CalibNet: Dual-branch Cross-modal Calibration for RGB-D Salient Instance Segmentation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Pei, Jialun, Jiang, Tao, Tang, He, Liu, Nian, Jin, Yueming, Fan, Deng-Ping, Heng, Pheng-Ann
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917690318258176
author Pei, Jialun
Jiang, Tao
Tang, He
Liu, Nian
Jin, Yueming
Fan, Deng-Ping
Heng, Pheng-Ann
author_facet Pei, Jialun
Jiang, Tao
Tang, He
Liu, Nian
Jin, Yueming
Fan, Deng-Ping
Heng, Pheng-Ann
contents We propose a novel approach for RGB-D salient instance segmentation using a dual-branch cross-modal feature calibration architecture called CalibNet. Our method simultaneously calibrates depth and RGB features in the kernel and mask branches to generate instance-aware kernels and mask features. CalibNet consists of three simple modules, a dynamic interactive kernel (DIK) and a weight-sharing fusion (WSF), which work together to generate effective instance-aware kernels and integrate cross-modal features. To improve the quality of depth features, we incorporate a depth similarity assessment (DSA) module prior to DIK and WSF. In addition, we further contribute a new DSIS dataset, which contains 1,940 images with elaborate instance-level annotations. Extensive experiments on three challenging benchmarks show that CalibNet yields a promising result, i.e., 58.0% AP with 320*480 input size on the COME15K-N test set, which significantly surpasses the alternative frameworks. Our code and dataset are available at: https://github.com/PJLallen/CalibNet.
format Preprint
id arxiv_https___arxiv_org_abs_2307_08098
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle CalibNet: Dual-branch Cross-modal Calibration for RGB-D Salient Instance Segmentation
Pei, Jialun
Jiang, Tao
Tang, He
Liu, Nian
Jin, Yueming
Fan, Deng-Ping
Heng, Pheng-Ann
Computer Vision and Pattern Recognition
We propose a novel approach for RGB-D salient instance segmentation using a dual-branch cross-modal feature calibration architecture called CalibNet. Our method simultaneously calibrates depth and RGB features in the kernel and mask branches to generate instance-aware kernels and mask features. CalibNet consists of three simple modules, a dynamic interactive kernel (DIK) and a weight-sharing fusion (WSF), which work together to generate effective instance-aware kernels and integrate cross-modal features. To improve the quality of depth features, we incorporate a depth similarity assessment (DSA) module prior to DIK and WSF. In addition, we further contribute a new DSIS dataset, which contains 1,940 images with elaborate instance-level annotations. Extensive experiments on three challenging benchmarks show that CalibNet yields a promising result, i.e., 58.0% AP with 320*480 input size on the COME15K-N test set, which significantly surpasses the alternative frameworks. Our code and dataset are available at: https://github.com/PJLallen/CalibNet.
title CalibNet: Dual-branch Cross-modal Calibration for RGB-D Salient Instance Segmentation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2307.08098