SLICK: Selective Localization and Instance Calibration for Knowledge-Enhanced Car Damage Segmentation in Automotive Insurance

TL;DR

SLICK is a comprehensive framework that combines structural priors, attention mechanisms, and knowledge fusion to enhance car damage segmentation accuracy and robustness in real-world automotive inspection scenarios.

Contribution

It introduces five novel components that improve damage segmentation precision by leveraging structural priors, attention, and domain knowledge, addressing occlusion, noise, and rare cases.

Findings

Superior segmentation performance on large-scale datasets

Enhanced robustness to occlusion and noise

Effective generalization to real-world inspection scenarios

Abstract

We present SLICK, a novel framework for precise and robust car damage segmentation that leverages structural priors and domain knowledge to tackle real-world automotive inspection challenges. SLICK introduces five key components: (1) Selective Part Segmentation using a high-resolution semantic backbone guided by structural priors to achieve surgical accuracy in segmenting vehicle parts even under occlusion, deformation, or paint loss; (2) Localization-Aware Attention blocks that dynamically focus on damaged regions, enhancing fine-grained damage detection in cluttered and complex street scenes; (3) an Instance-Sensitive Refinement head that leverages panoptic cues and shape priors to disentangle overlapping or adjacent parts, enabling precise boundary alignment; (4) Cross-Channel Calibration through multi-scale channel attention that amplifies subtle damage signals such as scratches and dents while suppressing noise like reflections and decals; and (5) a Knowledge Fusion Module that integrates synthetic crash data, part geometry, and real-world insurance datasets to improve generalization and handle rare cases effectively. Experiments on large-scale automotive datasets demonstrate SLICK's superior segmentation performance, robustness, and practical applicability for insurance and automotive inspection workflows.