# Rethinking Superpixel Segmentation from Biologically Inspired Mechanisms

arXiv: https://arxiv.org/abs/2309.13438 · HTML: https://mlsanity.com/paper/2309.13438/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 47 references that are in the map.
- First posted on arXiv 23 Sep 2023.

## Builds on (most cited first, 10 of 10)

- [Augmented Reality Meets Computer Vision : Efficient Data Generation for Urban Driving Scenes](https://mlsanity.com/paper/1708.01566/) (2017)
- [Superpixel Sampling Networks](https://mlsanity.com/paper/1807.10174/) (2018)
- [SEEDS: Superpixels Extracted via Energy-Driven Sampling](https://mlsanity.com/paper/1309.3848/) (2013)
- [Superpixel Segmentation with Fully Convolutional Networks](https://mlsanity.com/paper/2003.12929/) (2020)
- [Superpixels: An Evaluation of the State-of-the-Art](https://mlsanity.com/paper/1612.01601/) (2016)
- [Superpixel Convolutional Networks using Bilateral Inceptions](https://mlsanity.com/paper/1511.06739/) (2015)
- [Robust Semantic Segmentation with Superpixel-Mix](https://mlsanity.com/paper/2108.00968/) (2021)
- [Adaptive Superpixel for Active Learning in Semantic Segmentation](https://mlsanity.com/paper/2303.16817/) (2023)
- [E-CRF: Embedded Conditional Random Field for Boundary-caused Class Weights Confusion in Semantic Segmentation](https://mlsanity.com/paper/2112.07106/) (2021)
- [AINet+: Advancing Superpixel Segmentation via Cascaded Association Implantation](https://mlsanity.com/paper/2101.10696/) (2021)

## Built on by (most cited first, 2 of 2)

- [Superpixel Segmentation: A Long-Lasting Ill-Posed Problem](https://mlsanity.com/paper/2411.06478/) (2024)
- [Multivariate Time Series Forecasting needs Cross Variable Loss](https://mlsanity.com/paper/2608.05742/) (2026)

## Abstract (arXiv)

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.