English
Related papers

Related papers: Sparse Spatial Transformers for Few-Shot Learning

200 papers

Point cloud-based large scale place recognition is fundamental for many applications like Simultaneous Localization and Mapping (SLAM). Although many models have been proposed and have achieved good performance by learning short-range local…

Computer Vision and Pattern Recognition · Computer Science 2021-12-14 Zhaoxin Fan , Zhenbo Song , Hongyan Liu , Zhiwu Lu , Jun He , Xiaoyong Du

Few-shot learning is a challenging problem that has attracted more and more attention recently since abundant training samples are difficult to obtain in practical applications. Meta-learning has been proposed to address this issue, which…

Computer Vision and Pattern Recognition · Computer Science 2020-07-23 Xian Zhong , Cheng Gu , Wenxin Huang , Lin Li , Shuqin Chen , Chia-Wen Lin

Few-shot Learning aims to learn and distinguish new categories with a very limited number of available images, presenting a significant challenge in the realm of deep learning. Recent researchers have sought to leverage the additional…

Computer Vision and Pattern Recognition · Computer Science 2024-03-26 Chunpeng Zhou , Haishuai Wang , Xilu Yuan , Zhi Yu , Jiajun Bu

We present an image preprocessing technique capable of improving the performance of few-shot classifiers on abstract visual reasoning tasks. Many visual reasoning tasks with abstract features are easy for humans to learn with few examples…

Machine Learning · Computer Science 2019-10-07 Tanner Bohn , Yining Hu , Charles X. Ling

A few-shot semantic segmentation model is typically composed of a CNN encoder, a CNN decoder and a simple classifier (separating foreground and background pixels). Most existing methods meta-learn all three model components for fast…

Computer Vision and Pattern Recognition · Computer Science 2021-08-13 Zhihe Lu , Sen He , Xiatian Zhu , Li Zhang , Yi-Zhe Song , Tao Xiang

Few-shot semantic segmentation aims to segment novel-class objects in a query image with only a few annotated examples in support images. Most of advanced solutions exploit a metric learning framework that performs segmentation through…

Computer Vision and Pattern Recognition · Computer Science 2021-04-29 Jiacheng Chen , Bin-Bin Gao , Zongqing Lu , Jing-Hao Xue , Chengjie Wang , Qingmin Liao

Few-shot Semantic Segmentation (FSS) aims to adapt a pretrained model to new classes with as few as a single labelled training sample per class. Despite the prototype based approaches have achieved substantial success, existing models are…

Computer Vision and Pattern Recognition · Computer Science 2024-06-27 Song Tang , Shaxu Yan , Xiaozhi Qi , Jianxin Gao , Mao Ye , Jianwei Zhang , Xiatian Zhu

LiDAR-based 3D point cloud recognition has benefited various applications. Without specially considering the LiDAR point distribution, most current methods suffer from information disconnection and limited receptive field, especially for…

Computer Vision and Pattern Recognition · Computer Science 2023-03-23 Xin Lai , Yukang Chen , Fanbin Lu , Jianhui Liu , Jiaya Jia

Most pipelines for Augmented and Virtual Reality estimate the ego-motion of the camera by creating a map of sparse 3D landmarks. In this paper, we tackle the problem of depth completion, that is, densifying this sparse 3D map using RGB…

Computer Vision and Pattern Recognition · Computer Science 2022-06-10 Frederik Warburg , Michael Ramamonjisoa , Manuel López-Antequera

Image segmentation is often ambiguous at the level of individual image patches and requires contextual information to reach label consensus. In this paper we introduce Segmenter, a transformer model for semantic segmentation. In contrast to…

Computer Vision and Pattern Recognition · Computer Science 2021-09-03 Robin Strudel , Ricardo Garcia , Ivan Laptev , Cordelia Schmid

Weakly supervised object localization (WSOL) strives to learn to localize objects with only image-level supervision. Due to the local receptive fields generated by convolution operations, previous CNN-based methods suffer from partial…

Computer Vision and Pattern Recognition · Computer Science 2023-09-06 Yiwen Cao , Yukun Su , Wenjun Wang , Yanxia Liu , Qingyao Wu

The discrete curvelet transform decomposes an image into a set of fundamental components that are distinguished by direction and size as well as a low-frequency representation. The curvelet representation is approximately sparse; thus, it…

Image and Video Processing · Electrical Eng. & Systems 2022-12-08 Nicholas Dwork , Peder E. Z. Larson

Example-based mesh deformation methods are powerful tools for realistic shape editing. However, existing techniques typically combine all the example deformation modes, which can lead to overfitting, i.e. using a overly complicated model to…

Graphics · Computer Science 2017-09-06 Lin Gao , Yu-Kun Lai , Jie Yang , Ling-Xiao Zhang , Leif Kobbelt , Shihong Xia

Few-shot segmentation (FSS) aims to segment unseen classes given only a few annotated samples. Existing methods suffer the problem of feature undermining, i.e. potential novel classes are treated as background during training phase. Our…

Computer Vision and Pattern Recognition · Computer Science 2021-09-28 Lihe Yang , Wei Zhuo , Lei Qi , Yinghuan Shi , Yang Gao

In many practical few-shot learning problems, even though labeled examples are scarce, there are abundant auxiliary datasets that potentially contain useful information. We propose the problem of extended few-shot learning to study these…

Machine Learning · Computer Science 2021-07-06 Reza Esfandiarpoor , Amy Pu , Mohsen Hajabdollahi , Stephen H. Bach

Few-shot semantic segmentation addresses the learning task in which only few images with ground truth pixel-level labels are available for the novel classes of interest. One is typically required to collect a large mount of data (i.e., base…

Computer Vision and Pattern Recognition · Computer Science 2021-11-03 Yuan-Hao Lee , Fu-En Yang , Yu-Chiang Frank Wang

Few-shot learning (FSL), which aims to recognise new classes by adapting the learned knowledge with extremely limited few-shot (support) examples, remains an important open problem in computer vision. Most of the existing methods for…

Computer Vision and Pattern Recognition · Computer Science 2021-03-26 Chengming Xu , Chen Liu , Li Zhang , Chengjie Wang , Jilin Li , Feiyue Huang , Xiangyang Xue , Yanwei Fu

Humans demonstrate remarkable skill in transferring manipulation abilities across objects of varying shapes, poses, and appearances, a capability rooted in their understanding of semantic correspondences between different instances. To…

Robotics · Computer Science 2024-03-19 Qianxu Wang , Haotong Zhang , Congyue Deng , Yang You , Hao Dong , Yixin Zhu , Leonidas Guibas

Many meta-learning approaches for few-shot learning rely on simple base learners such as nearest-neighbor classifiers. However, even in the few-shot regime, discriminatively trained linear predictors can offer better generalization. We…

Computer Vision and Pattern Recognition · Computer Science 2019-04-24 Kwonjoon Lee , Subhransu Maji , Avinash Ravichandran , Stefano Soatto

Sparse support vector machine (SVM) is a popular classification technique that can simultaneously learn a small set of the most interpretable features and identify the support vectors. It has achieved great successes in many real-world…

Machine Learning · Statistics 2019-07-19 Weizhong Zhang , Bin Hong , Wei Liu , Jieping Ye , Deng Cai , Xiaofei He , Jie Wang