CGNet: A Light-Weight Context Guided Network for Semantic Segmentation

Wu, Tianyi; Tang, Sheng; Zhang, Rui; Cao, Juan; Zhang, Yongdong

doi:10.1109/tip.2020.3042065

Cited by 395 publications

(152 citation statements)

References 41 publications

Supporting

Mentioning

151

Contrasting

Unclassified

Order By: Relevance

“…Table 2 shows the results achieved by our CGAN-Net and several baselines, including CGNet [27], BiSeNet [21], FPENet [24], DFANet A [22] and DABNet [23]. It can be seen that our CGAN-Net with ResNet34 backbone outperforms these baselines with a mean IoU score of 72.1%.…”

Section: Semantic Segmentation On Public Benchmarksmentioning

confidence: 99%

Cgan-Net: Class-Guided Asymmetric Non-Local Network for Real-Time Semantic Segmentation

Chen

Yang

et al. 2021

ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

By introducing various non-local blocks to capture the longrange dependencies, remarkable progress has been achieved in semantic segmentation recently. However, the improvement in segmentation accuracy usually comes at the price of significant reductions in network efficiency, as non-local block usually requires expensive computation and memory cost for dense pixel-to-pixel correlation. In this paper, we introduce a Class-Guided Asymmetric Non-local Network (CGAN-Net) to enhance the class-discriminability in learned feature map, while maintaining real-time efficiency.The key to our approach is to calculate the dense similarity matrix in coarse semantic prediction maps, instead of the high-dimensional latent feature map. This is not only computationally and memory efficient, but helps to learn query-dependent global context. Experiments conducted on Cityscape and CamVid demonstrate the compelling performance of our CGAN-Net. In particular, our network achieves 76.8% mean IoU on the Cityscapes test set with a speed of 38 FPS for 1024×2048 images on a single Tesla V100 GPU.

show abstract

Section: Semantic Segmentation On Public Benchmarksmentioning

confidence: 99%

Cgan-Net: Class-Guided Asymmetric Non-Local Network for Real-Time Semantic Segmentation

Chen

Yang

et al. 2021

ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

show abstract

“…DeepLabV3+ [9] combines the properties of the above two methods that add a decoder upon DeepLabV3 to help model obtain multi-level contextual information and preserve spatial information. Differently, CGNet [49] proposed a Context Guided block for learning the joint representation of both local features and surrounding context. In addition, inspired by ParseNet [30], a global scene context was utilized in some methods [50,58] by introducing a global context branch in the network.…”

Section: Related Workmentioning

confidence: 99%

GINet: Graph Interaction Network for Scene Parsing

Zhu

et al. 2020

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

Recently, context reasoning using image regions beyond local convolution has shown great potential for scene parsing. In this work, we explore how to incorperate the linguistic knowledge to promote context reasoning over image regions by proposing a Graph Interaction unit (GI unit) and a Semantic Context Loss (SC-loss). The GI unit is capable of enhancing feature representations of convolution networks over highlevel semantics and learning the semantic coherency adaptively to each sample. Specifically, the dataset-based linguistic knowledge is first incorporated in the GI unit to promote context reasoning over the visual graph, then the evolved representations of the visual graph are mapped to each local representation to enhance the discriminated capability for scene parsing. GI unit is further improved by the SC-loss to enhance the semantic representations over the exemplar-based semantic graph. We perform full ablation studies to demonstrate the effectiveness of each component in our approach. Particularly, the proposed GINet outperforms the state-of-the-art approaches on the popular benchmarks, including Pascal-Context and COCO Stuff.

show abstract

“…Currently, real-time image semantic segmentation methods mainly focus on how to reduce the model complexity by lightening the backbone network design and simplifying the decoder structure to achieve a fast segmentation framework. [7][8][9] These approaches expect to obtain speed and performance tradeoffs with a simple framework. However, such an approach makes it difficult to recover the spatial detail information lost in the downsampling process, which results in low segmentation accuracy.…”

Section: Introductionmentioning

confidence: 99%

ASFNet: Adaptive multiscale segmentation fusion network for real‐time semantic segmentation

Zha

Liu

Yang

et al. 2021

Computer Animation & Virtual

View full text Add to dashboard Cite

Recently, the development of deep learning has facilitated continuous progress in the field of computer vision. Pixel-level semantic segmentation serves as a fundamental task in computer vision. It achieves significant results by connecting wider and deeper backbone networks and building fine-grained segmentation heads. However, applications such as self-driving cars are more critical to the computational speed of the algorithms. The trade-off between accuracy and real-time performance of existing algorithms is still a challenging task. To address this challenge, this article proposes an adaptive multiscale segmentation fusion network to fuse multiscale contextual, which designs an adaptive multiscale segmentation fusion module based on an attention mechanism. Using segmentation fusion instead of feature fusion, the multiscale segmentation results are aggregated to obtain more precise segmentation results. The final results achieved 70.9% mIoU of accuracy in the Cityspace test set, processing images at 61 FPS when the input is 1024 × 2048. In addition, when adjusting the input size to 512 × 1024, the images are processed at 185 FPS.

show abstract

CGNet: A Light-Weight Context Guided Network for Semantic Segmentation

Cited by 395 publications

References 41 publications

Cgan-Net: Class-Guided Asymmetric Non-Local Network for Real-Time Semantic Segmentation

Cgan-Net: Class-Guided Asymmetric Non-Local Network for Real-Time Semantic Segmentation

GINet: Graph Interaction Network for Scene Parsing

ASFNet: Adaptive multiscale segmentation fusion network for real‐time semantic segmentation

Contact Info

Product

Resources

About