Cross-Layer Feature Pyramid Network for Salient Object Detection

Li, Zun; Lang, Congyan; Liew, Jun Hao; Li, Yidong; Hou, Qibin; Feng, Jiashi

doi:10.1109/tip.2021.3072811

Cited by 54 publications

(19 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…At present, there are still some problems in remote sensing image CD that need to be dealt with: (1) High-resolution remote sensing images are rich in spectral and spatial information, but these information have not been fully utilized; (2) most SOTA CD methods are implemented by FPN-like feature fusion structure, in the process of feature fusion, the spatial structure details used to reconstruct the object boundary can only be obtained in the final fusion stage, which makes the change map predicted by these methods have low-quality object boundary or miss detection of small change regions 41 .…”

Section: Methodsmentioning

confidence: 99%

“…To enable effective information transfer between the feature maps of different layers of the network, we propose to replace the fusion mechanism in FPNs by aggregating the feature maps of different layers. Specifically, inspired by Li et al 41 , we design the MSFA that adaptively predicts a set of weights based on the importance of different layer features. The purpose of this design is to effectively enhance the feature representation of the feature map.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Multi-scale feature progressive fusion network for remote sensing image change detection

Cheng

Wang

et al. 2022

Sci Rep

View full text Add to dashboard Cite

Presently, research on deep learning-based change detection (CD) methods has become a hot topic. In particular, feature pyramid networks (FPNs) are widely used in CD tasks to gradually fuse semantic features. However, existing FPN-based CD methods do not correctly detect the complete change region and cannot accurately locate the boundaries of the change region. To solve these problems, a new Multi-Scale Feature Progressive Fusion Network (MFPF-Net) is proposed, which consists of three innovative modules: Layer Feature Fusion Module (LFFM), Multi-Scale Feature Aggregation Module (MSFA), and Multi-Scale Feature Distribution Module (MSFD). Specifically, we first concatenate the features of each layer extracted from the bi-temporal images with their difference maps, and the resulting change maps fuse richer semantic information while effectively representing change regions. Then, the obtained change maps of each layer are directly aggregated, which improves the effective communication and full fusion of feature maps in CD while avoiding the interference of indirect information. Finally, the aggregated feature maps are layered again by pooling and convolution operations, and then a feature fusion strategy with a pyramid structure is used, with layers fused from low to high, to obtain richer contextual information, so that each layer of the layered feature maps has original semantic information and semantic features of other layers. We conducted comprehensive experiments on three publicly available benchmark datasets, CDD, LEVIR-CD, and WHU-CD to verify the effectiveness of the method, and the experimental results show that the method in this paper outperforms other comparative methods.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Multi-scale feature progressive fusion network for remote sensing image change detection

Cheng

Wang

et al. 2022

Sci Rep

View full text Add to dashboard Cite

show abstract

“…Pang et al 23 designed an aggregate interaction module to progressively aggregate adjacent level features. Li et al 48 constructed a cross-layer feature pyramid network to aggregate multiscale features from different levels. Different from these methods, a dense pyramid attention module is proposed to effectively extract multiscale features.…”

Section: Background and Related Workmentioning

confidence: 99%

“…designed an aggregate interaction module to progressively aggregate adjacent level features. Li et al 48 . constructed a cross-layer feature pyramid network to aggregate multiscale features from different levels.…”

Section: Introductionmentioning

confidence: 99%

Attention-based pyramid decoder network for salient object detection in remote sensing images

Liu

Lin

Yue

et al. 2022

J. Appl. Rem. Sens.

View full text Add to dashboard Cite

Salient object detection (SOD) in remote sensing images (RSIs) is a highly practical task. However, scale variations of salient objects and the diversity of salient objects in RSIs pose challenges for detection. To address these issues, an attention-based pyramid decoder network (APDNet) is proposed for SOD in RSIs. The APDNet consists of three key components. First, a multiscale attention block is constructed to extract multiscale information and relations between salient objects, suppressing the distraction of variations of object types and scales. Second, a pyramid decoder structure is designed to take full advantage of multilevel features by gradually fusing features from two adjacent layers for result prediction. This feature fusion allows APDNet to efficiently exploit multilevel feature information, thus enabling a better feature representation. Finally, a bidirectional residual refinement module is proposed to enhance the structural integrity and boundary retention of initial saliency predictions. Extensive experiments on two public datasets demonstrate the superiority and effectiveness of the proposed APDNet against other compared state-of-the-art methods.

show abstract

“…The local and global pixel-wise contextual attention is recurrently captured to predict salient maps in [40]. Innovatively, the CFPN [12] learns a set-of layer-specific weights for the effective feature selection, according to the direct cross-layer communication. In addition, some interesting approaches have also merged.…”

Section: Introductionmentioning

confidence: 99%

CAT-EDNet: Cross-Attention Transformer-Based Encoder–Decoder Network for Salient Defect Detection of Strip Steel Surface

Luo

Yang

et al. 2022

IEEE Trans. Instrum. Meas.

View full text Add to dashboard Cite

The morphologies of various surface defects on strip steel suffer from oil stain, water drops, steel textures and erratic illumination. It is still challenging to recognize defect boundary precisely from cluttered backgrounds. This paper emphasizes such a fact that skip connections between encoder and decoder are not equally effective, attempts to adaptively allocate the aggregation weights which represent differentiated information entropy values in channel-wise, by importing a stack of cross-attention transformer (CAT) into the encoder-decoder network (EDNet). Besides, a cross-attention refinement module (CARM) is constructed closely after the decoder to further optimize the coarse saliency maps. This newly nominated CAT-EDNet can well address the semantic gap issue among the multi-scale features for its multi-head attention structure. The CAT-EDNet performs best on insuring defect integrity and maintaining defect boundary details when compared with twelve state-of-the-arts, and the detection efficiency is at 28 fps even under the noise interfered scenario.

show abstract

Cross-Layer Feature Pyramid Network for Salient Object Detection

Cited by 54 publications

References 48 publications

Multi-scale feature progressive fusion network for remote sensing image change detection

Multi-scale feature progressive fusion network for remote sensing image change detection

Attention-based pyramid decoder network for salient object detection in remote sensing images

CAT-EDNet: Cross-Attention Transformer-Based Encoder–Decoder Network for Salient Defect Detection of Strip Steel Surface

Contact Info

Product

Resources

About