Rank-Aware Quantile Activation for Motion-Robust Crop Segmentation in UAV Imagery

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kiran, Abinav, Danda, Sravan, Challa, Aditya, Sen, Sougata, S, Daya Sagar B
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913176973475840
author Kiran, Abinav
Danda, Sravan
Challa, Aditya
Sen, Sougata
S, Daya Sagar B
author_facet Kiran, Abinav
Danda, Sravan
Challa, Aditya
Sen, Sougata
S, Daya Sagar B
contents Motion blur from high-speed UAV acquisition de-grades semantic segmentation on rare texture-dependent classes with high agronomic value. Standard CNNs rely on high-frequency magnitude features that blur destroys, causing statistical erasure of minority signals. We propose Dual Quantile Activation (QAct), a rank-aware block replacing magnitude gating with instance-level rank normalization. Evaluated onAgriculture-Vision 2021 across zero-shot and blur-supervised regimes at multiple severities, QAct is the dominant architectural factor: it delivers consistent mIoU gains over ReLU across both regimes and all severities, with strongest gains on rare structural and texture-dependent classes. Some dominant classes (water,planter skip) show mixed per-class performance under distillation. At moderate blur, zero-shot QAct outperforms distillation-trained ReLU; across all severities, Distill-QAct achieves best performance, confirming rank aware activation and blur-domain training are complementary robustness sources.
format Preprint
id arxiv_https___arxiv_org_abs_2606_01118
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Rank-Aware Quantile Activation for Motion-Robust Crop Segmentation in UAV Imagery
Kiran, Abinav
Danda, Sravan
Challa, Aditya
Sen, Sougata
S, Daya Sagar B
Computer Vision and Pattern Recognition
Motion blur from high-speed UAV acquisition de-grades semantic segmentation on rare texture-dependent classes with high agronomic value. Standard CNNs rely on high-frequency magnitude features that blur destroys, causing statistical erasure of minority signals. We propose Dual Quantile Activation (QAct), a rank-aware block replacing magnitude gating with instance-level rank normalization. Evaluated onAgriculture-Vision 2021 across zero-shot and blur-supervised regimes at multiple severities, QAct is the dominant architectural factor: it delivers consistent mIoU gains over ReLU across both regimes and all severities, with strongest gains on rare structural and texture-dependent classes. Some dominant classes (water,planter skip) show mixed per-class performance under distillation. At moderate blur, zero-shot QAct outperforms distillation-trained ReLU; across all severities, Distill-QAct achieves best performance, confirming rank aware activation and blur-domain training are complementary robustness sources.
title Rank-Aware Quantile Activation for Motion-Robust Crop Segmentation in UAV Imagery
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2606.01118