CCAFNet: Crossflow and Cross-Scale Adaptive Fusion Network for Detecting Salient Objects in RGB-D Images

Zhou, Wujie; Zhu, Yun; Lei, Jingsheng; Wan, Jian; Yu, Lu

doi:10.1109/tmm.2021.3077767

Cited by 113 publications

(26 citation statements)

References 60 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are many RGB-D SOD methods which surpass previous methods in the last year. Therefore, we compare our model with these pioneering works published in 2021, including JL-DCF [122], CDNet [123], DPANet [69], HAINet [124], DSNet [46], CCAFNet [125], EBFSP [126], MMNet [77], RD3D [61], TriTransNet [97], DCF [56], DSA2F [63], VST [101], SPNet [127], EBMG [104], and SwinNet [27].…”

Section: Comparisons With Sotas 1) Rgb-d Sodmentioning

confidence: 99%

HRTransNet: HRFormer-Driven Two-Modality Salient Object Detection

Tang

Liu

Tan

et al. 2023

IEEE Trans. Circuits Syst. Video Technol.

View full text Add to dashboard Cite

High-Resolution Transformer (HRFormer) can maintain high-resolution representation and share global receptive fields. It is friendly towards salient object detection (SOD) in which the input and output have the same resolution. However, two critical problems need to be solved for two-modality SOD. One problem is two-modality fusion. The other problem is the HRFormer output's fusion. To address the first problem, a supplementary modality is injected into the primary modality by using global optimization and an attention mechanism to select and purify the modality at the input level. To solve the second problem, a dual-direction short connection fusion module is used to optimize the output features of HRFormer, thereby enhancing the detailed representation of objects at the output level. The proposed model, named HRTransNet, first introduces an auxiliary stream for feature extraction of supplementary modality. Then, features are injected into the primary modality at the beginning of each multi-resolution branch. Next, HRFormer is applied to achieve forwarding propagation. Finally, all the output features with different resolutions are aggregated by intrafeature and inter-feature interactive transformers. Application of the proposed model results in impressive improvement for driving two-modality SOD tasks, e.g., RGB-D, RGB-T, and light field SOD.https://github.com/liuzywen/HRTransNet

show abstract

Section: Comparisons With Sotas 1) Rgb-d Sodmentioning

confidence: 99%

HRTransNet: HRFormer-Driven Two-Modality Salient Object Detection

Tang

Liu

Tan

et al. 2023

IEEE Trans. Circuits Syst. Video Technol.

View full text Add to dashboard Cite

show abstract

“…C. Comparison with the State-of-the-Arts 1) Comparison Methods: We compare our model with 13 state-of-the-art RGB-D based SOD methods, including MMCI [14],TANet [15], DMRA [18], ICNet [48], A2dele [66], S2MA [67], DRLF [38], CCAFNet [68], JL-DCF [41], CPFP [19], D3Net [13], DQSD [21] and DFMNet [69]. Specially, the qualities of depth images are also considered in the last three methods, i.e., CPFP [19], D3Net [13], DQSD [21] and DFMNet [69].…”

Section: B Implementation Detailsmentioning

confidence: 99%

Bi-Directional Progressive Guidance Network for RGB-D Salient Object Detection

Yang

Qin

Luo

et al. 2022

IEEE Trans. Circuits Syst. Video Technol.

View full text Add to dashboard Cite

“…The obtained fusion image is more in line with human visual perception, and for other subsequent computer visual tasks, such as object detection and object recognition, which can achieve more accurate decisions than a single sensor. Therefore, infrared and visible image fusion cooperates with these two sensors to generate a higher quality result, and has important applications in many fields, such as person re-recognition [1], object fusion tracking [2] and salient object detection [3] and so on.…”

Section: Introductionmentioning

confidence: 99%