Msmsfnet: a multi-stream and multi-scale fusion net for edge detection (2404.04856v2)

Abstract: Edge detection is a long-standing problem in computer vision. Recent deep learning based algorithms achieve state-of-the-art performance in publicly available datasets. Despite their efficiency, their performance, however, relies heavily on the pre-trained weights of the backbone network on the ImageNet dataset. This significantly limits the design space of deep learning based edge detectors. Whenever we want to devise a new model, we have to train this new model on the ImageNet dataset first, and then fine-tune the model using the edge detection datasets. The comparison would be unfair otherwise. However, it is usually not feasible for many researchers to train a model on the ImageNet dataset due to the limited computation resources. Besides, if these methods need to be trained to detect edges in a different kind of data, Synthetic Aperture Radar (SAR) images for instance, the pre-trained weights on the ImageNet dataset are unlikely to improve the edge detection accuracy due to the strong differences in the statistics between optical and SAR images. In the meantime, no dataset for SAR image processing matches the size of the ImageNet dataset. In this work, we study the performance achievable by existing methods in publicly available datasets when they are trained from scratch, and devise a new network architecture, the multi-stream and multi-scale fusion net (msmsfnet), for edge detection. We show in our experiments that by training all models from scratch to ensure the fairness of comparison, our model outperforms state-of-the-art deep learning based edge detectors in three publicly available datasets. The efficiency of our model is further demonstrated by the experiments for edge detection in SAR images, which serves as an important evidence showing the meaningfulness of this work as no useful pre-trained weight is available for edge detection in SAR images.