Related papers: Enhanced 3D Object Detection via Diverse Feature R…
Knowledge Distillation (KD) has been used in image classification for model compression. However, rare studies apply this technology on single-stage object detectors. Focal loss shows that the accumulated errors of easily-classified samples…
As a general model compression paradigm, feature-based knowledge distillation allows the student model to learn expressive features from the teacher counterpart. In this paper, we mainly focus on designing an effective feature-distillation…
Recently, deep learning-based models have been widely studied for click-through rate (CTR) prediction and lead to improved prediction accuracy in many industrial applications. However, current research focuses primarily on building complex…
LiDAR-based 3D object detection models have traditionally struggled under rainy conditions due to the degraded and noisy scanning signals. Previous research has attempted to address this by simulating the noise from rain to improve the…
LiDAR point clouds are widely used in autonomous driving and consist of large numbers of 3D points captured at high frequency to represent surrounding objects such as vehicles, pedestrians, and traffic signs. While this dense data enables…
Object detection and classification is one of the most important computer vision problems. Ever since the introduction of deep learning \cite{krizhevsky2012imagenet}, we have witnessed a dramatic increase in the accuracy of this object…
Robust perception is a vital component for ensuring safe autonomous and assisted driving. Automotive radar (77 to 81 GHz), which offers weather-resilient sensing, provides a complementary capability to the vision- or LiDAR-based autonomous…
Transformers have revolutionized the object detection landscape by introducing DETRs, acclaimed for their simplicity and efficacy. Despite their advantages, the substantial size of these models poses significant challenges for practical…
In recent years, there has been a great deal of research in developing end-to-end speech recognition models, which enable simplifying the traditional pipeline and achieving promising results. Despite their remarkable performance…
The representation gap between teacher and student is an emerging topic in knowledge distillation (KD). To reduce the gap and improve the performance, current methods often resort to complicated training schemes, loss functions, and feature…
The existing solutions for object detection distillation rely on the availability of both a teacher model and ground-truth labels. We propose a new perspective to relax this constraint. In our framework, a student is first trained with…
Three-dimensional (3D) object recognition is crucial for intelligent autonomous agents such as autonomous vehicles and robots alike to operate effectively in unstructured environments. Most state-of-art approaches rely on relatively dense…
Recent mainstream masked distillation methods function by reconstructing selectively masked areas of a student network from the feature map of its teacher counterpart. In these methods, the masked regions need to be properly selected, such…
Detecting objects efficiently from radar sensors has recently become a popular trend due to their robustness against adverse lighting and weather conditions compared with cameras. This paper presents an efficient object detection model for…
Deep neural networks based methods have been proved to achieve outstanding performance on object detection and classification tasks. Despite significant performance improvement, due to the deep structures, they still require prohibitive…
Although multi-view 3D object detection based on the Bird's-Eye-View (BEV) paradigm has garnered widespread attention as an economical and deployment-friendly perception solution for autonomous driving, there is still a performance gap…
The emerging 4D millimeter-wave radar, measuring the range, azimuth, elevation, and Doppler velocity of objects, is recognized for its cost-effectiveness and robustness in autonomous driving. Nevertheless, its point clouds exhibit…
Vision-based crack detection faces deployment challenges due to the size of robust models and edge device limitations. These can be addressed with lightweight models trained with knowledge distillation (KD). However, state-of-the-art (SOTA)…
Light Detection And Ranging (LiDAR) has been widely used in autonomous vehicles for perception and localization. However, the cost of a high-resolution LiDAR is still prohibitively expensive, while its low-resolution counterpart is much…
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…