相关论文: Evaluating the Use of Reconstruction Error for Nov…

How can we detect anomalies: that is, samples that significantly differ from a given set of high-dimensional data, such as images or sensor data? This is a practical problem with numerous applications and is also relevant to the goal of…

Saliency maps have become a widely used method to assess which areas of the input image are most pertinent to the prediction of a trained neural network. However, in the context of medical imaging, there is no study to our knowledge that…

The success of modern deep learning algorithms for image segmentation heavily depends on the availability of large datasets with clean pixel-level annotations (masks), where the objects of interest are accurately delineated. Lack of time…

The task of large-scale retrieval-based image localization is to estimate the geographical location of a query image by recognizing its nearest reference images from a city-scale dataset. However, the general public benchmarks only provide…

We propose a lossy image compression system using the deep-learning autoencoder structure to participate in the Challenge on Learned Image Compression (CLIC) 2018. Our autoencoder uses the residual blocks with skip connections to reduce the…

Recent advances in saliency detection have utilized deep learning to obtain high level features to detect salient regions in a scene. These advances have demonstrated superior results over previous works that utilize hand-crafted low level…

Recent advances in image-based saliency prediction are approaching gold standard performance levels on existing benchmarks. Despite this success, we show that predicting fixations across multiple saliency datasets remains challenging due to…

Novelty detection using deep generative models such as autoencoder, generative adversarial networks mostly takes image reconstruction error as novelty score function. However, image data, high dimensional as it is, contains a lot of…

Saliency maps that identify the most informative regions of an image for a classifier are valuable for model interpretability. A common approach to creating saliency maps involves generating input masks that mask out portions of an image to…

Saliency methods have emerged as a popular tool to highlight features in an input deemed relevant for the prediction of a learned model. Several saliency methods have been proposed, often guided by visual appeal on image data. In this work,…

Besides per-pixel accuracy, topological correctness is also crucial for the segmentation of images with fine-scale structures, e.g., satellite images and biomedical images. In this paper, by leveraging the theory of digital topology, we…

Omni-directional images have been used in wide range of applications. For the applications, it would be useful to estimate saliency maps representing probability distributions of gazing points with a head-mounted display, to detect…

Salient object detection has become an important task in many image processing applications. The existing approaches exploit background prior and contrast prior to attain state of the art results. In this paper, instead of using background…

A major focus of recent developments in stereo vision has been on how to obtain accurate dense disparity maps in passive stereo vision. Active vision systems enable more accurate estimations of dense disparity compared to passive stereo.…

Salient object detection, which aims to identify and locate the most salient pixels or regions in images, has been attracting more and more interest due to its various real-world applications. However, this vision task is quite challenging,…

Visual localization is the problem of estimating a camera within a scene and a key component in computer vision applications such as self-driving cars and Mixed Reality. State-of-the-art approaches for accurate visual localization use…

Weakly supervised localization aims at finding target object regions using only image-level supervision. However, localization maps extracted from classification networks are often not accurate due to the lack of fine pixel-level…

Image super-resolution (SR) techniques have been developing rapidly, benefiting from the invention of deep networks and its successive breakthroughs. However, it is acknowledged that deep learning and deep neural networks are difficult to…

The performance of convolutional neural networks has continued to improve over the last decade. At the same time, as model complexity grows, it becomes increasingly more difficult to explain model decisions. Such explanations may be of…

Encoder-decoder networks have found widespread use in various dense prediction tasks. However, the strong reduction of spatial resolution in the encoder leads to a loss of location information as well as boundary artifacts. To address this,…