Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Latent Discriminant deterministic Uncertainty

About

Predictive uncertainty estimation is essential for deploying Deep Neural Networks in real-world autonomous systems. However, most successful approaches are computationally intensive. In this work, we attempt to address these challenges in the context of autonomous driving perception tasks. Recently proposed Deterministic Uncertainty Methods (DUM) can only partially meet such requirements as their scalability to complex computer vision tasks is not obvious. In this work we advance a scalable and effective DUM for high-resolution semantic segmentation, that relaxes the Lipschitz constraint typically hindering practicality of such architectures. We learn a discriminant latent space by leveraging a distinction maximization layer over an arbitrarily-sized set of trainable prototypes. Our approach achieves competitive results over Deep Ensembles, the state-of-the-art for uncertainty prediction, on image classification, segmentation and monocular depth estimation tasks. Our code is available at https://github.com/ENSTA-U2IS/LDU

Gianni Franchi, Xuanlong Yu, Andrei Bursuc, Emanuel Aldea, Severine Dubuisson, David Filliat• 2022

Related benchmarks

TaskDatasetResultRank
Semantic segmentationCholecSeg8K (test)--
13
3D Object DetectionaiMotive (test)
Mean AP (all-point)64.69
12
Tissue SegmentationCholecSeg8K corrupted (test)
Precision1.44
11
Tissue SegmentationEndoscopic Submucosal Dissection (ESD) (test)
ECE14.12
11
Tissue SegmentationEndoscopic Submucosal Dissection (ESD) OOD corrupted (test)
PR Score1.33
11
3D Object DetectionaiMotive Over-Exposure
AP (all-point)65.07
6
3D Object DetectionaiMotive LiDAR-Fog
AP (All-Point)65.47
6
3D Object DetectionaiMotive distant region >75m (test)
Highway (all-point AP)43.07
6
3D Object DetectionaiMotive Motion Blur
AP (All-Point)62.06
6
3D Object DetectionaiMotive Under-Exposure
AP (All-Point)62.87
6
Showing 10 of 11 rows

Other info

Follow for update