English
Related papers

Related papers: XtarNet: Learning to Extract Task-Adaptive Represe…

200 papers

The existing few-shot video classification methods often employ a meta-learning paradigm by designing customized temporal alignment module for similarity calculation. While significant progress has been made, these methods fail to focus on…

Computer Vision and Pattern Recognition · Computer Science 2021-10-26 Zhenxi Zhu , Limin Wang , Sheng Guo , Gangshan Wu

In few-shot recognition, a classifier that has been trained on one set of classes is required to rapidly adapt and generalize to a disjoint, novel set of classes. To that end, recent studies have shown the efficacy of fine-tuning with…

Computer Vision and Pattern Recognition · Computer Science 2023-06-16 Panagiotis Eustratiadis , Łukasz Dudziak , Da Li , Timothy Hospedales

We present a conceptually simple, flexible, and general framework for few-shot learning, where a classifier must learn to recognise new classes given only few examples from each. Our method, called the Relation Network (RN), is trained…

Computer Vision and Pattern Recognition · Computer Science 2018-03-28 Flood Sung , Yongxin Yang , Li Zhang , Tao Xiang , Philip H. S. Torr , Timothy M. Hospedales

Effective policy learning for robotic manipulation requires scene representations that selectively capture task-relevant environmental features. Current approaches typically employ task-agnostic representation extraction, failing to emulate…

Robotics · Computer Science 2025-09-23 Li Sun , Jiefeng Wu , Feng Chen , Ruizhe Liu , Yanchao Yang

Humans are capable of learning new tasks without forgetting previous ones, while neural networks fail due to catastrophic forgetting between new and previously-learned tasks. We consider a class-incremental setting which means that the…

Computer Vision and Pattern Recognition · Computer Science 2020-04-21 Xialei Liu , Chenshen Wu , Mikel Menta , Luis Herranz , Bogdan Raducanu , Andrew D. Bagdanov , Shangling Jui , Joost van de Weijer

The majority of existing few-shot learning methods describe image relations with binary labels. However, such binary relations are insufficient to teach the network complicated real-world relations, due to the lack of decision smoothness.…

Computer Vision and Pattern Recognition · Computer Science 2021-06-10 Hongguang Zhang , Piotr Koniusz , Songlei Jian , Hongdong Li , Philip H. S. Torr

Although prototypical network (ProtoNet) has proved to be an effective method for few-shot sound event detection, two problems still exist. Firstly, the small-scaled support set is insufficient so that the class prototypes may not represent…

Sound · Computer Science 2022-06-07 Dongchao Yang , Helin Wang , Yuexian Zou , Zhongjie Ye , Wenwu Wang

Popular approaches for few-shot classification consist of first learning a generic data representation based on a large annotated dataset, before adapting the representation to new classes given only a few labeled samples. In this work, we…

Computer Vision and Pattern Recognition · Computer Science 2020-07-21 Nikita Dvornik , Cordelia Schmid , Julien Mairal

It is a big problem that a model of deep learning for a picking robot needs many labeled images. Operating costs of retraining a model becomes very expensive because the object shape of a product or a part often is changed in a factory. It…

Robotics · Computer Science 2020-03-13 Yasuto Yokota , Kanata Suzuki , Yuzi Kanazawa , Tomoyoshi Takebayashi

Despite achieving state-of-the-art performance, deep learning methods generally require a large amount of labeled data during training and may suffer from overfitting when the sample size is small. To ensure good generalizability of deep…

Computer Vision and Pattern Recognition · Computer Science 2020-06-30 Xiaoxu Li , Liyun Yu , Xiaochen Yang , Zhanyu Ma , Jing-Hao Xue , Jie Cao , Jun Guo

Deep Learning shows very good performance when trained on large labeled data sets. The problem of training a deep net on a few or one sample per class requires a different learning approach which can generalize to unseen classes using only…

Machine Learning · Computer Science 2018-08-23 Jinchao Liu , Stuart J. Gibson , Margarita Osadchy

Graph representation learning, a critical step in graph-centric tasks, has seen significant advancements. Earlier techniques often operate in an end-to-end setting, which heavily rely on the availability of ample labeled data. This…

Machine Learning · Computer Science 2024-09-23 Xingtong Yu , Yuan Fang , Zemin Liu , Yuxia Wu , Zhihao Wen , Jianyuan Bo , Xinming Zhang , Steven C. H. Hoi

This study focuses on incremental learning for image classification, exploring how to reduce catastrophic forgetting of all learned knowledge when access to old data is restricted. The challenge lies in balancing plasticity (learning new…

Machine Learning · Computer Science 2026-03-12 Zhiping Zhou , Xuchen Xie , Yiqiao Qiu , Run Lin , Weishi Zheng , Ruixuan Wang

Synthetic aperture radar automatic target recognition (SAR-ATR) systems have rapidly evolved to tackle incremental recognition challenges in operational settings. Data scarcity remains a major hurdle that conventional SAR-ATR techniques…

Computer Vision and Pattern Recognition · Computer Science 2025-05-27 George Karantaidis , Athanasios Pantsios , Ioannis Kompatsiaris , Symeon Papadopoulos

Fine-tuning a deep network trained with the standard cross-entropy loss is a strong baseline for few-shot learning. When fine-tuned transductively, this outperforms the current state-of-the-art on standard datasets such as Mini-ImageNet,…

Machine Learning · Computer Science 2020-10-23 Guneet S. Dhillon , Pratik Chaudhari , Avinash Ravichandran , Stefano Soatto

Vision-based regression tasks, such as hand pose estimation, have achieved higher accuracy and faster convergence through representation learning. However, existing representation learning methods often encounter the following issues: the…

Computer Vision and Pattern Recognition · Computer Science 2025-02-19 Kaiwen Ren , Lei Hu , Zhiheng Zhang , Yongjing Ye , Shihong Xia

Although large-scale labeled data are essential for deep convolutional neural networks (ConvNets) to learn high-level semantic visual representations, it is time-consuming and impractical to collect and annotate large-scale datasets. A…

Computer Vision and Pattern Recognition · Computer Science 2023-10-06 Huili Huang , M. Mahdi Roozbahani

In task-based few-shot learning paradigms, it is commonly assumed that different tasks are independently and identically distributed (i.i.d.). However, in real-world scenarios, the distribution encountered in few-shot learning can…

Computer Vision and Pattern Recognition · Computer Science 2025-04-10 Jiajun Chen , Hongpeng Yin , Yifu Yang

Continual learning, also known as lifelong learning, is an emerging research topic that has been attracting increasing interest in the field of machine learning. With human activity recognition (HAR) playing a key role in enabling numerous…

Machine Learning · Computer Science 2022-11-18 Rebecca Adaimi , Edison Thomaz

In this paper, we look at the problem of few-shot classification that aims to learn a classifier for previously unseen classes and domains from few labeled samples. Recent methods use adaptation networks for aligning their features to new…

Computer Vision and Pattern Recognition · Computer Science 2021-03-26 Wei-Hong Li , Xialei Liu , Hakan Bilen