paper-with-me

Papers

PT-ResNet: Perspective Transformation-Based Residual Network for Semantic Road Image Segmentation

2019-10-29 · Rui Fan, Yu-An Wang, Lei Qiao, Ruiwen Yao, Peng Han, Weidong Zhang, Ioannis Pitas, Ming Liu

Semantic road region segmentation is a high-level task, which paves the way towards road scene understanding. This paper presents a residual network trained for semantic road segmentation. Firstly, we represent the projections of road disparities in the v-disparity map as a linear model, which can be estimated by optimizing the v-disparity map using dynamic programming. This linear model is then utilized to reduce the redundant information in the left and right road images. The right image is also transformed into the left perspective view, which greatly enhances the road surface similarity between the two images. Finally, the processed stereo images and their disparity maps are concatenated to create a set of 3D images, which are then utilized to train our neural network. The experimental results illustrate that our network achieves a maximum F1-measure of approximately 91.19% when analyzing the images from the KITTI road dataset.

📄 PDF Abstract BibTeX arXiv:1910.13055

Code (0)

등록된 구현이 없습니다.

Tasks

Image Segmentationroad scene understandingRoad SegmentationScene UnderstandingSegmentationSemantic Segmentation

Similar Papers 제목 키워드 기반

MFI-ResNet: Efficient ResNet Architecture Optimization via MeanFlow Compression and Selective Incubation

2025-11-16 · Nuolin Sun, Linyuan Wang, Haonan Wei, Lei Li 외 arxiv

ResNet has achieved tremendous success in computer vision through its residual connection mechanism. ResNet can be viewed as a discretized form of ordinary differential equations (ODEs). From this perspective, the multip…

Broadcasted Residual Learning for Efficient Keyword Spotting

2021-06-08 · Byeonggeun Kim, Simyung Chang, Jinkyu Lee, Dooyong Sung

Keyword spotting is an important research field because it plays a key role in device wake-up and user interaction on smart devices. However, it is challenging to minimize errors while operating efficiently in devices wi…

Keyword Spotting

Residual Networks as Flows of Velocity Fields for Diffeomorphic Time Series Alignment

2021-06-22 · Hao Huang, Boulbaba Ben Amor, Xichan Lin, Fan Zhu 외

Non-linear (large) time warping is a challenging source of nuisance in time-series analysis. In this paper, we propose a novel diffeomorphic temporal transformer network for both pairwise and joint time-series alignment.…

Time SeriesTime Series AlignmentTime Series Analysis

On the Global Convergence of Training Deep Linear ResNets

2020-03-02 · ICLR 2020 1 · Difan Zou, Philip M. Long, Quanquan Gu

We study the convergence of gradient descent (GD) and stochastic gradient descent (SGD) for training $L$-hidden-layer linear residual networks (ResNets). We prove that for training deep residual networks with certain lin…

A Dynamical System Perspective for Lipschitz Neural Networks

2021-10-25 · Laurent Meunier, Blaise Delattre, Alexandre Araujo, Alexandre Allauzen

The Lipschitz constant of neural networks has been established as a key quantity to enforce the robustness to adversarial examples. In this paper, we tackle the problem of building $1$-Lipschitz Neural Networks. By study…