BiSeNet V2: Bilateral Network with Guided Aggregation for Real-Time Semantic Segmentation

Yu, Changqian; Gao, Changxin; Wang, Jingbo; Yu, Gang; Shen, Chunhua; Sang, Nong

doi:10.1007/s11263-021-01515-2

Cited by 967 publications

(414 citation statements)

References 59 publications

Supporting

Mentioning

301

Contrasting

Unclassified

Order By: Relevance

“…The evaluation of image semantic segmentation of the converted classes of RELLIS-3D and RUGD were done using two state-of-the-art architectures: BiSeNetV2 [16] and HRNETV2 [15]+OCR [17]. BiSeNetV2 consists of two branches: detail branch and semantic branch.…”

Section: A Segmentationmentioning

confidence: 99%

OFFSEG: A Semantic Segmentation Framework For Off-Road Driving

Viswanath¹,

Singh²,

Jiang³

et al. 2021

Preprint

View full text Add to dashboard Cite

Off-road image semantic segmentation is challenging due to the presence of uneven terrains, unstructured class boundaries, irregular features and strong textures. These aspects affect the perception of the vehicle from which the information is used for path planning. Current off-road datasets exhibit difficulties like class imbalance and understanding of varying environmental topography. To overcome these issues we propose a framework for off-road semantic segmentation called as OFFSEG that involves (i) a pooled class semantic segmentation with four classes (sky, traversable region, nontraversable region and obstacle) using state-of-the-art deep learning architectures (ii) a colour segmentation methodology to segment out specific sub-classes (grass, puddle, dirt, gravel, etc.) from the traversable region for better scene understanding. The evaluation of the framework is carried out on two off-road driving datasets, namely, RELLIS-3D and RUGD. We have also tested proposed framework in IISERB campus frames. The results show that OFFSEG achieves good performance and also provides detailed information on the traversable region.

show abstract

Section: A Segmentationmentioning

confidence: 99%

OFFSEG: A Semantic Segmentation Framework For Off-Road Driving

Viswanath¹,

Singh²,

Jiang³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Although these deep learning architectures achieved excellent segmentation performance, the dilation convolutions and the skip connections increase the computational complexity and memory overhead, leading to slow inference speeds. To solve this issue, Yu et al [ 19 ], [ 20 ] proposed a two-pathway architecture, known as the Bilateral Segmentation Network (BiSeNet), to speed up the segmentation inference time. The first pathway has wide channels and shallow layers to capture the spatial information from the image while the second pathway provides a large receptive field to capture wider context.…”

Section: Introductionmentioning

confidence: 99%

“…These two pathways concurrently generate feature representations, which significantly increase the segmentation efficiency. As demonstrated in [ 19 ], [ 20 ], this conceptual design is significantly faster than dilation and encoder-decoder architectures.…”

Section: Introductionmentioning

confidence: 99%

“…First, we use a Spatial Transformer Network (STN) as a module to direct the attention of segmentation to a specific ROI while learning the context relationship between different ROIs. Second, we integrate into BiSeNet [ 20 ] a handcrafted pathway ( HP ) with handcrafted-encoded convolutional kernels. This pathway is used to extract, at different levels of abstraction, a unique set of features complementary to the deep features.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Trilateral Attention Network for Real-Time Cardiac Region Segmentation

2021

View full text Add to dashboard Cite

The accurate segmentation of cardiac images into anatomically meaningful regions is critical for the extraction of quantitative cardiac indices. The common pipeline for segmentation comprises regions of interest (ROIs) localization and segmentation stages that are independent of each other and typically performed using separate models. In this paper, we propose an end-to-end network, called Trilateral Attention Network (TaNet), for real-time region localization and segmentation. TaNet has a module for ROIs localization and three segmentation pathways: spatial pathway, handcrafted pathway, and context pathway. The localization module focuses segmentation attention on the desired region while learning the context relationship between different regions in the image. The localized regions are then sent to the three pathways for segmentation. The spatial pathway, which has regular convolutional kernels, is used to extract deep features at different levels of abstraction. The handcrafted pathway, which has hand-designed convolutional kernels, is used to extract a unique set of features complementary to the deep features. Finally, the context (or global) pathway is used to enlarge the receptive field. By jointly training TaNet for localization and segmentation, TaNet achieved superior performance, in terms of accuracy and speed, when evaluated on two echocardiography datasets for cardiac region segmentation. The code and models will be made publicly available in TaNet Github page.

show abstract

“…These architectures indeed have fewer operations, but the decoders lack the ability of feature aggregation and may easily lose the fine-grained spatial details around boundaries or small objects. To make a balance between accuracy and speed, Changqian Yu et al [20] put forward an improved version of BiSeNet [19] (dubbed BiSeNet V2). The core components include Spatial Path and Context Path to cope with the loss of spatial information and shrinkage of receptive field, respectively.…”

Section: Introductionmentioning

confidence: 99%

A Hierarchical Feature Extraction Network for Fast Scene Segmentation

Liu

Zhang

2021

Sensors

View full text Add to dashboard Cite

Semantic segmentation is one of the most active research topics in computer vision with the goal to assign dense semantic labels for all pixels in a given image. In this paper, we introduce HFEN (Hierarchical Feature Extraction Network), a lightweight network to reach a balance between inference speed and segmentation accuracy. Our architecture is based on an encoder-decoder framework. The input images are down-sampled through an efficient encoder to extract multi-layer features. Then the extracted features are fused via a decoder, where the global contextual information and spatial information are aggregated for final segmentations with real-time performance. Extensive experiments have been conducted on two standard benchmarks, Cityscapes and Camvid, where our network achieved superior performance on NVIDIA 2080Ti.

show abstract

BiSeNet V2: Bilateral Network with Guided Aggregation for Real-Time Semantic Segmentation

Cited by 967 publications

References 59 publications

OFFSEG: A Semantic Segmentation Framework For Off-Road Driving

OFFSEG: A Semantic Segmentation Framework For Off-Road Driving

Trilateral Attention Network for Real-Time Cardiac Region Segmentation

A Hierarchical Feature Extraction Network for Fast Scene Segmentation

Contact Info

Product

Resources

About