Weakly Supervised Learning with Region and Box-level Annotations for Salient Instance Segmentation

08/19/2020
by   Jialun Pei, et al.
4

Salient instance segmentation is a new challenging task that received widespread attention in saliency detection area. Due to the limited scale of the existing dataset and the high mask annotations cost, it is difficult to train a salient instance neural network completely. In this paper, we appeal to train a salient instance segmentation framework by a weakly supervised source without resorting to laborious labeling. We present a cyclic global context salient instance segmentation network (CGCNet), which is supervised by the combination of the binary salient regions and bounding boxes from the existing saliency detection datasets. For a precise pixel-level location, a global feature refining layer is introduced that dilates the context features of each salient instance to the global context in the image. Meanwhile, a labeling updating scheme is embedded in the proposed framework to online update the weak annotations for next iteration. Experiment results demonstrate that the proposed end-to-end network trained by weakly supervised annotations can be competitive to the existing fully supervised salient instance segmentation methods. Without bells and whistles, our proposed method achieves a mask AP of 57.13 states of the art for weakly supervised salient instance segmentation.

READ FULL TEXT

page 1

page 2

page 3

page 5

page 8

page 9

page 10

page 11

research
04/04/2021

Weakly-supervised Instance Segmentation via Class-agnostic Learning with Salient Images

Humans have a strong class-agnostic object segmentation ability and can ...
research
03/20/2023

Weakly-Supervised Text Instance Segmentation

Text segmentation is a challenging vision task with many downstream appl...
research
09/29/2019

Salient Instance Segmentation via Subitizing and Clustering

The goal of salient region detection is to identify the regions of an im...
research
11/21/2017

S^4Net: Single Stage Salient-Instance Segmentation

In this paper, we consider an interesting vision problem---salient insta...
research
08/28/2020

Regularized Densely-connected Pyramid Network for Salient Instance Segmentation

Much of the recent efforts on salient object detection (SOD) has been de...
research
02/25/2022

Weakly Supervised Instance Segmentation using Motion Information via Optical Flow

Weakly supervised instance segmentation has gained popularity because it...
research
02/03/2022

Weakly Supervised Nuclei Segmentation via Instance Learning

Weakly supervised nuclei segmentation is a critical problem for patholog...

Please sign up or login with your details

Forgot password? Click here to reset