Supervised Edge Attention Network for Accurate Image Instance Segmentation

Chen, Xier; Lian, Yanchao; Jiao, Licheng; Wang, Haoran; Gao, Yanjie; Shi, Lingling

doi:10.1007/978-3-030-58583-9_37

Cited by 29 publications

(15 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…2) Synergistic learning for feature-level domain adaptation. The shared encoder along with the position attention module (PAM) [15] and edge attention module (EAM) [16] is utilized to extract domain-invariant features. Then, we apply the edge decoder and mask decoder to obtain the edge prediction map and segmentation prediction map.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Unsupervised Domain Adaptation Based Image Synthesis and Synergistic Adversarial Learning for Optic Disc and Cup Segmentation

Liu

Lei

Xie

et al. 2021

2021 IEEE International Conference on Multimedia and Expo (ICME)

View full text Add to dashboard Cite

Due to the discrepancy of different devices for fundus image collection, a well-trained neural network usually fails to be applied to another new dataset. To solve this problem, the unsupervised domain adaptation strategy attracts a lot of attention. In this paper, we adopt image synthesis and adversarial learning mechanism to complete input-level adaptation and output-level adaptation, respectively. In particular, the edge structure information of optic disc and cup is embedded into the devised encoder-decoder structure in feature-level adaptation to obtain domain-invariant features. To enhance the ability of feature representation, we introduce the position attention module and the edge attention module to extract discriminative features. We train our proposed method on the training set of the REFUGE challenge dataset and test it on Drishti-GS and RIM-ONE-r3 datasets. The experimental results demonstrate that our method is promising with respect to the segmentation of optic disc and cup.

show abstract

Section: Methodsmentioning

confidence: 99%

“…As shown in Fig. 2, we introduce a conventional EAM inspired by [16]. We reshape the extracted feature map to low dimension and use a matrix multiplication operation between them to get an attention map.…”

Section: Synergistic Learning In Feature-level Adaptationmentioning

confidence: 99%

Unsupervised Domain Adaptation Based Image Synthesis and Synergistic Adversarial Learning for Optic Disc and Cup Segmentation

Liu

Lei

Xie

et al. 2021

2021 IEEE International Conference on Multimedia and Expo (ICME)

View full text Add to dashboard Cite

show abstract

“…This phenomenon greatly weakens the representation ability of features and brings difficulties to the construction of hierarchical understanding. SEAnet [3] utilizes edge attention to highlight the object and suppress background noise, and SPNet [15] proposes strip pooling to aggregate global and local contexts for scene parsing.…”

Section: Information Enhancementmentioning

confidence: 99%

MWQ: Multiscale Wavelet Quantized Neural Networks

Sun¹,

Ren²,

Jiao³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Model quantization can reduce the model size and computational latency, it has become an essential technique for the deployment of deep neural networks on resourceconstrained hardware (e.g., mobile phones and embedded devices). The existing quantization methods mainly consider the numerical elements of the weights and activation values, ignoring the relationship between elements. The decline of representation ability and information loss usually lead to the performance degradation. Inspired by the characteristics of images in the frequency domain, we propose a novel multiscale wavelet quantization (MWQ) method. This method decomposes original data into multiscale frequency components by wavelet transform, and then quantizes the components of different scales, respectively. It exploits the multiscale frequency and spatial information to alleviate the information loss caused by quantization in the spatial domain. Because of the flexibility of MWQ, we demonstrate three applications (e.g., model compression, quantized network optimization, and information enhancement) on the ImageNet and COCO datasets. Experimental results show that our method has stronger representation ability and can play an effective role in quantized neural networks.

show abstract

“…Recently, PointRend [30] is proposed to refine the coarse masks by rending them through one shared multi-layer perception module. Some works [10,11,33] fuse to learned edge map into segmentation head to improve segmentation performance on the boundary, while GSCNN [55] uses a gated layer to control the information flow between edge part and regular part. All these works focus on locally mining the edge information and ignore the global shape information, which is essential for recognizing the glass-like objects.…”

Section: Related Workmentioning

confidence: 99%

Enhanced Boundary Learning for Glass-like Object Segmentation

He¹,

Li²,

Cheng³

et al. 2021

Preprint

View full text Add to dashboard Cite

Glass-like objects such as windows, bottles, and mirrors exist widely in the real world. Sensing these objects has many applications, including robot navigation and grasping. However, this task is very challenging due to the arbitrary scenes behind glass-like objects. This paper aims to solve the glass-like object segmentation problem via enhanced boundary learning. In particular, we first propose a novel refined differential module for generating finer boundary cues. Then an edge-aware pointbased graph convolution network module is proposed to model the global shape representation along the boundary. Both modules are lightweight and effective, which can be embedded into various segmentation models. Moreover, we use these two modules to design a decoder to get accurate segmentation results, especially on the boundary. Extensive experiments on three recent glass-like object segmentation datasets, including Trans10k, MSD, and GDD, show that our approach establishes new state-of-theart performances. We also offer the generality and superiority of our approach compared with recent methods on three general segmentation datasets, including Cityscapes, BDD, and COCO Stuff. Code and models will be available at (https://github.com/hehao13/EBLNet).

show abstract

Supervised Edge Attention Network for Accurate Image Instance Segmentation

Cited by 29 publications

References 24 publications

Unsupervised Domain Adaptation Based Image Synthesis and Synergistic Adversarial Learning for Optic Disc and Cup Segmentation

Unsupervised Domain Adaptation Based Image Synthesis and Synergistic Adversarial Learning for Optic Disc and Cup Segmentation

MWQ: Multiscale Wavelet Quantized Neural Networks

Enhanced Boundary Learning for Glass-like Object Segmentation

Contact Info

Product

Resources

About