English
Related papers

Related papers: NIV-SSD: Neighbor IoU-Voting Single-Stage Object D…

200 papers

SSD (Single Shot Multibox Detector) is one of the best object detection algorithms with both high accuracy and fast speed. However, SSD's feature pyramid detection method makes it hard to fuse the features from different scales. In this…

Computer Vision and Pattern Recognition · Computer Science 2024-02-26 Zuoxin Li , Lu Yang , Fuqiang Zhou

In the machine learning field, dimensionality reduction is an important task. It mitigates the undesired properties of high-dimensional spaces to facilitate classification, compression, and visualization of high-dimensional data. During the…

Machine Learning · Computer Science 2019-11-19 Mohammed Elhenawy , Mahmoud Masoud , Sebastian Glaser , Andry Rakotonirainy

We present a novel framework for high-fidelity novel view synthesis (NVS) from sparse images, addressing key limitations in recent feed-forward 3D Gaussian Splatting (3DGS) methods built on Vision Transformer (ViT) backbones. While…

Computer Vision and Pattern Recognition · Computer Science 2026-01-21 Yitong Dong , Qi Zhang , Minchao Jiang , Zhiqiang Wu , Qingnan Fan , Ying Feng , Huaqi Zhang , Hujun Bao , Guofeng Zhang

Object detection involves two sub-tasks, i.e. localizing objects in an image and classifying them into various categories. For existing CNN-based detectors, we notice the widespread divergence between localization and classification, which…

Computer Vision and Pattern Recognition · Computer Science 2021-03-26 Taiheng Zhang , Qiaoyong Zhong , Shiliang Pu , Di Xie

Person re-identification (re-ID) has recently been tremendously boosted due to the advancement of deep convolutional neural networks (CNN). The majority of deep re-ID methods focus on designing new CNN architectures, while less attention is…

Computer Vision and Pattern Recognition · Computer Science 2018-08-21 Kai Li , Zhengming Ding , Kunpeng Li , Yulun Zhang , Yun Fu

3D object detection with multi-sensors is essential for an accurate and reliable perception system of autonomous driving and robotics. Existing 3D detectors significantly improve the accuracy by adopting a two-stage paradigm which merely…

Computer Vision and Pattern Recognition · Computer Science 2022-09-23 Xinli Xu , Shaocong Dong , Lihe Ding , Jie Wang , Tingfa Xu , Jianan Li

Classification and regression are two pillars of object detectors. In most CNN-based detectors, these two pillars are optimized independently. Without direct interactions between them, the classification loss and the regression loss can not…

Computer Vision and Pattern Recognition · Computer Science 2021-08-30 Keyang Wang , Lei Zhang

Inadequate bounding box modeling in regression tasks constrains the performance of one-stage 3D object detection. Our study reveals that the primary reason lies in two aspects: (1) The limited center-offset prediction seriously impairs the…

Computer Vision and Pattern Recognition · Computer Science 2024-09-04 Weiping Xiao , Yiqiang Wu , Chang Liu , Yu Qin , Xiaomao Li , Liming Xin

One-stage object detectors are trained by optimizing classification-loss and localization-loss simultaneously, with the former suffering much from extreme foreground-background class imbalance issue due to the large number of anchors. This…

Computer Vision and Pattern Recognition · Computer Science 2026-03-03 Kean Chen , Jianguo Li , Weiyao Lin , John See , Ji Wang , Lingyu Duan , Zhibo Chen , Changwei He , Junni Zou

Confluence is a novel non-Intersection over Union (IoU) alternative to Non-Maxima Suppression (NMS) in bounding box post-processing in object detection. It overcomes the inherent limitations of IoU-based NMS variants to provide a more…

Computer Vision and Pattern Recognition · Computer Science 2022-08-04 Andrew Shepley , Greg Falzon , Paul Kwan

To ensure safe urban driving for autonomous platforms, it is crucial not only to develop high-performance object detection techniques but also to establish a diverse and representative dataset that captures various urban environments and…

Computer Vision and Pattern Recognition · Computer Science 2024-06-03 Jin-Hee Lee , Jae-Keun Lee , Je-Seok Kim , Soon Kwon

It is laborious to manually label point cloud data for training high-quality 3D object detectors. This work proposes a weakly supervised approach for 3D object detection, only requiring a small set of weakly annotated scenes, associated…

Computer Vision and Pattern Recognition · Computer Science 2020-07-24 Qinghao Meng , Wenguan Wang , Tianfei Zhou , Jianbing Shen , Luc Van Gool , Dengxin Dai

This letter introduces SVN-ICP, a novel Iterative Closest Point (ICP) algorithm with uncertainty estimation that leverages Stein Variational Newton (SVN) on manifold. Designed specifically for fusing LiDAR odometry in multisensor systems,…

Robotics · Computer Science 2025-10-14 Shiping Ma , Haoming Zhang , Marc Toussaint

Existing solutions to visual simultaneous localization and mapping (V-SLAM) assume that errors in feature extraction and matching are independent and identically distributed (i.i.d), but this assumption is known to not be true -- features…

Computer Vision and Pattern Recognition · Computer Science 2020-11-20 Sadegh Rabiee , Joydeep Biswas

LiDAR is widely used to capture accurate 3D outdoor scene structures. However, LiDAR produces many undesirable noise points in snowy weather, which hamper analyzing meaningful 3D scene structures. Semantic segmentation with snow labels…

Computer Vision and Pattern Recognition · Computer Science 2022-08-09 Gwangtak Bae , Byungjun Kim , Seongyong Ahn , Jihong Min , Inwook Shim

Most existing person re-identification (re-id) methods focus on learning the optimal distance metrics across camera views. Typically a person's appearance is represented using features of thousands of dimensions, whilst only hundreds of…

Computer Vision and Pattern Recognition · Computer Science 2016-03-08 Li Zhang , Tao Xiang , Shaogang Gong

We study source-free unsupervised domain adaptation (SFUDA) for semantic segmentation, which aims to adapt a source-trained model to the target domain without accessing the source data. Many works have been proposed to address this…

Computer Vision and Pattern Recognition · Computer Science 2024-06-12 Dong Zhao , Shuang Wang , Qi Zang , Licheng Jiao , Nicu Sebe , Zhun Zhong

Event cameras, characterized by high temporal resolution, high dynamic range, low power consumption, and high pixel bandwidth, offer unique capabilities for object detection in specialized contexts. Despite these advantages, the inherent…

Computer Vision and Pattern Recognition · Computer Science 2024-03-25 Yimeng Fan , Wei Zhang , Changsong Liu , Mingyang Li , Wenrui Lu

Semi-supervised object detection (SSOD) has made significant progress with the development of pseudo-label-based end-to-end methods. However, many of these methods face challenges due to class imbalance, which hinders the effectiveness of…

Computer Vision and Pattern Recognition · Computer Science 2023-06-06 Purbayan Kar , Vishal Chudasama , Naoyuki Onoe , Pankaj Wasnik

Video salient object detection (VSOD) aims to locate and segment the most attractive object by exploiting both spatial cues and temporal cues hidden in video sequences. However, spatial and temporal cues are often unreliable in real-world…

Computer Vision and Pattern Recognition · Computer Science 2021-05-17 Peijia Chen , Jianhuang Lai , Guangcong Wang , Huajun Zhou