Learning Cruxes to Push for Object Detection in Low-Quality Images

Highly degraded images greatly challenge existing algorithms to detect objects of interest in adverse scenarios, such as rain, fog, and underwater. Recently, researchers develop sophisticated deep architectures in order to enhance image quality. Unfortunately, the visually appealing output of the enhancement module does not necessarily generate high accuracy for deep detectors. Another feasible solution for low-quality image detection is to transform it into a domain adaptation problem. Typically, these approaches invoke complicated training strategies such as adversarial learning and graph matching. False detection is likely to occur in local regions of a low-quality image. In this paper, we propose a simple yet effective strategy with two learners for low-quality image detection. We devise the crux learner to generate cruxes that have great impacts on detection performance. The catch-up leaner with a simple residual transfer mechanism maps the feature distributions of crux regions to those favouring a deep detector. These two learners can be plugged into any CNN-based feature extraction networks, e.g., ResNetXT101 and ResNet50, and yield high detection accuracy on various degraded scenarios. Extensive experiments on several public datasets demonstrate that our method achieves more promising results than state-of-the-art detection approaches. The codes: https://github.com/xiaoDetection/learning-cruxes-to-push .