Translating Images to Road Network: A Non-Autoregressive Sequence-to-Sequence Approach

2023-01-01 · ICCV 2023 1 · Jiachen Lu, Renyuan Peng, Xinyue Cai, Hang Xu, Hongyang Li, Feng Wen, Wei zhang, Li Zhang

The extraction of road network is essential for the generation of high-definition maps since it enables the precise localization of road landmarks and their interconnections. However, generating road network poses a significant challenge due to the conflicting underlying combination of Euclidean (e.g., road landmarks location) and non-Euclidean (e.g., road topological connectivity) structures. Existing methods struggle to merge the two types of data domains effectively, but few of them address it properly. Instead, our work establishes a unified representation of both types of data domain by projecting both Euclidean and non-Euclidean data into an integer series called RoadNet Sequence. Further than modeling an auto-regressive sequence-to-sequence Transformer model to understand RoadNet Sequence, we decouple the dependency of RoadNet Sequence into a mixture of auto-regressive and non-autoregressive dependency. Building on this, our proposed non-autoregressive sequence-to-sequence approach leverages non-autoregressive dependencies while fixing the gap towards auto-regressive dependencies, resulting in success on both efficiency and accuracy. Extensive experiments on nuScenes dataset demonstrate the superiority of RoadNet Sequence representation and the non-autoregressive approach compared to existing state-of-the-art alternatives.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Attention 설명 없음

Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…

Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…

BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…

Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…

Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.

Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…

Translating Images to Road Network: A Sequence-to-Sequence Perspective

2024-02-13 · Jiachen Lu, Renyuan Peng, Xinyue Cai, Hang Xu 외

Data-Driven Stochastic Modeling Using Autoregressive Sequence Models: Translating Event Tables to Queueing Dynamics

2025-09-06 · Daksh Mittal, Shunri Zheng, Jing Dong, Hongseok Namkoong arxiv

While queueing network models are powerful tools for analyzing service systems, they traditionally require substantial human effort and domain expertise to construct. To make this modeling approach more scalable and acce…

Jointly Masked Sequence-to-Sequence Model for Non-Autoregressive Neural Machine Translation

2020-07-01 · ACL 2020 6 · Junliang Guo, Linli Xu, Enhong Chen

The masked language model has received remarkable attention due to its effectiveness on various natural language processing tasks. However, few works have adopted this technique in the sequence-to-sequence models. In thi…

Decoder Language Modeling Language Modelling Machine Translation+1

Hidden Markov Transformer for Simultaneous Machine Translation

2023-03-01 · Shaolei Zhang, Yang Feng

Simultaneous machine translation (SiMT) outputs the target sequence while receiving the source sequence, and hence learning when to start translating each target token is the core challenge for SiMT task. However, it is …

Machine Translation Translation

Separators in Enhancing Autoregressive Pretraining for Vision Mamba

2026-03-04 · Hanpeng Liu, Zidan Wang, Shuoxi Zhang, Kaiyuan Gao 외 arxiv

The state space model Mamba has recently emerged as a promising paradigm in computer vision, attracting significant attention due to its efficient processing of long sequence tasks. Mamba's inherent causal mechanism rend…