Delving into Cascaded Instability: A Lipschitz Continuity View on Image Restoration and Object Detection Synergy
cascade frameworksdecision boundariesdetection networksdetection robustnessfeature learningfunctional mismatchgradient flowhaze benchmarksimage restorationlipschitz continuitylipschitz-regularized object detectionlow-light benchmarksoptimizationrestoration networksyolo detectors
To improve detection robustness in adverse conditions (e.g., haze and low light), image restoration is commonly applied as a pre-processing step to enhance image quality for the detector. However, the functional mismatch between restoration and detection networks can introduce instability and hinder effective integration