Multi-Scale Patch Aggregation (MPA) for Simultaneous Detection and Segmentation

2016-06-01 · CVPR 2016 6 · Shu Liu, Xiaojuan Qi, Jianping Shi, Hong Zhang, Jiaya Jia

Aiming at simultaneous detection and segmentation (SDS), we propose a proposal-free framework, which detect and segment object instances via mid-level patches. We design a unified trainable network on patches, which is followed by a fast and effective patch aggregation algorithm to infer object instances. Our method benefits from end-to-end training. Without object proposal generation, computation time can also be reduced. In experiments, our method yields results 62.1% and 61.8% in terms of mAPr on VOC2012 segmentation val and VOC2012 SDS val, which are state-of-the-art at the time of submission. We also report results on Microsoft COCO test-std/test-dev dataset in this paper.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

ObjectObject Proposal Generation Segmentation

Coarse-to-Fine Embedded PatchMatch and Multi-Scale Dynamic Aggregation for Reference-based Super-Resolution

2022-01-12 · Bin Xia, Yapeng Tian, Yucheng Hang, Wenming Yang 외

Reference-based super-resolution (RefSR) has made significant progress in producing realistic textures using an external reference (Ref) image. However, existing RefSR methods obtain high-quality correspondence matchings…

Reference-based Super-Resolution Super-Resolution

Multi-Target Federated Backdoor Attack Based on Feature Aggregation

2025-02-23 · Lingguag Hao, Kuangrong Hao, Bing Wei, Xue-song Tang

Current federated backdoor attacks focus on collaboratively training backdoor triggers, where multiple compromised clients train their local trigger patches and then merge them into a global trigger during the inference …

Backdoor Attack Federated Learning

DINOv3 Visual Representations for Blueberry Perception Toward Robotic Harvesting

2026-03-02 · Rui-Feng Wang, Daniel Petti, Yue Chen, Changying Li arxiv

Vision Foundation Models trained via large-scale self-supervised learning have demonstrated strong generalization in visual perception; however, their practical role and performance limits in agricultural settings remain…

Self-Supervised Learning

COVID-19 Infection Segmentation from Chest CT Images Based on Scale Uncertainty

2022-01-09 · Masahiro Oda, Tong Zheng, Yuichiro Hayashi, Yoshito Otake 외

This paper proposes a segmentation method of infection regions in the lung from CT volumes of COVID-19 patients. COVID-19 spread worldwide, causing many infected patients and deaths. CT image-based diagnosis of COVID-19 …

Prediction Segmentation

PFF-Net: Patch Feature Fitting for Point Cloud Normal Estimation

2025-11-26 · Qing Li, Huifang Feng, Kanle Shi, Yue Gao 외 arxiv

Estimating the normal of a point requires constructing a local patch to provide center-surrounding context, but determining the appropriate neighborhood size is difficult when dealing with different data or geometries. E…

Point Clouds