Rethinking of the Image Salient Object Detection: Object-level Semantic Saliency Re-ranking First, Pixel-wise Saliency Refinement Latter

08/10/2020
by   Zhenyu Wu, et al.
2

The real human attention is an interactive activity between our visual system and our brain, using both low-level visual stimulus and high-level semantic information. Previous image salient object detection (SOD) works conduct their saliency predictions in a multi-task manner, i.e., performing pixel-wise saliency regression and segmentation-like saliency refinement at the same time, which degenerates their feature backbones in revealing semantic information. However, given an image, we tend to pay more attention to those regions which are semantically salient even in the case that these regions are perceptually not the most salient ones at first glance. In this paper, we divide the SOD problem into two sequential tasks: 1) we propose a lightweight, weakly supervised deep network to coarsely locate those semantically salient regions first; 2) then, as a post-processing procedure, we selectively fuse multiple off-the-shelf deep models on these semantically salient regions as the pixel-wise saliency refinement. In sharp contrast to the state-of-the-art (SOTA) methods that focus on learning pixel-wise saliency in "single image" using perceptual clues mainly, our method has investigated the "object-level semantic ranks between multiple images", of which the methodology is more consistent with the real human attention mechanism. Our method is simple yet effective, which is the first attempt to consider the salient object detection mainly as an object-level semantic re-ranking problem.

READ FULL TEXT

page 1

page 3

page 4

page 6

research
01/29/2015

Weakly Supervised Learning for Salient Object Detection

Recent advances in supervised salient object detection has resulted in s...
research
06/29/2017

Co-salient Object Detection Based on Deep Saliency Networks and Seed Propagation over an Integrated Graph

This paper presents a co-salient object detection method to find common ...
research
01/28/2017

Exploiting saliency for object segmentation from image level labels

There have been remarkable improvements in the semantic labelling task i...
research
12/15/2018

PiCANet: Pixel-wise Contextual Attention Learning for Accurate Saliency Detection

In saliency detection, every pixel needs contextual information to make ...
research
07/25/2018

Semantics Meet Saliency: Exploring Domain Affinity and Models for Dual-Task Prediction

Much research has examined models for prediction of semantic labels or i...
research
12/27/2016

Semantic Perceptual Image Compression using Deep Convolution Networks

It has long been considered a significant problem to improve the visual ...
research
06/09/2021

Salient Object Ranking with Position-Preserved Attention

Instance segmentation can detect where the objects are in an image, but ...

Please sign up or login with your details

Forgot password? Click here to reset