paper-with-me

Papers

Rethinking Superpixel Segmentation from Biologically Inspired Mechanisms

2023-09-23 · TingYu Zhao, Bo Peng, Yuan Sun, DaiPeng Yang, Zhenguang Zhang, Xi Wu

Recently, advancements in deep learning-based superpixel segmentation methods have brought about improvements in both the efficiency and the performance of segmentation. However, a significant challenge remains in generating superpixels that strictly adhere to object boundaries while conveying rich visual significance, especially when cross-surface color correlations may interfere with objects. Drawing inspiration from neural structure and visual mechanisms, we propose a biological network architecture comprising an Enhanced Screening Module (ESM) and a novel Boundary-Aware Label (BAL) for superpixel segmentation. The ESM enhances semantic information by simulating the interactive projection mechanisms of the visual cortex. Additionally, the BAL emulates the spatial frequency characteristics of visual cortical cells to facilitate the generation of superpixels with strong boundary adherence. We demonstrate the effectiveness of our approach through evaluations on both the BSDS500 dataset and the NYUv2 dataset.

📄 PDF Abstract BibTeX arXiv:2309.13438

Code (0)

등록된 구현이 없습니다.

Tasks

SegmentationSuperpixels

Similar Papers 제목 키워드 기반

Superpixel Segmentation: A Long-Lasting Ill-Posed Problem

2024-11-10 · Rémi Giraud, Michaël Clément

For many years, image over-segmentation into superpixels has been essential to computer vision pipelines, by creating homogeneous and identifiable regions of similar sizes. Such constrained segmentation problem would req…

SegmentationSemantic SegmentationSuperpixels

Rethinking Unsupervised Neural Superpixel Segmentation

2022-06-21 · Moshe Eliasof, Nir Ben Zikri, Eran Treister

Recently, the concept of unsupervised learning for superpixel segmentation via CNNs has been studied. Essentially, such methods generate superpixels by convolutional neural network (CNN) employed on a single image, and s…

SegmentationSuperpixels

Adaptive Superpixel for Active Learning in Semantic Segmentation

2023-03-29 · ICCV 2023 1 · Hoyoung Kim, Minhyeon Oh, Sehyun Hwang, Suha Kwak 외

Learning semantic segmentation requires pixel-wise annotations, which can be time-consuming and expensive. To reduce the annotation cost, we propose a superpixel-based active learning (AL) framework, which collects a dom…

Active LearningSegmentationSemantic SegmentationSuperpixels

Improved Robustness from Biologically Inspired Sparse Contrast Representations

2025-09-29 · Lorena Stracke, Lia Nimmermann, Shashank Agnihotri, Margret Keuper 외 arxiv

Deep neural networks surpass humans on many vision benchmarks, yet remain far less robust to distribution shifts such as illumination and weather changes. Existing approaches address this challenge by additional training…

Semantic Segmentation

MSP : Refine Boundary Segmentation via Multiscale Superpixel

2021-12-03 · Jie Zhu, Huabin Huang, Banghuai Li, Yong liu 외

In this paper, we propose a simple but effective message passing method to improve the boundary quality for the semantic segmentation result. Inspired by the generated sharp edges of superpixel blocks, we employ superpix…

Scene ParsingSegmentationSemantic Segmentation