Saved in:
Bibliographic Details
Main Author: Liu, Mingquan
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2506.21905
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908425395372032
author Liu, Mingquan
author_facet Liu, Mingquan
contents Fine Grained Visual Categorization (FGVC) remains a challenging task in computer vision due to subtle inter class differences and fragile feature representations. Existing methods struggle in fine grained scenarios, especially when labeled data is scarce. We propose a semi supervised method combining Mamba based feature modeling, region attention, and Bayesian uncertainty. Our approach enhances local to global feature modeling while focusing on key areas during learning. Bayesian inference selects high quality pseudo labels for stability. Experiments show strong performance on FGVC benchmarks with occlusions, demonstrating robustness when labeled data is limited. Code is available at https://github.com/wxqnl/RAUM Net.
format Preprint
id arxiv_https___arxiv_org_abs_2506_21905
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle RAUM-Net: Regional Attention and Uncertainty-aware Mamba Network
Liu, Mingquan
Computer Vision and Pattern Recognition
Fine Grained Visual Categorization (FGVC) remains a challenging task in computer vision due to subtle inter class differences and fragile feature representations. Existing methods struggle in fine grained scenarios, especially when labeled data is scarce. We propose a semi supervised method combining Mamba based feature modeling, region attention, and Bayesian uncertainty. Our approach enhances local to global feature modeling while focusing on key areas during learning. Bayesian inference selects high quality pseudo labels for stability. Experiments show strong performance on FGVC benchmarks with occlusions, demonstrating robustness when labeled data is limited. Code is available at https://github.com/wxqnl/RAUM Net.
title RAUM-Net: Regional Attention and Uncertainty-aware Mamba Network
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2506.21905