# Semantic Edge Detection with Diverse Deep Supervision

arXiv: https://arxiv.org/abs/1804.02864 · HTML: https://mlsanity.com/paper/1804.02864/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Apr 2018.

## Built on by (most cited first, 13 of 13)

- [Concealed Object Detection](https://mlsanity.com/paper/2102.10274/) (2021)
- [Open-World Instance Segmentation: Exploiting Pseudo Ground Truth From Learned Pairwise Affinity](https://mlsanity.com/paper/2204.06107/) (2022)
- [Vision Transformers with Hierarchical Attention](https://mlsanity.com/paper/2106.03180/) (2021)
- [Learning Local and Global Temporal Contexts for Video Semantic Segmentation](https://mlsanity.com/paper/2204.03330/) (2022)
- [A Comprehensive Review on Deep Supervision: Theories and Applications](https://mlsanity.com/paper/2207.02376/) (2022)
- [Focus for Free in Density-Based Counting](https://mlsanity.com/paper/2306.05129/) (2023)
- [Revisiting Computer-Aided Tuberculosis Diagnosis](https://mlsanity.com/paper/2307.02848/) (2023)
- [Mobile-Seed: Joint Semantic Segmentation and Boundary Detection for Mobile Robots](https://mlsanity.com/paper/2311.12651/) (2023)
- [PNT-Edge: Towards Robust Edge Detection with Noisy Labels by Learning Pixel-level Noise Transitions](https://mlsanity.com/paper/2307.14070/) (2023)
- [Rethinking Interactive Image Segmentation: Feature Space Annotation](https://mlsanity.com/paper/2101.04378/) (2021)
- [Zero Pixel Directional Boundary by Vector Transform](https://mlsanity.com/paper/2203.08795/) (2022)
- [Boosting Semantic Segmentation with Semantic Boundaries](https://mlsanity.com/paper/2304.09427/) (2023)
- [Empirical Study of Multi-Task Hourglass Model for Semantic Segmentation Task](https://mlsanity.com/paper/2105.13531/) (2021)

## Abstract (arXiv)

Semantic edge detection (SED), which aims at jointly extracting edges as well as their category information, has far-reaching applications in domains such as semantic segmentation, object proposal generation, and object recognition. SED naturally requires achieving two distinct supervision targets: locating fine detailed edges and identifying high-level semantics. Our motivation comes from the hypothesis that such distinct targets prevent state-of-the-art SED methods from effectively using deep supervision to improve results. To this end, we propose a novel fully convolutional neural network using diverse deep supervision (DDS) within a multi-task framework where bottom layers aim at generating category-agnostic edges, while top layers are responsible for the detection of category-aware semantic edges. To overcome the hypothesized supervision challenge, a novel information converter unit is introduced, whose effectiveness has been extensively evaluated on SBD and Cityscapes datasets.