …

Few-shot object detection with fully cross-transformer

G Han, J Ma, S Huang, L Chen… - Proceedings of the …, 2022‏ - openaccess.thecvf.com
Few-shot object detection (FSOD), with the aim to detect novel objects using very few
training examples, has recently attracted great research interest in the community. Metric …