Related papers: Efficient Transformer-based 3D Object Detection wi…

Robust 3D object detection is a core challenge for autonomous mobile systems in field robotics. To tackle this issue, many researchers have demonstrated improvements in 3D object detection performance in datasets. However, real-world urban…

We present an approach to pose object recognition as next token prediction. The idea is to apply a language decoder that auto-regressively predicts the text tokens from image embeddings to form labels. To ground this prediction process in…

Occupancy and 3D object detection are characterized as two standard tasks in modern autonomous driving system. In order to deploy them on a series of edge chips with better precision and time-consuming trade-off, contemporary approaches…

Attention is sparse in vision transformers. We observe the final prediction in vision transformers is only based on a subset of most informative tokens, which is sufficient for accurate image recognition. Based on this observation, we…

Vision Transformer (ViT)-based sparse multi-view 3D object detectors have achieved remarkable accuracy but still suffer from high inference latency due to heavy token processing. To accelerate these models, token compression has been widely…

Service robots, in general, have to work independently and adapt to the dynamic changes happening in the environment in real-time. One important aspect in such scenarios is to continually learn to recognize newer object categories when they…

In Transformer architectures, tokens\textemdash discrete units derived from raw data\textemdash are formed by segmenting inputs into fixed-length chunks. Each token is then mapped to an embedding, enabling parallel attention computations…

3D Transformers have achieved great success in point cloud understanding and representation. However, there is still considerable scope for further development in effective and efficient Transformers for large-scale LiDAR point cloud scene…

In radar-camera 3D object detection, the radar point clouds are sparse and noisy, which causes difficulties in fusing camera and radar modalities. To solve this, we introduce a novel query-based detection method named Radar-Camera…

Transformers have been matching deep convolutional networks for vision architectures in recent works. Most work is focused on getting the best results on large-scale benchmarks, and scaling laws seem to be the most successful strategy:…

Detecting 3D objects in point clouds plays a crucial role in autonomous driving systems. Recently, advanced multi-modal methods incorporating camera information have achieved notable performance. For a safe and effective autonomous driving…

Vision transformers have achieved significant improvements on various vision tasks but their quadratic interactions between tokens significantly reduce computational efficiency. Many pruning methods have been proposed to remove redundant…

In the world of deep learning, Transformer models have become very significant, leading to improvements in many areas from understanding language to recognizing images, covering a wide range of applications. Despite their success, the…

Deep network architectures struggle to continually learn new tasks without forgetting the previous tasks. A recent trend indicates that dynamic architectures based on an expansion of the parameters can reduce catastrophic forgetting…

3D object detection with surround-view images is an essential task for autonomous driving. In this work, we propose DETR4D, a Transformer-based framework that explores sparse attention and direct feature query for 3D object detection in…

Attention mechanism has been crucial for image diffusion models, however, their quadratic computational complexity limits the sizes of images we can process within reasonable time and memory constraints. This paper investigates the…

Line detection is a basic digital image processing operation used by higher-level processing methods. Recently, transformer-based methods for line detection have proven to be more accurate than methods based on CNNs, at the expense of…

Diffusion Transformers (DiTs) achieve superior image generation quality but suffer from quadratic computational complexity relative to token count. While various token reduction (TR) methods have been proposed to mitigate this cost, they…

This work aims to address the challenges in autonomous driving by focusing on the 3D perception of the environment using roadside LiDARs. We design a 3D object detection model that can detect traffic participants in roadside LiDARs in…

We develop an edge-assisted object recognition system with the aim of studying the system-level trade-offs between end-to-end latency and object recognition accuracy. We focus on developing techniques that optimize the transmission delay of…