paper-with-me

Papers

RoadPainter: Points Are Ideal Navigators for Topology transformER

2024-07-22 · Zhongxing Ma, Shuang Liang, Yongkun Wen, Weixin Lu, Guowei Wan

Topology reasoning aims to provide a precise understanding of road scenes, enabling autonomous systems to identify safe and efficient routes. In this paper, we present RoadPainter, an innovative approach for detecting and reasoning the topology of lane centerlines using multi-view images. The core concept behind RoadPainter is to extract a set of points from each centerline mask to improve the accuracy of centerline prediction. We start by implementing a transformer decoder that integrates a hybrid attention mechanism and a real-virtual separation strategy to predict coarse lane centerlines and establish topological associations. Then, we generate centerline instance masks guided by the centerline points from the transformer decoder. Moreover, we derive an additional set of points from each mask and combine them with previously detected centerline points for further refinement. Additionally, we introduce an optional module that incorporates a Standard Definition (SD) map to further optimize centerline detection and enhance topological reasoning performance. Experimental evaluations on the OpenLane-V2 dataset demonstrate the state-of-the-art performance of RoadPainter.

📄 PDF Abstract BibTeX arXiv:2407.15349

Code (0)

등록된 구현이 없습니다.

Tasks

Decoder

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Attention 설명 없음
SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

Virtual avatar generation models as world navigators

2024-06-03 · Sai Mandava

We introduce SABR-CLIMB, a novel video model simulating human movement in rock climbing environments using a virtual avatar. Our diffusion transformer predicts the sample instead of noise in each diffusion step and inges…

Beyond Point-wise Neural Collapse: A Topology-Aware Hierarchical Classifier for Class-Incremental Learning

2026-05-12 · Huiyu Yi, Zhiming Xu, Dunwei Tu, Zhicheng Wang 외 arxiv

The Nearest Class Mean (NCM) classifier is widely favored in Class-Incremental Learning (CIL) for its superior resistance to catastrophic forgetting compared to Fully Connected layers. While Neural Collapse (NC) theory s…

class-incremental learning

PoliFormer: Scaling On-Policy RL with Transformers Results in Masterful Navigators

2024-06-28 · Kuo-Hao Zeng, Zichen Zhang, Kiana Ehsani, Rose Hendrix 외

We present PoliFormer (Policy Transformer), an RGB-only indoor navigation agent trained end-to-end with reinforcement learning at scale that generalizes to the real-world without adaptation despite being trained purely i…

DecoderObjectObject Tracking

Visual Transformers: Where Do Transformers Really Belong in Vision Models?

2021-01-01 · ICCV 2021 10 · Bichen Wu, Chenfeng Xu, Xiaoliang Dai, Alvin Wan 외

A recent trend in computer vision is to replace convolutions with transformers. However, the performance gain of transformers is attained at a steep cost, requiring GPU years and hundreds of millions of samples for t…

GPUSemantic Segmentation

AutoMS: Multi-Agent Evolutionary Search for Cross-Physics Inverse Microstructure Design

2026-03-28 · Zhenyuan Zhao, Yu Xing, Tianyang Xue, Lingxin Cao 외 arxiv

Designing microstructures with coupled cross-physics objectives is a fundamental challenge where traditional topology optimization is often computationally prohibitive and deep generative models frequently suffer from ph…