English
Related papers

Related papers: PRSNet: A Masked Self-Supervised Learning Pedestri…

200 papers

3D object detection task from lidar or camera sensors is essential for autonomous driving. Pioneer attempts at multi-modality fusion complement the sparse lidar point clouds with rich semantic texture information from images at the cost of…

Computer Vision and Pattern Recognition · Computer Science 2022-07-13 Bo Ju , Zhikang Zou , Xiaoqing Ye , Minyue Jiang , Xiao Tan , Errui Ding , Jingdong Wang

Unsupervised learning and supervised learning are key research topics in deep learning. However, as high-capacity supervised neural networks trained with a large amount of labels have achieved remarkable success in many computer vision…

Machine Learning · Computer Science 2017-04-18 Yuting Zhang , Kibok Lee , Honglak Lee

The task of point cloud upsampling aims to acquire dense and uniform point sets from sparse and irregular point sets. Although significant progress has been made with deep learning models, state-of-the-art methods require ground-truth dense…

Computer Vision and Pattern Recognition · Computer Science 2022-06-14 Xinhai Liu , Xinchen Liu , Yu-Shen Liu , Zhizhong Han

One paradigm for learning from few labeled examples while making best use of a large amount of unlabeled data is unsupervised pretraining followed by supervised fine-tuning. Although this paradigm uses unlabeled data in a task-agnostic way,…

Machine Learning · Computer Science 2020-10-27 Ting Chen , Simon Kornblith , Kevin Swersky , Mohammad Norouzi , Geoffrey Hinton

Self-supervised learning is popular method because of its ability to learn features in images without using its labels and is able to overcome limited labeled datasets used in supervised learning. Self-supervised learning works by using a…

Computer Vision and Pattern Recognition · Computer Science 2023-07-28 Aristo Renaldo Ruslim , Novanto Yudistira , Budi Darma Setiawan

Image reconstruction from undersampled k-space data plays an important role in accelerating the acquisition of MR data, and a lot of deep learning-based methods have been exploited recently. Despite the achieved inspiring results, the…

Computer Vision and Pattern Recognition · Computer Science 2021-09-28 Chen Hu , Cheng Li , Haifeng Wang , Qiegen Liu , Hairong Zheng , Shanshan Wang

Part-level representations are important for robust person re-identification (ReID), but in practice feature quality suffers due to the body part misalignment problem. In this paper, we present a robust, compact, and easy-to-use method…

Computer Vision and Pattern Recognition · Computer Science 2021-05-10 Changxing Ding , Kan Wang , Pengfei Wang , Dacheng Tao

Person re-identification is a challenging task mainly due to factors such as background clutter, pose, illumination and camera point of view variations. These elements hinder the process of extracting robust and discriminative…

Computer Vision and Pattern Recognition · Computer Science 2018-04-03 Mahdi M. Kalayeh , Emrah Basaran , Muhittin Gokmen , Mustafa E. Kamasak , Mubarak Shah

BERT adopts masked language modeling (MLM) for pre-training and is one of the most successful pre-training models. Since BERT neglects dependency among predicted tokens, XLNet introduces permuted language modeling (PLM) for pre-training to…

Computation and Language · Computer Science 2020-11-03 Kaitao Song , Xu Tan , Tao Qin , Jianfeng Lu , Tie-Yan Liu

Object re-identification (re-id) aims to identify a specific object across times or camera views, with the person re-id and vehicle re-id as the most widely studied applications. Re-id is challenging because of the variations in viewpoints,…

Computer Vision and Pattern Recognition · Computer Science 2020-01-22 Xin Jin , Cuiling Lan , Wenjun Zeng , Zhibo Chen

There is an increasing need of continual learning in dynamic systems, such as the self-driving vehicle, the surveillance drone, and the robotic system. Such a system requires learning from the data stream, training the model to preserve…

Machine Learning · Computer Science 2019-12-23 Xiaocong Du , Gouranga Charan , Frank Liu , Yu Cao

Many remote sensing applications employ masking of pixels in satellite imagery for subsequent measurements. For example, estimating water quality variables, such as Suspended Sediment Concentration (SSC) requires isolating pixels depicting…

Computer Vision and Pattern Recognition · Computer Science 2024-12-12 Rangel Daroya , Luisa Vieira Lucchese , Travis Simmons , Punwath Prum , Tamlin Pavelsky , John Gardner , Colin J. Gleason , Subhransu Maji

Over the years, computer vision researchers have spent an immense amount of effort on designing image features for the visual object recognition task. We propose to incorporate this valuable experience to guide the task of training deep…

Computer Vision and Pattern Recognition · Computer Science 2016-11-15 Ming-Yu Liu , Arun Mallya , Oncel C. Tuzel , Xi Chen

Recently, the progress of learning-by-synthesis has proposed a training model for synthetic images, which can effectively reduce the cost of human and material resources. However, due to the different distribution of synthetic images…

Computer Vision and Pattern Recognition · Computer Science 2019-03-21 Tongtong Zhao , Yuxiao Yan , Jinjia Peng , Huibing Wang , Xianping Fu

This paper addresses the problem of matching pedestrians across multiple camera views, known as person re-identification. Variations in lighting conditions, environment and pose changes across camera views make re-identification a…

Computer Vision and Pattern Recognition · Computer Science 2015-12-01 Rahul Rama Varior , Gang Wang

Self-supervised learning has become a popular approach in recent years for its ability to learn meaningful representations without the need for data annotation. This paper proposes a novel image augmentation technique, overlaying images,…

Computer Vision and Pattern Recognition · Computer Science 2023-01-25 Yinheng Li , Han Ding , Shaofei Wang

While metric learning is important for Person re-identification (RE-ID), a significant problem in visual surveillance for cross-view pedestrian matching, existing metric models for RE-ID are mostly based on supervised learning that requires…

Computer Vision and Pattern Recognition · Computer Science 2017-10-19 Hong-Xing Yu , Ancong Wu , Wei-Shi Zheng

Self-supervised learning (SSL) has demonstrated significant potential in pre-training robust models with limited labeled data, making it particularly valuable for remote sensing (RS) tasks. A common assumption is that pre-training on…

Computer Vision and Pattern Recognition · Computer Science 2025-02-18 Saad Lahrichi , Zion Sheng , Shufan Xia , Kyle Bradbury , Jordan Malof

Face Super-Resolution (FSR) aims to recover high-resolution (HR) face images from low-resolution (LR) ones. Despite the progress made by convolutional neural networks in FSR, the results of existing approaches are not ideal due to their low…

Computer Vision and Pattern Recognition · Computer Science 2024-06-25 Hao Liu , Yang Yang , Yunxia Liu

State-of-the-art semantic segmentation methods require sufficient labeled data to achieve good results and hardly work on unseen classes without fine-tuning. Few-shot segmentation is thus proposed to tackle this problem by learning a model…

Computer Vision and Pattern Recognition · Computer Science 2020-08-05 Zhuotao Tian , Hengshuang Zhao , Michelle Shu , Zhicheng Yang , Ruiyu Li , Jiaya Jia