FRNet: Factorized and Regular Blocks Network for Semantic Segmentation in Road Scene

Lu, Mengxu; Chen, Zhenxue; Wu, Q. M. Jonathan; Wang, Nannan; Rong, Xuewen; Yan, Xinghe

doi:10.1109/tits.2020.3037727

Cited by 20 publications

(2 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…FANet [18] presented a fast attention module and manually added a downsampling layer in ResNet to reduce the computational cost. FR-Net [25] used an asymmetric encoder-decoder architecture with factorized and regular blocks, making a trade-off between accuracy and speed. DSANet [26] employed a channel split and shuffle to reduce the computation and maintain higher segmentation accuracy.…”

Section: Related Workmentioning

confidence: 99%

Interactive Efficient Multi-Task Network for RGB-D Semantic Segmentation

Xu,

Liu,

Liu

2023

Electronics

View full text Add to dashboard Cite

Semantic segmentation is significant for robotic indoor activities. However, relying solely on RGB modality often leads to poor results due to limited information. Introducing other modalities can improve performance but also increases complexity and cost, making it unsuitable for real-time robotic applications. To address the balance issue of performance and speed in robotic indoor scenarios, we propose an interactive efficient multitask RGB-D semantic segmentation network (IEMNet) that utilizes both RGB and depth modalities. On the premise of ensuring rapid inference speed, we introduce a cross-modal feature rectification module, which calibrates the noise of RGB and depth modalities and achieves comprehensive cross-modal feature interaction. Furthermore, we propose a coordinate attention fusion module to achieve more effective feature fusion. Finally, an instance segmentation task is added to the decoder to assist in enhancing the performance of semantic segmentation. Experiments on two indoor scene datasets, NYUv2 and SUNRGB-D, demonstrate the superior performance of the proposed method, especially on the NYUv2, achieving 54.5% mIoU and striking an excellent balance between performance and inference speed at 42 frames per second.

show abstract

Section: Related Workmentioning

confidence: 99%

Interactive Efficient Multi-Task Network for RGB-D Semantic Segmentation

Xu,

Liu,

Liu

2023

Electronics

View full text Add to dashboard Cite

show abstract

“…For feature connection, directly connecting the low- and high-level features with the same feature resolution ignores the effectiveness of the cooperation of spatial and semantic feature maps 14 . In 2022, an interim was added between the encoder and decoder in several models, such as contextual ensemble network (CENet), 15 factorized and regular blocks network (FRNet), 16 and spectrum-aware feature augmentation network (SFANet) 17 . This additional and complicated operation focuses excessively on the collaboration of feature maps, leaving the semantic information neglected.…”

Section: Introductionmentioning

confidence: 99%

Multi-scale dense and attention mechanism for image semantic segmentation based on improved DeepLabv3+

et al. 2022

View full text Add to dashboard Cite

. Semantic scene segmentation has become an important application in computer vision and is an essential part of intelligent transportation systems for complete scene understanding of the surrounding environment. Several methods based on convolutional neural networks have emerged, but they have some problems, including small-scale target loss, inaccurate detailed region segmentation, and boundary category confusion. Using shallow features, we exploit the capabilities of global context information according to the theory of pyramids. A weighted pyramid feature fusion module is constructed to fuse the feature maps of different scales generated by the backbone network, and the proportion of feature fusion is dynamically updated by trainable parameters. After that, a self-attention mechanism is introduced to discover information about spatial channel interdependencies. Finally, the atrous spatial pyramid pooling module of the DeepLabv3+ network is improved by connecting the atrous convolution with different dilation rates at the receptive field. The experimental results show 4.1% mean pixel accuracy and 3.92% mean intersection over union improvements in the proposed method compared with the DeepLabv3+, and the result of semantic segmentation is more accurate.

show abstract