EmbedMask: Embedding Coupling for One-stage Instance Segmentation

12/04/2019
by   Hui Ying, et al.
20

Current instance segmentation methods can be categorized into segmentation-based methods that segment first then do clustering, and proposal-based methods that detect first then predict masks for each instance proposal using repooling. In this work, we propose a one-stage method, named EmbedMask, that unifies both methods by taking advantages of them. Like proposal-based methods, EmbedMask builds on top of detection models making it strong in detection capability. Meanwhile, EmbedMask applies extra embedding modules to generate embeddings for pixels and proposals, where pixel embeddings are guided by proposal embeddings if they belong to the same instance. Through this embedding coupling process, pixels are assigned to the mask of the proposal if their embeddings are similar. The pixel-level clustering enables EmbedMask to generate high-resolution masks without missing details from repooling, and the existence of proposal embedding simplifies and strengthens the clustering procedure to achieve high speed with higher performance than segmentation-based methods. Without any bells and whistles, EmbedMask achieves comparable performance as Mask R-CNN, which is the representative two-stage method, and can produce more detailed masks at a higher speed.

READ FULL TEXT

page 1

page 3

page 7

page 10

research
06/26/2019

Instance Segmentation by Jointly Optimizing Spatial Embeddings and Clustering Bandwidth

Current state-of-the-art instance segmentation methods are not suited fo...
research
04/16/2019

Single Pixel Reconstruction for One-stage Instance Segmentation

Object instance segmentation is one of the most fundamental but challeng...
research
07/13/2020

Improving Pixel Embedding Learning through Intermediate Distance Regression Supervision for Instance Segmentation

As a proposal-free approach, instance segmentation through pixel embeddi...
research
09/28/2020

Learning Category- and Instance-Aware Pixel Embedding for Fast Panoptic Segmentation

Panoptic segmentation (PS) is a complex scene understanding task that re...
research
05/26/2023

OpenVIS: Open-vocabulary Video Instance Segmentation

We propose and study a new computer vision task named open-vocabulary vi...
research
08/19/2020

Towards Lightweight Lane Detection by Optimizing Spatial Embedding

A number of lane detection methods depend on a proposal-free instance se...
research
08/01/2020

PanoNet: Real-time Panoptic Segmentation through Position-Sensitive Feature Embedding

We propose a simple, fast, and flexible framework to generate simultaneo...

Please sign up or login with your details

Forgot password? Click here to reset