MRFDCNet: Multireceptive Field Dense Connection Network for Real-Time Semantic Segmentation

Wang, Xiaotian; Cao, Weiqun

doi:10.1155/2022/6100292

Cited by 3 publications

(3 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Notable transformer-based models include SETR [23], SegFormer [24] and RTFormer [25]. Additionally, the latest research has integrated CNNs and transformers, resulting in hybrid models like Vision Mamba [26] and VMamba [27]. Each of these models presents unique strengths and weaknesses [28].…”

Section: Semantic Segmentationmentioning

confidence: 99%

FP-Deeplab: a segmentation model for fabric defect detection

Liu,

Shen,

et al. 2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

In the pursuit of fabric production efficiency and quality, the application of deep learning for defect detection has become prevalent. Nevertheless, fabric defect detection faces challenges such as low recognition ratio, suboptimal classification performance, detection inefficiency, and high model complexity. To address these issues, an end-to-end semantic segmentation network is proposed employing an efficient encoder-decoder structure, denoted as Feature Pyramid-Deeplab (FP-Deeplab). The improvements involves enhancing the backbone network by improving the mobilenetv3 network for superior performance, a novel Atrous Spatial Pyramid Pooling with Dilated Strip Pooling (ASPP-DSP) module which combines strip pooling, dilated convolution and ASPP, to ensure an expanded receptive field and the capability to gather distant contextual information. Additionally, a Feature Pyramid module (FP module) is proposed to integrate multiscale features at various stages more efficiently. The incorporating of depth-wise separable convolution in FP-Deeplab enables significant parameter and computational cost reduction, catering to online detection requirements. Experimental results showcase the superiority of FP-Deeplab over classical and recent segmentation models. Comparative analysis demonstrates higher segmentation accuracy and reduced parameter quantity. Specifically, compared to the benchmark Deeplabv3+ model with MobileV2 as the backbone, FP-Deeplab achieves a notable increase in segmentation accuracy (F1 score and MIoU) by 4.26% and 5.81%, respectively. Moreover, the model parameters (params) are only one-fifth of the original model, indicating the efficiency and effectiveness of our proposed approach.

show abstract

Section: Semantic Segmentationmentioning

confidence: 99%

FP-Deeplab: a segmentation model for fabric defect detection

Liu,

Shen,

et al. 2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

show abstract

“…U-Transformer [29] and EUT [30] modify the cross-attention in the original transformer to leverage the information from the encoder, allowing a fine spatial recovery in the decoder. The cross-resolution attention employed by RTFormer [31] enables the gathering of comprehensive contextual information for high-resolution features.…”

Section: Vision Transformermentioning

confidence: 99%

Coarse Semantic Guided Alpha Matting via Simultaneous Foreground and Background Estimation

Wang¹,

Zhang²

2022

J Comput-Aided Design Comput Graphics

View full text Add to dashboard Cite

The portrait matting task aims to extract an alpha matte with complete semantics and finely-detailed contours. In comparison to CNN-based approaches, transformers with self-attention allow a larger receptive field, enabling it to better capture long-range dependencies and low-frequency semantic information of a portrait. However, the recent research shows that self-attention mechanism struggle with modeling highfrequency information and capturing fine contour details, which can lead to bias while predicting the portrait's contours. To address the problem, we propose EFormer to enhance the model's attention towards semantic and contour features. Especially the latter, which is surrounded by a large amount of high-frequency details. We build a semantic and contour detector (SCD) to accurately capture the distribution of semantic and contour features. And we further design contour-edge extraction branch and semantic extraction branch for refining contour features and complete semantic information. Finally, we fuse the two kinds of features and leverage the segmentation head to generate the predicted portrait matte. Remarkably, EFormer is an end-to-end trimap-free method and boasts a simple structure. Experiments conducted on VideoMatte240K-JPEGSD and AIM datasets demonstrate that EFormer outperforms previous portrait matte methods.

show abstract

“…Following BiseNet (Yu et al 2018), BiSeNetV2 (Yu et al 2021) and STDC (Fan et al 2021) make further efforts to strengthen the capability to extract rich long-range context or reduce the computational costs of the spatial branch. To balance inference speed and accuracy, DDRNet (Pan et al 2022), RTFormer (Wang et al 2022), and SeaFormer (Wan et al 2023) adopt a feature-sharing architecture that divides spatial and contextual features at the deep stages, as shown in Figure 2(b). However, these methods introduce dense fusion modules between two branches to boost the semantic information of extracted features.…”

Section: Introductionmentioning

confidence: 99%

SCTNet: Single-Branch CNN with Transformer Semantic Information for Real-Time Segmentation

Xu,

Wu,

et al. 2024

AAAI

View full text Add to dashboard Cite

Recent real-time semantic segmentation methods usually adopt an additional semantic branch to pursue rich long-range context. However, the additional branch incurs undesirable computational overhead and slows inference speed. To eliminate this dilemma, we propose SCTNet, a single branch CNN with transformer semantic information for real-time segmentation. SCTNet enjoys the rich semantic representations of an inference-free semantic branch while retaining the high efficiency of lightweight single branch CNN. SCTNet utilizes a transformer as the training-only semantic branch considering its superb ability to extract long-range context. With the help of the proposed transformer-like CNN block CFBlock and the semantic information alignment module, SCTNet could capture the rich semantic information from the transformer branch in training. During the inference, only the single branch CNN needs to be deployed. We conduct extensive experiments on Cityscapes, ADE20K, and COCO-Stuff-10K, and the results show that our method achieves the new state-of-the-art performance. The code and model is available at https://github.com/xzz777/SCTNet.

show abstract

MRFDCNet: Multireceptive Field Dense Connection Network for Real-Time Semantic Segmentation

Cited by 3 publications

References 30 publications

FP-Deeplab: a segmentation model for fabric defect detection

FP-Deeplab: a segmentation model for fabric defect detection

Coarse Semantic Guided Alpha Matting via Simultaneous Foreground and Background Estimation

SCTNet: Single-Branch CNN with Transformer Semantic Information for Real-Time Segmentation

Contact Info

Product

Resources

About