相关论文: A Study on the Generality of Neural Network Struct…

End-to-end automatic speech recognition systems have achieved great accuracy by using deeper and deeper models. However, the increased depth comes with a larger receptive field that can negatively impact model performance in streaming…

Graph neural networks (GNNs) have received tremendous attention due to their superiority in learning node representations. These models rely on message passing and feature transformation functions to encode the structural and feature…

Monocular depth estimation is one of the fundamental tasks in environmental perception and has achieved tremendous progress in virtue of deep learning. However, the performance of trained models tends to degrade or deteriorate when employed…

Convolutional neural networks (CNNs) achieved the state-of-the-art performance in medical image segmentation due to their ability to extract highly complex feature representations. However, it is argued in recent studies that traditional…

We revisit the problem of visual depth estimation in the context of autonomous vehicles. Despite the progress on monocular depth estimation in recent years, we show that the gap between monocular and stereo depth accuracy remains large$-$a…

Transformers have attracted increasing interests in computer vision, but they still fall behind state-of-the-art convolutional networks. In this work, we show that while Transformers tend to have larger model capacity, their generalization…

Depth estimation is an important task in various robotics systems and applications. In mobile robotics systems, monocular depth estimation is desirable since a single RGB camera can be deployable at a low cost and compact size. Due to its…

Depth estimation is an active area of research in the field of computer vision, and has garnered significant interest due to its rising demand in a large number of applications ranging from robotics and unmanned aerial vehicles to…

Convolutional Neural Networks (CNNs) exhibit a well-known texture bias, prioritizing local patterns over global shapes - a tendency inherent to their convolutional architecture. While this bias is beneficial for texture-rich natural images,…

Depth estimation from a single image is an important task that can be applied to various fields in computer vision, and has grown rapidly with the development of convolutional neural networks. In this paper, we propose a novel structure and…

In this paper we consider the problem of single monocular image depth estimation. It is a challenging problem due to its ill-posedness nature and has found wide application in industry. Previous efforts belongs roughly to two families:…

Increasingly more similarities between human vision and convolutional neural networks (CNNs) have been revealed in the past few years. Yet, vanilla CNNs often fall short in generalizing to adversarial or out-of-distribution (OOD) examples…

Thanks to the excellent learning capability of deep convolutional neural networks (CNN), monocular depth estimation using CNNs has achieved great success in recent years. However, depth estimation from a monocular image alone is essentially…

Currently, increasingly deeper neural networks have been applied to improve their accuracy. In contrast, We propose a novel wider Convolutional Neural Networks (CNN) architecture, motivated by the Multi-column Deep Neural Networks and the…

The compositional generalization abilities of neural models have been sought after for human-like linguistic competence. The popular method to evaluate such abilities is to assess the models' input-output behavior. However, that does not…

With the substantial performance of neural networks in sensitive fields increases the need for interpretable deep learning models. Major challenge is to uncover the multiscale and distributed representation hidden inside the basket mappings…

This paper reviews recent studies in understanding neural-network representations and learning neural networks with interpretable/disentangled middle-layer representations. Although deep neural networks have exhibited superior performance…

While learning based depth estimation from images/videos has achieved substantial progress, there still exist intrinsic limitations. Supervised methods are limited by a small amount of ground truth or labeled data and unsupervised methods…

Successful training of convolutional neural networks is often associated with sufficiently deep architectures composed of high amounts of features. These networks typically rely on a variety of regularization and pruning techniques to…

Given the recent advances in depth prediction from Convolutional Neural Networks (CNNs), this paper investigates how predicted depth maps from a deep neural network can be deployed for accurate and dense monocular reconstruction. We propose…