End-to-End Instance Edge Detection

04/06/2022
by   Xueyan Zou, et al.
8

Edge detection has long been an important problem in the field of computer vision. Previous works have explored category-agnostic or category-aware edge detection. In this paper, we explore edge detection in the context of object instances. Although object boundaries could be easily derived from segmentation masks, in practice, instance segmentation models are trained to maximize IoU to the ground-truth mask, which means that segmentation boundaries are not enforced to precisely align with ground-truth edge boundaries. Thus, the task of instance edge detection itself is different and critical. Since precise edge detection requires high resolution feature maps, we design a novel transformer architecture that efficiently combines a FPN and a transformer decoder to enable cross attention on multi-scale high resolution feature maps within a reasonable computation budget. Further, we propose a light weight dense prediction head that is applicable to both instance edge and mask detection. Finally, we use a penalty reduced focal loss to effectively train the model with point supervision on instance edges, which can reduce annotation costs. We demonstrate highly competitive instance edge detection performance compared to state-of-the-art baselines, and also show that the proposed task and loss are complementary to instance segmentation and object detection.

READ FULL TEXT

page 10

page 14

page 17

page 18

research
05/03/2021

ISTR: End-to-End Instance Segmentation with Transformers

End-to-end paradigms significantly improve the accuracy of various deep-...
research
09/19/2018

Faster Training of Mask R-CNN by Focusing on Instance Boundaries

We present an auxiliary task to Mask R-CNN, an instance segmentation net...
research
06/03/2019

Panoptic Edge Detection

Pursuing more complete and coherent scene understanding towards realisti...
research
07/07/2020

Instance Segmentation for Whole Slide Imaging: End-to-End or Detect-Then-Segment

Automatic instance segmentation of glomeruli within kidney Whole Slide I...
research
04/05/2018

A Pyramid CNN for Dense-Leaves Segmentation

Automatic detection and segmentation of overlapping leaves in dense foli...
research
03/15/2023

PENet: A Joint Panoptic Edge Detection Network

In recent years, compact and efficient scene understanding representatio...
research
08/20/2021

BlockCopy: High-Resolution Video Processing with Block-Sparse Feature Propagation and Online Policies

In this paper we propose BlockCopy, a scheme that accelerates pretrained...

Please sign up or login with your details

Forgot password? Click here to reset