Search

Visual scene understanding mainly depends on pixel-wise classification obtained from a deep convolutional neural network. However, existing semantic segmentation models often face difficulties in real-time applications due to their large network architecture. Although there are real-time semantic segmentation models available, their shallow backbone can degrade the performance considerably. This paper introduces SDBNetV2, a lightweight semantic segmentation model designed to improve real-time performance without increasing computational costs. A key contribution is a novel Short-term Dense Bottleneck (SDB) module in the encoder, which provides varied field-of-views to capture different geometrical objects in a complex scene. Additionally, we propose dense feature refinement and improved semantic aggregation modules at the decoder end to enhance contextualization and object localization. We evaluate the proposed model's performance on several indoor and outdoor datasets in structured and unstructured environments. The results show that SDBNetV2 achieves superior segmentation performance over other real-time models with less than 2 million parameters. [Display omitted] • By relying on dense bottleneck design, an encoder is crafted for better field-of-view. • Introduce larger kernel sizes early in the encoder for better receptivity. • Propose a dense feature refinement module for improved global feature maps. • Propose an aggregation module for better contextualization and object localization. • The proposed model achieves the optimal trade-off between accuracy and efficiency. [ABSTRACT FROM AUTHOR]

• A new yet effective lightweight shared multiple sub-encoders design for feature sharing and feature reusing across the encoder. • A novel Cascading Context Mining (CCM) module which segments the regions with different receptive fields at different spatial dimensions of the input. • A new Hybrid Path Attention Semantic Aggregation (HPA-SA) module for identifying and localizing all the objects in a complex scene accurately. • The proposed model produced the state-of-the-art result on four datasets among the existing semantic models having 2 million parameters or less. Recent studies show a significant growth in semantic segmentation. However, many semantic segmentation models still have a large number of parameters, making them unsuitable for resource-constrained embedded devices. To address this issue, we propose an efficient Shared Feature Reuse Segmentation (SFRSeg) model containing several novelties: a new yet effective shared-branch multiple sub-encoders design, a context mining module and a semantic aggregating module for better context granularity. In particular, our shared-branch approach improves the entire feature hierarchy by sharing the spatial and context knowledge in both shallow and deep branches. After every shared point in each sub-encoder, a proposed cascading context mining (CCM) module is deployed to filter out the noisy spatial details from the feature maps and provides a diverse size of receptive fields for capturing the latent context between multi-scale geometric shapes in the scene. To overcome the gradient vanishing issue at the early stage, we reduce the number of layers in the first sub-encoder and employ a unique multiple sub-encoders design which reprocesses the rich global feature maps through multiple sub-encoders for better feature refinement. Later, the rich semantic features generated by the efficient sub-encoders at different levels are fused by the proposed Hybrid Path Attention Semantic Aggregation (HPA-SA) module that effectively reduces the semantic gap between feature maps at different levels and alleviate the well-known boundary degeneration effect. To make it computationally efficient for resource-constrained embedded devices, a series of lightweight methods such as a lightweight encoder, a squeeze-and-excitation design, separable convolution filters, channel reduction (CR) are carefully exploited. With an exceptional performance on Cityscapes (70.6% test mIoU) and CamVid (74.7% test mIoU) data sets, the proposed model is shown to be superior over existing light real-time semantic segmentation models whilst having only 1.6 million parameters. [ABSTRACT FROM AUTHOR]