Object Contour and Edge Detection with RefineContourNet
This work addresses the problem of improving accuracy in object contour and edge detection for computer vision applications, representing an incremental advancement over existing methods.
The paper tackles object contour and edge detection by using a ResNet-based multi-path refinement CNN that fuses high, mid, and low-level features in a specific order, achieving state-of-the-art results with an ODS of 0.752 on a refined PASCAL-val dataset and 0.824 on BSDS500 for edge detection.
A ResNet-based multi-path refinement CNN is used for object contour detection. For this task, we prioritise the effective utilization of the high-level abstraction capability of a ResNet, which leads to state-of-the-art results for edge detection. Keeping our focus in mind, we fuse the high, mid and low-level features in that specific order, which differs from many other approaches. It uses the tensor with the highest-levelled features as the starting point to combine it layer-by-layer with features of a lower abstraction level until it reaches the lowest level. We train this network on a modified PASCAL VOC 2012 dataset for object contour detection and evaluate on a refined PASCAL-val dataset reaching an excellent performance and an Optimal Dataset Scale (ODS) of 0.752. Furthermore, by fine-training on the BSDS500 dataset we reach state-of-the-art results for edge-detection with an ODS of 0.824.