Skip to content
AI News HubLIVE
Original source2 min read

Evidential Deep Learning for Multi-Modal Anti-UAV Detection

Summary

A controlled ablation across three benchmarks finds that evidential deep learning's gains come mainly from its training objective rather than its uncertainty estimates, while Dempster-Shafer fusion, Dirichlet vacuity, and temporal sensor gating fail to support their hypotheses.

SourcearXiv Computer VisionAuthor: Dmitry Golovchits, Seyed Sahand Mohammadi Ziabari, Ali Mohammed Mansoor Alsahag
Evidential Deep Learning for Multi-Modal Anti-UAV Detection
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[Submitted on 1 Sep 2026]

Title:Evidential Deep Learning for Multi-Modal Anti-UAV Detection

View a PDF of the paper titled Evidential Deep Learning for Multi-Modal Anti-UAV Detection, by Dmitry Golovchits and 2 other authors

View PDF HTML (experimental)

Abstract:Anti-UAV systems increasingly fuse multiple sensors, yet their detection heads provide no per-modality reliability signal. This study evaluates whether evidential deep learning (EDL) heads, Dempster-Shafer (DS) evidence fusion, and uncertainty-driven temporal sensor gating improve anti-UAV detection through a controlled ablation on three benchmarks: thermal tracking (AntiUAV600), RGB-audio-RF classification (TRIDENT), and RGB-IR tracking (MM-UAV). The EDL training objective improves accuracy over retrained sigmoid baselines (+5.9 percentage points in accuracy and a tripled tracker-on-absent rate in E1; +4.8 percentage points in classification accuracy in E2, surviving a clip-clustered bootstrap, p = 0.011) and ranks classification errors substantially better (entropy UAUC approximately 0.94 vs. 0.51). The remaining components do not support their respective hypotheses. DS fusion does not outperform simple probability averaging. Dirichlet vacuity adds no ranking power beyond predictive entropy and inverts at the detection level, where extreme background imbalance causes it to encode class membership rather than error likelihood, a failure also observed for entropy and sigmoid confidence. Temporal gating preserves accuracy only when nearly inactive and yields no realised latency saving on shared-backbone hardware. The benefit of evidential learning therefore arises primarily from its training objective rather than its uncertainty estimate; a crop-level control further localises the detection-level breakdown to anchor-level evaluation rather than the learned representation.

Subjects:

Computer Vision and Pattern Recognition (cs.CV)

Cite as: arXiv:2609.01742 [cs.CV]

(or arXiv:2609.01742v1 [cs.CV] for this version)

https://doi.org/10.48550/arXiv.2609.01742

arXiv-issued DOI via DataCite

Submission history

From: Seyed Sahand Mohammadi Ziabari [view email] [v1] Tue, 1 Sep 2026 18:09:46 UTC (1,242 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled Evidential Deep Learning for Multi-Modal Anti-UAV Detection, by Dmitry Golovchits and 2 other authors

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.CV

new | recent | 2026-09

Change to browse by:

cs

References & Citations

NASA ADS

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

Key points and analysis

Article intelligence

InvestorsAdvanced

Key points

  • The EDL training objective improves accuracy by 5.9 percentage points and triples the tracker-on-absent rate in E1, and raises classification accuracy by 4.8 points in E2 (p = 0.011).
  • EDL ranks classification errors much better, with entropy UAUC around 0.94 versus 0.51 for the baseline.
  • DS fusion does not beat simple probability averaging, and Dirichlet vacuity inverts at the detection level under extreme background imbalance.
  • Temporal gating preserves accuracy only when nearly inactive and yields no realised latency saving on shared-backbone hardware.

Highlights and analysis are generated automatically and may contain errors. Check the original source.