Signals 4 · free daily AI digest

ODPure: Backdoor Purification for Object Detection via Ensemble Corruption Consensus

Paper recorded by Signals 4 on 2026-09-23 in cs.CV. Abstract reproduced from arXiv; link to the original below.

Published 2026-09-23 on arXiv · recorded by Signals 4 on 2026-09-24

Category: cs.CV · 计算机视觉 · first seen 2026-09-24

Abstract

With the development of applications like autonomous driving, object detection has gained significant attention, while also highlighting critical vulnerabilities like backdoor attacks that severely compromise model integrity. Specifically, such attacks involve altering the categories of objects (i.e., object misclassification), removing bounding boxes (i.e., object disappearance), or generating bo

Read on arXiv →

#15 most recent of 301 cs.CV papers we have recorded · ↑ newer: Generalizable Robotic Insertion with World Models · ↓ older: φ-RIE: From Photorealistic Reconstruction to Interactive Environments
Cite this page: ODPure: Backdoor Purification for Object Detection via Ensemble Corruption Consensus: the #15 most recent of 301 cs.CV papers we have recorded (as of 2026-09-23). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/odpure-backdoor-purification-for-object-detection-via-ensemble-corruption-consen.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable: papers.json
Related: More cs.CV papers · arXiv signals · All papers · Today in AI
Get 4 AI signals a day by email — free.
Subscribe free → See all plans →
Get 4 AI signals a day by email — free
All models · All repos · By company · Daily editions