paper-with-me

Papers

Robust Semantic Segmentation with Superpixel-Mix

2021-08-02 · Gianni Franchi, Nacim Belkhir, Mai Lan Ha, Yufei Hu, Andrei Bursuc, Volker Blanz, Angela Yao

Along with predictive performance and runtime speed, reliability is a key requirement for real-world semantic segmentation. Reliability encompasses robustness, predictive uncertainty and reduced bias. To improve reliability, we introduce Superpixel-mix, a new superpixel-based data augmentation method with teacher-student consistency training. Unlike other mixing-based augmentation techniques, mixing superpixels between images is aware of object boundaries, while yielding consistent gains in segmentation accuracy. Our proposed technique achieves state-of-the-art results in semi-supervised semantic segmentation on the Cityscapes dataset. Moreover, Superpixel-mix improves the reliability of semantic segmentation by reducing network uncertainty and bias, as confirmed by competitive results under strong distributions shift (adverse weather, image corruptions) and when facing out-of-distribution data.

📄 PDF Abstract BibTeX arXiv:2108.00968

Code (2)

giannifranchi/deeplabv3-superpixelmix 공식 구현 pytorch
valeoai/bravo_challenge pytorch

Tasks

Data AugmentationSegmentationSemantic SegmentationSemi-Supervised Semantic SegmentationSuperpixels

Methods 이 논문이 사용한 방법론

AWARE We propose to theoretically and empirically examine the effect of incorporating weighting schemes into walk-aggregating GNNs. To this end, we propose a simple, interpretable, and…

Similar Papers 제목 키워드 기반

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

Superpixel Transformers for Efficient Semantic Segmentation

2023-09-28 · Alex Zihao Zhu, Jieru Mei, Siyuan Qiao, Hang Yan 외

Semantic segmentation, which aims to classify every pixel in an image, is a key task in machine perception, with many applications across robotics and autonomous driving. Due to the high dimensionality of this task, most…

Autonomous DrivingSegmentationSemantic SegmentationSuperpixels

Re-purposing SAM into Efficient Visual Projectors for MLLM-Based Referring Image Segmentation

2025-09-17 · Xiaobo Yang, Xiaojin Gong arxiv

Recently, Referring Image Segmentation (RIS) frameworks that pair the Multimodal Large Language Model (MLLM) with the Segment Anything Model (SAM) have achieved impressive results. However, adapting MLLM to segmentation …

Image Segmentation

Generating superpixels using deep image representations

2019-03-11 · Thomas Verelst, Matthew Blaschko, Maxim Berman

Superpixel algorithms are a common pre-processing step for computer vision algorithms such as segmentation, object tracking and localization. Many superpixel methods only rely on colors features for segmentation, limitin…

ClusteringGeneral ClassificationObjectObject Tracking+3

Revisiting Superpixels for Active Learning in Semantic Segmentation With Realistic Annotation Costs

2021-06-19 · CVPR 2021 1 · Lile Cai, Xun Xu, Jun Hao Liew, Chuan Sheng Foo

State-of-the-art methods for semantic segmentation are based on deep neural networks that are known to be data-hungry. Region-based active learning has shown to be a promising method for reducing data annotation cost…

Active LearningSemantic SegmentationSuperpixels