paper-with-me

Papers

Hyperbolic Uncertainty Aware Semantic Segmentation

2022-03-16 · Bike Chen, Wei Peng, Xiaofeng Cao, Juha Röning

Semantic segmentation (SS) aims to classify each pixel into one of the pre-defined classes. This task plays an important role in self-driving cars and autonomous drones. In SS, many works have shown that most misclassified pixels are commonly near object boundaries with high uncertainties. However, existing SS loss functions are not tailored to handle these uncertain pixels during training, as these pixels are usually treated equally as confidently classified pixels and cannot be embedded with arbitrary low distortion in Euclidean space, thereby degenerating the performance of SS. To overcome this problem, this paper designs a "Hyperbolic Uncertainty Loss" (HyperUL), which dynamically highlights the misclassified and high-uncertainty pixels in Hyperbolic space during training via the hyperbolic distances. The proposed HyperUL is model agnostic and can be easily applied to various neural architectures. After employing HyperUL to three recent SS models, the experimental results on Cityscapes and UAVid datasets reveal that the segmentation performance of existing SS models can be consistently improved.

📄 PDF Abstract BibTeX arXiv:2203.08881

Code (0)

등록된 구현이 없습니다.

Tasks

SegmentationSelf-Driving CarsSemantic Segmentation

Similar Papers 제목 키워드 기반

Lorentz Framework for Semantic Segmentation

2026-04-18 · Zahid Hasan, Masud Ahmed, Nirmalya Roy arxiv

Semantic segmentation in hyperbolic space enables compact modeling of hierarchical structure while providing inherent uncertainty quantification. Prior approaches predominantly rely on the Poincaré ball model, which suff…

Semantic Segmentation

Hyperbolic Active Learning for Semantic Segmentation under Domain Shift

2023-06-19 · Luca Franco, Paolo Mandica, Konstantinos Kallidromitis, Devin Guillory 외

We introduce a hyperbolic neural network approach to pixel-level active learning for semantic segmentation. Analysis of the data statistics leads to a novel interpretation of the hyperbolic radius as an indicator of data…

Domain AdaptationSemantic SegmentationSource-Free Domain Adaptation

Hyperbolic Uncertainty-Aware Few-Shot Incremental Point Cloud Segmentation

2025-01-01 · CVPR 2025 1 · Tanuj Sur, Samrat Mukherjee, Kaizer Rahaman, Subhasis Chaudhuri 외

3D point cloud segmentation is essential across a range of applications; however, conventional methods often struggle in evolving environments, particularly when tasked with identifying novel categories under limited…

class-incremental learningClass Incremental LearningFew-Shot Class-Incremental LearningFew-Shot Learning+3

Hyp-UML: Hyperbolic Image Retrieval with Uncertainty-aware Metric Learning

2023-10-12 · ShiYang Yan, Zongxuan Liu, Lin Xu

Metric learning plays a critical role in training image retrieval and classification. It is also a key algorithm in representation learning, e.g., for feature learning and its alignment in metric space. Hyperbolic embedd…

Contrastive LearningImage RetrievalMetric LearningRepresentation Learning+1

Hyperbolic Image Segmentation

2022-03-11 · CVPR 2022 1 · Mina GhadimiAtigh, Julian Schoep, Erman Acar, Nanne van Noord 외

For image segmentation, the current standard is to perform pixel-level optimization and inference in Euclidean output embedding spaces through linear hyperplanes. In this work, we show that hyperbolic manifolds provide a…

Image SegmentationSegmentationSemantic Segmentation