Saved in:
Bibliographic Details
Main Authors: Sellam, Abdellah Zakaria, Benaissa, Ilyes, Bekhouche, Salah Eddine, Hadid, Abdenour, Renó, Vito, Distante, Cosimo
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2509.00578
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909870583709696
author Sellam, Abdellah Zakaria
Benaissa, Ilyes
Bekhouche, Salah Eddine
Hadid, Abdenour
Renó, Vito
Distante, Cosimo
author_facet Sellam, Abdellah Zakaria
Benaissa, Ilyes
Bekhouche, Salah Eddine
Hadid, Abdenour
Renó, Vito
Distante, Cosimo
contents Fine-grained object detection in challenging visual domains, such as vehicle damage assessment, presents a formidable challenge even for human experts to resolve reliably. While DiffusionDet has advanced the state-of-the-art through conditional denoising diffusion, its performance remains limited by local feature conditioning in context-dependent scenarios. We address this fundamental limitation by introducing Context-Aware Fusion (CAF), which leverages cross-attention mechanisms to integrate global scene context with local proposal features directly. The global context is generated using a separate dedicated encoder that captures comprehensive environmental information, enabling each object proposal to attend to scene-level understanding. Our framework significantly enhances the generative detection paradigm by enabling each object proposal to attend to comprehensive environmental information. Experimental results demonstrate an improvement over state-of-the-art models on the CarDD benchmark, establishing new performance benchmarks for context-aware object detection in fine-grained domains
format Preprint
id arxiv_https___arxiv_org_abs_2509_00578
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle C-DiffDet+: Fusing Global Scene Context with Generative Denoising for High-Fidelity Car Damage Detection
Sellam, Abdellah Zakaria
Benaissa, Ilyes
Bekhouche, Salah Eddine
Hadid, Abdenour
Renó, Vito
Distante, Cosimo
Computer Vision and Pattern Recognition
Fine-grained object detection in challenging visual domains, such as vehicle damage assessment, presents a formidable challenge even for human experts to resolve reliably. While DiffusionDet has advanced the state-of-the-art through conditional denoising diffusion, its performance remains limited by local feature conditioning in context-dependent scenarios. We address this fundamental limitation by introducing Context-Aware Fusion (CAF), which leverages cross-attention mechanisms to integrate global scene context with local proposal features directly. The global context is generated using a separate dedicated encoder that captures comprehensive environmental information, enabling each object proposal to attend to scene-level understanding. Our framework significantly enhances the generative detection paradigm by enabling each object proposal to attend to comprehensive environmental information. Experimental results demonstrate an improvement over state-of-the-art models on the CarDD benchmark, establishing new performance benchmarks for context-aware object detection in fine-grained domains
title C-DiffDet+: Fusing Global Scene Context with Generative Denoising for High-Fidelity Car Damage Detection
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2509.00578