Lighting-aware Unified Model for Instance Segmentation
For instance segmentation models like SAM, the paper addresses the practical problem of performance drop under varied lighting conditions, offering a lightweight solution.
The paper tackles the degradation of SAM-based instance segmentation under diverse real-world illumination by introducing a Lighting Convolutional-Attention adapter that improves robustness without fine-tuning the backbone, achieving superior lighting-robust segmentation across multiple benchmarks.
Foundation models like the Segment Anything Model (SAM) demonstrate impressive zero-shot generalization but frequently degrade under diverse real-world illumination, particularly for instance segmentation. In this work, we address this limitation by developing \textit{Lighting Convolutional-Attention (\lca{})}, an adapter module that enhances segmentation robustness without fine-tuning the heavy backbone. \lca{} employs a dual-branch architecture to process RGB features alongside contrast maps, enabling physically motivated sensitivity to structural changes rather than illumination artifacts. We optimize \lca{} through a pairwise training strategy, introducing a targeted loss term that explicitly penalizes discrepancies between clean images and their corresponding illumination variants. To evaluate and support this architecture, we conduct a comprehensive empirical study across multiple existing benchmarks and present a novel Unity-based synthetic dataset specifically designed to accurately replicate complex real-world lighting conditions. Extensive experimental results demonstrate that our approach successfully bridges the domain gap, delivering superior lighting-robust segmentation.