JL-DCF: Joint Learning and Densely-Cooperative Fusion Framework for RGB-D Salient Object Detection

By Keren Fu, Deng-Ping Fan, Ge-Peng Ji, Qijun Zhao. Computer Vision and Pattern Recognition, 2020

309 citations recorded by the source corpus.

This paper proposes a novel joint learning and densely-cooperative fusion (JL-DCF) architecture for RGB-D salient object detection. Existing models usually treat RGB and depth as independent information and design separate networks for feature extraction from each. Such schemes can easily be constrained by a limited amount of training data or over-reliance on an elaborately-designed training process. In contrast, our JL-DCF learns from both RGB and depth inputs through a Siamese network. To this end, we propose two effective components: joint learning (JL), and densely-cooperative fusion (DCF). The JL module provides robust saliency feature learning, while the latter is introduced for complementary feature discovery. Comprehensive experiments on four popular metrics show that the designed framework yields a robust RGB-D saliency detector with good generalization. As a result, JL-DCF significantly advances the top-1 D3Net model by an average of ~1.9% (S-measure) across six challenging datasets, showing that the proposed framework offers a potential solution for real-world applications and could provide more insight into the cross-modality complementarity task. The code will be available at https://github.com/kerenfu/JLDCF/.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/1f1abcd6fba3283d9799527b325b0d302cb7bace

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

RGB-D salient object detection: A survey (2020, methodology): “C D C P [8 4]”
Uncertainty-aware Joint Salient Object and Camouflaged Object Detection (2021, background): “Joint training is mostly designed for positively related tasks [43, 14, 51].”
Attentional Feature Fusion (2020, background): “The attention mechanism in deep learning, which mimics the human visual attention mechanism [5, 8], is originally developed on a global scale.”
UC-Net: Uncertainty Inspired RGB-D Saliency Detection via Conditional Variational Autoencoders (2020, background): “Building upon large scale RGB-D datasets, deep convolutional neural network based models [21, 61, 6, 24] have made profound progress in learning the mapping from an RGB-D image pair to the corresponding GT saliency map.”
SwinNet: Swin Transformer Drives Edge-Aware RGB-D and RGB-T Salient Object Detection (2022, unknown): “DRLF [90], SSF [43], SSMA [38], A2dele [46], UC-Net [91], JL-DCF [92], CoNet [44], DANet [81], EBFSP [93],CDNet”
Camouflaged Object Detection (2020, methodology): “In future work, we plan to extend COD10K dataset to provide input of various forms, for example, RGB-D camouﬂage object detection (similar to RGB-D salient object detection [19,71,74]), among others.”
BBS-Net: RGB-D Salient Object Detection with a Bifurcated Backbone Strategy Network (2020, background): “Two recent famous works have also explored uncertainty [68], bilateral attention [73], graph neural network [48] and a joint learning strategy [25] and achieve good performance.”
PraNet: Parallel Reverse Attention Network for Polyp Segmentation (2020, background): “further introduce four other metrics which are widely used in the field of object detection [7,31,8,11,37,38].”
Rethinking RGB-D Salient Object Detection: Models, Data Sets, and Large-Scale Benchmarks (2019, background): “JL-DCF [118], GFNet [119], DMRA [120], ERNet [121], BiANet [122], etc, have been released.”