Reimagine BiSeNet for Real-Time Domain Adaptation in Semantic Segmentation

2021-10-22 · Antonio Tavera, Carlo Masone, Barbara Caputo

Semantic segmentation models have reached remarkable performance across various tasks. However, this performance is achieved with extremely large models, using powerful computational resources and without considering training and inference time. Real-world applications, on the other hand, necessitate models with minimal memory demands, efficient inference speed, and executable with low-resources embedded devices, such as self-driving vehicles. In this paper, we look at the challenge of real-time semantic segmentation across domains, and we train a model to act appropriately on real-world data even though it was trained on a synthetic realm. We employ a new lightweight and shallow discriminator that was specifically created for this purpose. To the best of our knowledge, we are the first to present a real-time adversarial approach for assessing the domain adaption problem in semantic segmentation. We tested our framework in the two standard protocol: GTA5 to Cityscapes and SYNTHIA to Cityscapes. Code is available at: https://github.com/taveraantonio/RTDA.

📄 PDF Abstract BibTeX arXiv:2110.11662

Code (1)

taveraantonio/rtda 공식 구현 pytorch

Tasks

Domain Adaptation Real-Time Semantic Segmentation Segmentation Semantic Segmentation

The revenge of BiSeNet: Efficient Multi-Task Image Segmentation

2024-04-15 · Gabriele Rosi, Claudia Cuttano, Niccolò Cavagnero, Giuseppe Averta 외

Recent advancements in image segmentation have focused on enhancing the efficiency of the models to meet the demands of real-time applications, especially on edge devices. However, existing research has primarily concent…

Image Segmentation Panoptic Segmentation Segmentation Semantic Segmentation

BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation

2018-08-02 · ECCV 2018 9 · Changqian Yu, Jingbo Wang, Chao Peng, Changxin Gao 외

Semantic segmentation requires both rich spatial information and sizeable receptive field. However, modern approaches usually compromise spatial resolution to achieve real-time inference speed, which leads to poor perfor…

Dichotomous Image Segmentation Real-Time Semantic Segmentation Segmentation Semantic Segmentation+1

Threshold-adaptive Unsupervised Focal Loss for Domain Adaptation of Semantic Segmentation

2022-08-23 · Weihao Yan, Yeqiang Qian, Chunxiang Wang, Ming Yang

Semantic segmentation is an important task for intelligent vehicles to understand the environment. Current deep learning methods require large amounts of labeled data for training. Manual annotation is expensive, while s…

Data Augmentation Domain Adaptation Segmentation Semantic Segmentation+1

Rethinking BiSeNet For Real-time Semantic Segmentation

2021-04-27 · CVPR 2021 1 · Mingyuan Fan, Shenqi Lai, Junshi Huang, Xiaoming Wei 외

BiSeNet has been proved to be a popular two-stream network for real-time segmentation. However, its principle of adding an extra path to encode spatial information is time-consuming, and the backbones borrowed from pretr…

Decoder Dichotomous Image Segmentation image-classification Image Classification+4

ShelfNet for Fast Semantic Segmentation

2018-11-27 · Juntang Zhuang, Junlin Yang, Lin Gu, Nicha Dvornek

In this paper, we present ShelfNet, a novel architecture for accurate fast semantic segmentation. Different from the single encoder-decoder structure, ShelfNet has multiple encoder-decoder branch pairs with skip connecti…

Autonomous Driving Decoder Real-Time Semantic Segmentation Scene Understanding+2