Related papers: Uncertainty-Aware Decomposed Hybrid Networks

Image decomposition is a crucial subject in the field of image processing. It can extract salient features from the source image. We propose a new image decomposition method based on convolutional neural network. This method can be applied…

Neural networks have greatly boosted performance in computer vision by learning powerful representations of input data. The drawback of end-to-end training for maximal overall performance are black-box models whose hidden representations…

Image dehazing is fundamental yet not well-solved in computer vision. Most cutting-edge models are trained in synthetic data, leading to the poor performance on real-world hazy scenarios. Besides, they commonly give deterministic dehazed…

There are two main algorithmic approaches to autonomous driving systems: (1) An end-to-end system in which a single deep neural network learns to map sensory input directly into appropriate warning and driving responses. (2) A mediated…

Deep convolutional neural networks (CNNs) have delivered superior performance in many computer vision tasks. In this paper, we propose a novel deep fully convolutional network model for accurate salient object detection. The key…

As image recognition models become more prevalent, scalable coding methods for machines and humans gain more importance. Applications of image recognition models include traffic monitoring and farm management. In these use cases, the…

Navigation in natural outdoor environments requires a robust and reliable traversability classification method to handle the plethora of situations a robot can encounter. Binary classification algorithms perform well in their native domain…

The mainstream human activity recognition (HAR) algorithms are developed based on RGB cameras, which are easily influenced by low-quality images (e.g., low illumination, motion blur). Meanwhile, the privacy protection issue caused by…

A key strategy for balancing performance and cost in modern machine learning systems is to dynamically route queries to either a low-cost model or a more expensive oracle (such as a large pretrained model or human expert), an approach known…

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…

Although neural networks have seen tremendous success as predictive models in a variety of domains, they can be overly confident in their predictions on out-of-distribution (OOD) data. To be viable for safety-critical applications, like…

Robustness verification that aims to formally certify the prediction behavior of neural networks has become an important tool for understanding model behavior and obtaining safety guarantees. However, previous methods can usually only…

The great performance of machine learning algorithms and deep neural networks in several perception and control tasks is pushing the industry to adopt such technologies in safety-critical applications, as autonomous robots and self-driving…

Time series anomaly detection is important in modern large-scale systems and is applied in a variety of domains to analyze and monitor the operation of diverse systems. Unsupervised approaches have received widespread interest, as they do…

Dense image alignment from RGB-D images remains a critical issue for real-world applications, especially under challenging lighting conditions and in a wide baseline setting. In this paper, we propose a new framework to learn a pixel-wise…

Neural representations have emerged as a new paradigm for applications in rendering, imaging, geometric modeling, and simulation. Compared to traditional representations such as meshes, point clouds, or volumes they can be flexibly…

Deep networks for computer vision are not reliable when they encounter adversarial examples. In this paper, we introduce a framework that uses the dense intrinsic constraints in natural images to robustify inference. By introducing…

We propose a novel intrinsic image decomposition network considering reflectance consistency. Intrinsic image decomposition aims to decompose an image into illumination-invariant and illumination-variant components, referred to as…

Image reconstruction methods based on deep neural networks have shown outstanding performance, equalling or exceeding the state-of-the-art results of conventional approaches, but often do not provide uncertainty information about the…

Traffic signs play a critical role in road safety and traffic management for autonomous driving systems. Accurate traffic sign classification is essential but challenging due to real-world complexities like adversarial examples and…