# Object Contour and Edge Detection with RefineContourNet

## TL;DR

RefineContourNet is a ResNet-based multi-path CNN that effectively fuses multi-level features for superior object contour and edge detection, achieving state-of-the-art results on standard datasets.

## Contribution

Introduces a novel multi-path refinement CNN that fuses high, mid, and low-level features in a specific order for improved contour detection.

## Key findings

- Achieves an ODS of 0.752 on PASCAL dataset for contour detection.
- Reaches an ODS of 0.824 on BSDS500 for edge detection.
- Outperforms previous methods in both contour and edge detection tasks.

## Abstract

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.