Semantic Edge Detection with Diverse Deep Supervision

Yun Liu

Last update: Dec 31, 2022

Related tags

Deep Learning DDS

Overview

Semantic Edge Detection with Diverse Deep Supervision

This repository contains the code for our IJCV paper: "Semantic Edge Detection with Diverse Deep Supervision". The code is based on the Caffe framework which is outdated now (the reviewing process lasts very very long). Hence, we only release the code for the future reference. If you want to do something about the task of semantic edge detection, the code for the DFF paper ("Dynamic Feature Fusion for Semantic Edge Detection", IJCAI 2019) is a good choice to start with, which is based on the popular PyTorch framework. If you really want to run our Caffe code, please prepare data like the SEAL repository ("Simultaneous Edge Alignment and Learning", ECCV 2018), although I guess that no one would like to do so...

Citations

@article{liu2021semantic,
  title={Semantic edge detection with diverse deep supervision},
  author={Liu, Yun and Cheng, Ming-Ming and Fan, Deng-Ping and Zhang, Le and Bian, JiaWang and Tao, Dacheng},
  journal={International Journal of Computer Vision},
  year={2021}
}

Implementation for the paper 'YOLO-ReT: Towards High Accuracy Real-time Object Detection on Edge GPUs'

YOLO-ReT This is the original implementation of the paper: YOLO-ReT: Towards High Accuracy Real-time Object Detection on Edge GPUs. Prakhar Ganesh, Ya

69 Oct 19, 2022

CenterFace(size of 7.3MB) is a practical anchor-free face detection and alignment method for edge devices.

CenterFace Introduce CenterFace(size of 7.3MB) is a practical anchor-free face detection and alignment method for edge devices. Recent Update 2019.09.

1.2k Dec 21, 2022

A light and fast one class detection framework for edge devices. We provide face detector, head detector, pedestrian detector, vehicle detector......

A Light and Fast Face Detector for Edge Devices Big News: LFD, which is a big update of LFFD, now is released (2021.03.09). It is strongly recommended

1.3k Dec 25, 2022

Structured Edge Detection Toolbox

################################################################### # # # Structure

779 Jan 2, 2023

Image Processing, Image Smoothing, Edge Detection and Transforms

opevcvdl-hw1 This project uses openCV and Qt to achieve the requirements. Version Python 3.7 opencv-contrib-python 3.4.2.17 Matplotlib 3.1.1 pyqt5 5.1

3 Aug 17, 2022

BED: A Real-Time Object Detection System for Edge Devices

BED: A Real-Time Object Detection System for Edge Devices About this project Thi

Data Analytics Lab at Texas A&M University

44 Nov 18, 2022

Official implementation of "Not only Look, but also Listen: Learning Multimodal Violence Detection under Weak Supervision" ECCV2020

XDVioDet Official implementation of "Not only Look, but also Listen: Learning Multimodal Violence Detection under Weak Supervision" ECCV2020. The proj

64 Dec 12, 2022

Lyapunov-guided Deep Reinforcement Learning for Stable Online Computation Offloading in Mobile-Edge Computing Networks

PyTorch code to reproduce LyDROO algorithm [1], which is an online computation offloading algorithm to maximize the network data processing capability subject to the long-term data queue stability and average power constraints. It applies Lyapunov optimization to decouple the multi-stage stochastic MINLP into deterministic per-frame MINLP subproblems and solves each subproblem via DROO algorithm. It includes:

87 Dec 28, 2022

Official PyTorch code for CVPR 2020 paper "Deep Active Learning for Biased Datasets via Fisher Kernel Self-Supervision"

Deep Active Learning for Biased Datasets via Fisher Kernel Self-Supervision https://arxiv.org/abs/2003.00393 Abstract Active learning (AL) aims to min

29 Nov 21, 2022

Comments

Questions about evaluations

After reading your paper, I noticed that you have used Gated-SCNN for your comparison. As far as I know, GSCNN outputs semantic segmentation and category agnostic edge maps. In the paper, you described the process of evaluation as "Gated-SCNN learns semantic edges for improving the training of semantic segmentation. Hence, we retain it for semantic edge detection by removing its segmentation loss and dual task loss, and the other settings are kept by default." I'm curious on how to extract semantic edges in Gated-SCNN since looking at their code and paper, it seems like the edges are binary maps (maybe you could mask the segmentation maps with the edge maps, but it doesn't seem like what you guys did). Could you explain the process?

opened by haruishi43 2

Semantic Edge Detection with Diverse Deep Supervision

Related tags

Overview

Semantic Edge Detection with Diverse Deep Supervision

Citations

You might also like...

Implementation for the paper 'YOLO-ReT: Towards High Accuracy Real-time Object Detection on Edge GPUs'

CenterFace(size of 7.3MB) is a practical anchor-free face detection and alignment method for edge devices.

A light and fast one class detection framework for edge devices. We provide face detector, head detector, pedestrian detector, vehicle detector......

Structured Edge Detection Toolbox

Image Processing, Image Smoothing, Edge Detection and Transforms

BED: A Real-Time Object Detection System for Edge Devices

Official implementation of "Not only Look, but also Listen: Learning Multimodal Violence Detection under Weak Supervision" ECCV2020

Lyapunov-guided Deep Reinforcement Learning for Stable Online Computation Offloading in Mobile-Edge Computing Networks

Official PyTorch code for CVPR 2020 paper "Deep Active Learning for Biased Datasets via Fisher Kernel Self-Supervision"

Comments

Questions about evaluations

Owner

Yun Liu

Mixup for Supervision, Semi- and Self-Supervision Learning Toolbox and Benchmark

Learning Pixel-level Semantic Affinity with Image-level Supervision for Weakly Supervised Semantic Segmentation, CVPR 2018

Implementation of Diverse Semantic Image Synthesis via Probability Distribution Modeling

[CVPR 2021] Semi-Supervised Semantic Segmentation with Cross Pseudo Supervision

DiscoBox: Weakly Supervised Instance Segmentation and Semantic Correspondence from Box Supervision

The PyTorch implementation of DiscoBox: Weakly Supervised Instance Segmentation and Semantic Correspondence from Box Supervision.

CCPD: a diverse and well-annotated dataset for license plate detection and recognition

Code for the ICCV 2021 paper "Pixel Difference Networks for Efficient Edge Detection" (Oral).

pcnaDeep integrates cutting-edge detection techniques with tracking and cell cycle resolving models.

a reimplementation of Holistically-Nested Edge Detection in PyTorch