SOTA: Spike-Navigated Optimal TrAnsport Saliency Region Detection in Composite-bias Videos
This addresses saliency detection for spike camera applications, which is incremental as it builds on existing spike camera advantages while mitigating specific noise biases.
The paper tackles the problem of saliency detection in composite-bias videos from spike cameras, which suffer from noise-induced discontinuities and distortions, by proposing the SOTA framework that uses spike-based debiasing techniques to eliminate composite noise bias. The result shows that SOTA outperforms existing methods on real and synthetic datasets, with code and dataset to be released.
Existing saliency detection methods struggle in real-world scenarios due to motion blur and occlusions. In contrast, spike cameras, with their high temporal resolution, significantly enhance visual saliency maps. However, the composite noise inherent to spike camera imaging introduces discontinuities in saliency detection. Low-quality samples further distort model predictions, leading to saliency bias. To address these challenges, we propose Spike-navigated Optimal TrAnsport Saliency Region Detection (SOTA), a framework that leverages the strengths of spike cameras while mitigating biases in both spatial and temporal dimensions. Our method introduces Spike-based Micro-debias (SM) to capture subtle frame-to-frame variations and preserve critical details, even under minimal scene or lighting changes. Additionally, Spike-based Global-debias (SG) refines predictions by reducing inconsistencies across diverse conditions. Extensive experiments on real and synthetic datasets demonstrate that SOTA outperforms existing methods by eliminating composite noise bias. Our code and dataset will be released at https://github.com/lwxfight/sota.