Related papers: Study of Dropout in PointPillars with 3D Object De…
The ability to detect objects that are not prevalent in the training set is a critical capability in many 3D applications, including autonomous driving. Machine learning methods for object recognition often assume that all object categories…
LiDAR-based 3D object detection has become an essential part of automated driving due to its ability to localize and classify objects precisely in 3D. However, object detectors face a critical challenge when dealing with unknown foreground…
Dropout is often used in deep neural networks to prevent over-fitting. Conventionally, dropout training invokes \textit{random drop} of nodes from the hidden layers of a Neural Network. It is our hypothesis that a guided selection of nodes…
In this work, we address the problem of 3D object detection from point cloud data in real time. For autonomous vehicles to work, it is very important for the perception component to detect the real world objects with both high accuracy and…
Weakly Supervised Object Localization (WSOL) techniques learn the object location only using image-level labels, without location annotations. A common limitation for these techniques is that they cover only the most discriminative part of…
This paper proposes a new regularization algorithm referred to as macro-block dropout. The overfitting issue has been a difficult problem in training large neural network models. The dropout technique has proven to be simple yet very…
Contrary to most machine learning models, modern deep artificial neural networks typically include multiple components that contribute to regularization. Despite the fact that some (explicit) regularization techniques, such as weight decay…
3D object detection with LiDAR point clouds plays an important role in autonomous driving perception module that requires high speed, stability and accuracy. However, the existing point-based methods are challenging to reach the speed…
Dropout has been proven to be an effective algorithm for training robust deep networks because of its ability to prevent overfitting by avoiding the co-adaptation of feature detectors. Current explanations of dropout include bagging, naive…
Object detection and tracking are vital and fundamental tasks for autonomous driving, aiming at identifying and locating objects from those predefined categories in a scene. 3D point cloud learning has been attracting more and more…
We propose DOPS, a fast single-stage 3D object detection method for LIDAR data. Previous methods often make domain-specific design decisions, for example projecting points into a bird-eye view image in autonomous driving scenarios. In…
Dropout as a common regularizer to prevent overfitting in deep neural networks has been less effective in convolutional layers than in fully connected layers. This is because Dropout drops features randomly, without considering local…
Deep convolutional neural networks have shown remarkable performance on various computer vision tasks, and yet, they are susceptible to picking up spurious correlations from the training signal. So called `shortcuts' can occur during…
Dropout is conventionally used during the training phase as regularization method and for quantifying uncertainty in deep learning. We propose to use dropout during training as well as inference steps, and average multiple predictions to…
Variants dropout methods have been designed for the fully-connected layer, convolutional layer and recurrent layer in neural networks, and shown to be effective to avoid overfitting. As an appealing alternative to recurrent and…
The past few years have witnessed the fast development of different regularization methods for deep learning models such as fully-connected deep neural networks (DNNs) and Convolutional Neural Networks (CNNs). Most of previous methods…
We present a simple and flexible object detection framework optimized for autonomous driving. Building on the observation that point clouds in this application are extremely sparse, we propose a practical pillar-based approach to fix the…
Recurrent neural networks (RNNs) with Long Short-Term memory cells currently hold the best known results in unconstrained handwriting recognition. We show that their performance can be greatly improved using dropout - a recently proposed…
This work aims to address the challenges in domain adaptation of 3D object detection using infrastructure LiDARs. We design a model DASE-ProPillars that can detect vehicles in infrastructure-based LiDARs in real-time. Our model uses…
Using a large number of parameters , deep neural networks have achieved remarkable performance on computer vison and natural language processing tasks. However the networks usually suffer from overfitting by using too much parameters.…