Related papers: Comparing a composite model versus chained models …

We present here, a novel network architecture called MergeNet for discovering small obstacles for on-road scenes in the context of autonomous driving. The basis of the architecture rests on the central consideration of training with less…

A strong visual object tracker nowadays relies on its well-crafted modules, which typically consist of manually-designed network architectures to deliver high-quality tracking results. Not surprisingly, the manual design process becomes a…

Neural architecture search has attracted wide attentions in both academia and industry. To accelerate it, researchers proposed weight-sharing methods which first train a super-network to reuse computation among different operators, from…

Multi-task learning improves generalization performance by sharing knowledge among related tasks. Existing models are for task combinations annotated on the same dataset, while there are cases where multiple datasets are available for each…

This work theoretically investigates the performance of a composite neural network. A composite neural network is a rooted directed acyclic graph combining a set of pre-trained and non-instantiated neural network models, where a pre-trained…

This paper presents a comparative study of a custom convolutional neural network (CNN) architecture against widely used pretrained and transfer learning CNN models across five real-world image datasets. The datasets span binary…

This study delves into the application of graph neural networks in the realm of traffic forecasting, a crucial facet of intelligent transportation systems. Accurate traffic predictions are vital for functions like trip planning, traffic…

Learning-based methods have become increasingly popular for solving vehicle routing problems due to their near-optimal performance and fast inference speed. Among them, the combination of deep reinforcement learning and graph representation…

Object detection and segmentation are two core modules of an autonomous vehicle perception system. They should have high efficiency and low latency while reducing computational complexity. Currently, the most commonly used algorithms are…

Deep convolutional neural networks, assisted by architectural design strategies, make extensive use of data augmentation techniques and layers with a high number of feature maps to embed object transformations. That is highly inefficient…

Motivated by the increasing availability of vehicle trajectory data, we propose learn-to-route, a comprehensive trajectory-based routing solution. Specifically, we first construct a graph-like structure from trajectories as the routing…

In recent years, deep neural networks have had great success in machine learning and pattern recognition. Architecture size for a neural network contributes significantly to the success of any neural network. In this study, we optimize the…

A deep learning architecture is proposed to predict graspable locations for robotic manipulation. It considers situations where no, one, or multiple object(s) are seen. By defining the learning problem to be classification with null…

Coreset, which is a summary of the original dataset in the form of a small weighted set in the same sample space, provides a promising approach to enable machine learning over distributed data. Although viewed as a proxy of the original…

This dissertation is a study on the design and analysis of novel, optimal routing and rate control algorithms in wireless, mobile communication networks. Congestion control and routing algorithms upto now have been designed and optimized…

This work investigates the framework and performance issues of the composite neural network, which is composed of a collection of pre-trained and non-instantiated neural network models connected as a rooted directed acyclic graph for…

In this paper, we address the problem of global-scale image geolocation, proposing a mixed classification-retrieval scheme. Unlike other methods that strictly tackle the problem as a classification or retrieval task, we combine the two…

We propose a vision-based architecture search algorithm for robot manipulation learning, which discovers interactions between low dimension action inputs and high dimensional visual inputs. Our approach automatically designs architectures…

Algorithms based on deep network models are being used for many pattern recognition and decision-making tasks in robotics and AI. Training these models requires a large labeled dataset and considerable computational resources, which are not…

In this paper we aim to determine the location and orientation of a ground-level query image by matching to a reference database of overhead (e.g. satellite) images. For this task we collect a new dataset with one million pairs of street…