Feature Reintegration over Differential Treatment: A Top-down and Adaptive Fusion Network for RGB-D Salient Object Detection

Zhang, Miao; Piao, Yongri; Hu, Beiqi; Lu, Huchuan

doi:10.1145/3394171.3413969

“…We compare our CDINet with 15 state-of-the-art CNN-based RGB-D SOD methods, including MMCI [3], TAN [2], CPFP [44], DMRA [32], FRDT [41], SSF [40], S2MA [28], A2dele [33], JL-DCF [18], DANet [45], PGAR [4], cmMS [26], BiANet [43], D3Net [15], and ASIFNet [25].…”

Section: Comparisons With Sota Methodsmentioning

confidence: 99%

Cross-modality Discrepant Interaction Network for RGB-D Salient Object Detection

Zhang

¹

,

Cong

²

,

Lin

³

et al. 2021

Proceedings of the 29th ACM International Conference on Multimedia

View full text Add to dashboard Cite

The popularity and promotion of depth maps have brought new vigor and vitality into salient object detection (SOD), and a mass of RGB-D SOD algorithms have been proposed, mainly concentrating on how to better integrate cross-modality features from RGB image and depth map. For the cross-modality interaction in feature encoder, existing methods either indiscriminately treat RGB and depth modalities, or only habitually utilize depth cues as auxiliary information of the RGB branch. Different from them, we reconsider the status of two modalities and propose a novel Cross-modality Discrepant Interaction Network (CDINet) for RGB-D SOD, which differentially models the dependence of two modalities according to the feature representations of different layers. To this end, two components are designed to implement the effective cross-modality interaction: 1) the RGB-induced Detail Enhancement (RDE) module leverages RGB modality to enhance the details of the depth features in low-level encoder stage. 2) the Depth-induced Semantic Enhancement (DSE) module transfers the object positioning and internal consistency of depth features to the RGB branch in high-level encoder stage. Furthermore, we also design a Dense Decoding Reconstruction (DDR) structure, which constructs a semantic block by combining multi-level encoder features to upgrade the skip connection in the feature decoding. Extensive experiments on five benchmark datasets demonstrate that our network outperforms 15 stateof-the-art methods both quantitatively and qualitatively. Our code is publicly available at: https:// rmcong.github.io/ proj_CDINet.html. CCS CONCEPTS• Computing methodologies → Interest point and salient region detections;.

show abstract

“…We compare our CDINet with 15 state-of-the-art CNN-based RGB-D SOD methods, including MMCI [3], TAN [2], CPFP [44], DMRA [32], FRDT [41], SSF [40], S2MA [28], A2dele [33], JL-DCF [18], DANet [45], PGAR [4], cmMS [26], BiANet [43], D3Net [15], and ASIFNet [25]. For fair comparisons, we test these methods with the released codes under the default settings to obtain the saliency maps.…”

Section: Comparisons With Sota Methodsmentioning

confidence: 99%

“…We compare our CDINet with 15 state-of-the-art CNN-based RGB-D SOD methods, including MMCI [3], TAN [2], CPFP [44], DMRA [32], FRDT [41], SSF [40], S2MA [28], A2dele [33], JL-DCF [18], DANet [45], PGAR [4], cmMS [26], BiANet [43], D3Net [15] and ASIFNet [25] on five benchmark datasets (i.e., NLPR [31], NJUD [22], DUT [32], STEREO [29], and LFSD [27]). In this supplementary materials, we provide the more visual comparisons and P-R curves in Figure 5 and Figure 6, respectively.…”

Section: B Experimentsmentioning

confidence: 99%

Cross-modality Discrepant Interaction Network for RGB-D Salient Object Detection

Zhang

¹

,

Cong

²

,

Lin

³

et al. 2021

Preprint

0

View full text Add to dashboard Cite

The popularity and promotion of depth maps have brought new vigor and vitality into salient object detection (SOD), and a mass of RGB-D SOD algorithms have been proposed, mainly concentrating on how to better integrate cross-modality features from RGB image and depth map. For the cross-modality interaction in feature encoder, existing methods either indiscriminately treat RGB and depth modalities, or only habitually utilize depth cues as auxiliary information of the RGB branch. Different from them, we reconsider the status of two modalities and propose a novel Cross-modality Discrepant Interaction Network (CDINet) for RGB-D SOD, which differentially models the dependence of two modalities according to the feature representations of different layers. To this end, two components are designed to implement the effective cross-modality interaction: 1) the RGB-induced Detail Enhancement (RDE) module leverages RGB modality to enhance the details of the depth features in low-level encoder stage. 2) the Depth-induced Semantic Enhancement (DSE) module transfers the object positioning and internal consistency of depth features to the RGB branch in high-level encoder stage. Furthermore, we also design a Dense Decoding Reconstruction (DDR) structure, which constructs a semantic block by combining multi-level encoder features to upgrade the skip connection in the feature decoding. Extensive experiments on five benchmark datasets demonstrate that our network outperforms 15 stateof-the-art methods both quantitatively and qualitatively. Our code is publicly available at: https:// rmcong.github.io/ proj_CDINet.html. CCS CONCEPTS• Computing methodologies → Interest point and salient region detections.

show abstract

“…Multi-scale modeling. Modeling multi-scale features is an important procedure in deep learning-based computer vision [23,3,25,60,22,64,36,15,50] because it is able to enlarge the receptive field and increase resolution. In 3D representation, modeling multi-scale features is also popular and important.…”

Section: Related Workmentioning

confidence: 99%

M3DeTR: Multi-representation, Multi-scale, Mutual-relation 3D Object Detection with Transformers

Guan¹,

Wang²,

Lan³

et al. 2021

Preprint

View full text Add to dashboard Cite

We present a novel architecture for 3D object detection, M3DETR, which combines different point cloud representations (raw, voxels, bird-eye view) with different feature scales based on multi-scale feature pyramids. M3DETR is the first approach that unifies multiple point cloud representations, feature scales, as well as models mutual relationships between point clouds simultaneously using transformers. We perform extensive ablation experiments that highlight the benefits of fusing representation and scale, and modeling the relationships. Our method achieves state-of-the-art performance on the KITTI 3D object detection dataset and Waymo Open Dataset. Results show that M3DETR improves the baseline significantly by 1.48% mAP for all classes on Waymo Open Dataset. In particular, our approach ranks 1 st on the well-known KITTI 3D Detection Benchmark for both car and cyclist classes, and ranks 1 st on Waymo Open Dataset with single frame point cloud input.

show abstract

Feature Reintegration over Differential Treatment: A Top-down and Adaptive Fusion Network for RGB-D Salient Object Detection

Cited by 43 publications

References 39 publications

Cross-modality Discrepant Interaction Network for RGB-D Salient Object Detection

Cross-modality Discrepant Interaction Network for RGB-D Salient Object Detection

Cross-modality Discrepant Interaction Network for RGB-D Salient Object Detection

M3DeTR: Multi-representation, Multi-scale, Mutual-relation 3D Object Detection with Transformers

Contact Info

Product

Resources

About