SOTA: Spike-Navigated Optimal TrAnsport Saliency Region Detection in Composite-bias Videos

TL;DR

This paper introduces SOTA, a novel saliency detection framework utilizing spike camera data to improve robustness against noise, motion blur, and occlusions, outperforming existing methods in real-world scenarios.

Contribution

The paper presents Spike-navigated Optimal TrAnsport Saliency Region Detection (SOTA), a new method that mitigates biases in spike camera-based saliency detection through innovative debiasing techniques.

Findings

SOTA outperforms existing methods on real and synthetic datasets.

The proposed debiasing techniques effectively reduce noise and bias.

SOTA enhances saliency detection accuracy in challenging conditions.

Abstract

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.