Related papers: Sparse Laneformer

In this paper, we propose a learning approach for sparse code multiple access (SCMA) signal detection by using a deep neural network via unfolding the procedure of message passing algorithm (MPA). The MPA can be converted to a sparsely…

Standard inference and training with transformer based architectures scale quadratically with input sequence length. This is prohibitively large for a variety of applications especially in web-page translation, query-answering etc.…

Vision Transformers (ViTs) have become a universal backbone for both image recognition and image generation. Yet their Multi-Head Self-Attention (MHSA) layer still performs a quadratic query-key interaction for every token pair, spending…

Linear attention has emerged as a promising alternative to softmax-based attention, leveraging kernelized feature maps to reduce complexity from quadratic to linear in sequence length. However, the non-negative constraint on feature maps…

Vision Transformers have achieved impressive performance in many vision tasks. While the token mixer or attention block has been studied in great detail, much less research has been devoted to the channel mixer or feature mixing block (FFN…

In this paper, we present a dense hybrid proposal modulation (DHPM) method for lane detection. Most existing methods perform sparse supervision on a subset of high-scoring proposals, while other proposals fail to obtain effective shape and…

The Vision-Language-Action (VLA) models have demonstrated remarkable performance on embodied tasks and shown promising potential for real-world applications. However, current VLAs still struggle to produce consistent and precise…

Rotation detection serves as a fundamental building block in many visual applications involving aerial image, scene text, and face etc. Differing from the dominant regression-based approaches for orientation estimation, this paper explores…

The task of Stance Detection involves discerning the stance expressed in a text towards a specific subject or target. Prior works have relied on existing transformer models that lack the capability to prioritize targets effectively.…

While supervised detection and classification frameworks in autonomous driving require large labelled datasets to converge, Unsupervised Domain Adaptation (UDA) approaches, facilitated by synthetic data generated from photo-real simulated…

High-dimensional data sets are often analyzed and explored via the construction of a latent low-dimensional space which enables convenient visualization and efficient predictive modeling or clustering. For complex data structures, linear…

Generating robust and reliable correspondences across images is a fundamental task for a diversity of applications. To capture context at both global and local granularity, we propose ASpanFormer, a Transformer-based detector-free matcher…

Efficiency is quite important for 3D lane detection due to practical deployment demand. In this work, we propose a simple, fast, and end-to-end detector that still maintains high detection precision. Specifically, we devise a set of fully…

Lane detection is an integral part of control systems in autonomous vehicles and lane departure warning systems as lanes are a key component of the operating environment for road vehicles. In a previous paper, a robust neural network output…

Lane detection is one of the fundamental modules in self-driving. In this paper we employ a transformer-only method for lane detection, thus it could benefit from the blooming development of fully vision transformer and achieve the…

The search for predictive models that generalize to the long tail of sensor inputs is the central difficulty when developing data-driven models for autonomous vehicles. In this paper, we use lane detection to study modeling and training…

Lane detection is a fundamental task in autonomous driving. While the problem is typically formulated as the detection of continuous boundaries, we study the problem of detecting lane boundaries that are sparsely marked by 2D points with…

The latest generation of transformer-based vision models has proven to be superior to Convolutional Neural Network (CNN)-based models across several vision tasks, largely attributed to their remarkable prowess in relation modeling.…

Recent advances in training-free video editing have enabled lightweight and precise cross-frame generation by leveraging pre-trained text-to-image diffusion models. However, existing methods often rely on heuristic frame selection to…

3D-LaneNet+ is a camera-based DNN method for anchor free 3D lane detection which is able to detect 3d lanes of any arbitrary topology such as splits, merges, as well as short and perpendicular lanes. We follow recently proposed 3D-LaneNet,…