Free Lunch for Co-Saliency Detection: Context Adjustment

08/04/2021
by   Lingdong Kong, et al.
0

We unveil a long-standing problem in the prevailing co-saliency detection systems: there is indeed inconsistency between training and testing. Constructing a high-quality co-saliency detection dataset involves time-consuming and labor-intensive pixel-level labeling, which has forced most recent works to rely instead on semantic segmentation or saliency detection datasets for training. However, the lack of proper co-saliency and the absence of multiple foreground objects in these datasets can lead to spurious variations and inherent biases learned by models. To tackle this, we introduce the idea of counterfactual training through context adjustment, and propose a "cost-free" group-cut-paste (GCP) procedure to leverage images from off-the-shelf saliency detection datasets and synthesize new samples. Following GCP, we collect a novel dataset called Context Adjustment Training. The two variants of our dataset, i.e., CAT and CAT+, consist of 16,750 and 33,500 images, respectively. All images are automatically annotated with high-quality masks. As a side-product, object categories, as well as edge information, are also provided to facilitate other related works. Extensive experiments with state-of-the-art models are conducted to demonstrate the superiority of our dataset. We hope that the scale, diversity, and quality of CAT/CAT+ can benefit researchers in this area and beyond. The dataset and benchmark toolkit will be accessible through our project page.

READ FULL TEXT

page 1

page 4

page 5

page 6

page 8

research
09/10/2015

STC: A Simple to Complex Framework for Weakly-supervised Semantic Segmentation

Recently, significant improvement has been made on semantic object segme...
research
07/30/2019

Grid Saliency for Context Explanations of Semantic Segmentation

Recently, there has been a growing interest in developing saliency metho...
research
04/28/2020

Gradient-Induced Co-Saliency Detection

Co-saliency detection (Co-SOD) aims to segment the common salient foregr...
research
03/11/2021

Triple-cooperative Video Shadow Detection

Shadow detection in a single image has received significant research int...
research
11/22/2021

ATLANTIS: A Benchmark for Semantic Segmentation of Waterbody Images

Vision-based semantic segmentation of waterbodies and nearby related obj...
research
01/30/2022

Comprehensive Saliency Fusion for Object Co-segmentation

Object co-segmentation has drawn significant attention in recent years, ...
research
06/08/2020

Big GANs Are Watching You: Towards Unsupervised Object Segmentation with Off-the-Shelf Generative Models

Since collecting pixel-level groundtruth data is expensive, unsupervised...

Please sign up or login with your details

Forgot password? Click here to reset