Object detection is widely applied in fields such as scene perception and intelligent driving. However, interfered by degradations such as rain, haze, and snow, object detection in adverse weather conditions pose significant challenges. Mainstream methods usually fail to take into account the object detection of degraded images and cannot effectively handle them. In this paper, we present a Restoration-enhanced object detection network for adverse weather scenes enabled by Degradation Modeling, dubbed RDMNet. Firstly, to capture more potential information of degraded images, we incorporate the idea of restoration into the detection network, thus forming a dual branch network. Secondly, to improve the network's adaptability for different weather types, we propose to model the degradation of degraded images and learn its multi-scale degradation representations to guide the feature transformation in both restoration and detection branches. Finally, to facilitate the cross-task integration of restoration and detection branches, we develop a multi-scale bi-directional feature fusion block and propose a restoration weight decay training strategy. Extensive experiments in rain, haze, and snow weathers demonstrate that our RDMNet outperforms the recent object detection approaches. The code and datasets are available at https://github.com/xfwang23/RDMNet .
With the advent of image super-resolution (SR) algorithms, how to evaluate the quality of generated SR images has become an urgent task. Although full-reference methods perform well in SR image quality assessment (SR-IQA), their reliance on high-resolution (HR) images limits their practical applicability. Leveraging available reconstruction information as much as possible for SR-IQA, such as low-resolution (LR) images and the scale factors, is a promising way to enhance assessment performance for SR-IQA without HR for reference. In this paper, we attempt to evaluate the perceptual quality and reconstruction fidelity of SR images considering LR images and scale factors. Specifically, we propose a novel dual-branch reduced-reference SR-IQA network, i.e. , Perception-and Fidelity-aware SR-IQA (PFIQA). The perception-aware branch evaluates the perceptual quality of SR images by leveraging the merits of global modeling of Vision Transformer (ViT) and local relation of ResNet, and incorporating the scale factor to enable comprehensive visual perception. Meanwhile, the fidelity-aware branch assesses the reconstruction fidelity between LR and SR images through their visual perception. The combination of the two branches substantially aligns with the human visual system, enabling a comprehensive SR image evaluation. Experimental results indicate that our PFIQA outperforms current state-of-the-art models across three widely-used SR-IQA benchmarks. Notably, PFIQA excels in assessing the quality of real-world SR images. Our code is available at https://github.com/xinyouu/PFIQA.
6 January 2022 in Expert Systems with Applications
The majority of advanced remote sensing object detection technologies excel in accurately detecting objects from high-resolution images. However, in practical scenarios, it is often necessary to detect objects in images of varying resolutions due to differences in imaging equipment. When dealing with lower-resolution images, the limited detailed information and blurry boundaries lead to a noticeable decrease in detection accuracy. To address this problem, we propose an efficient object detection method for low-resolution remote sensing images based on the YOLO detector, named CRKD-YOLO. The method constructs a cross-resolution knowledge distillation (CRKD) framework to resolve the issue of feature mismatch, enabling the model with low-resolution inputs to learn more refined feature representations from high-resolution images. Furthermore, to effectively leverage the limited detailed information in low-resolution images, we propose the backbone augment feature pyramid network (BAFPN). It enhances detection accuracy for low-resolution remote sensing images while making the model more lightweight. Massive experiments on DOTA, DIOR, NWPU VHR-10, DroneVehicle, and VEDAI demonstrate that our CRKD-YOLO achieves significant improvements, even achieving higher accuracy compare to training and testing high-resolution images with baseline. Our code is published at https://github.com/Jianfantasy/CRKD-YOLO