Related papers: Visualizing Deep Networks by Optimizing with Integ…
Computing the gradients of a rendering process is paramount for diverse applications in computer vision and graphics. However, accurate computation of these gradients is challenging due to discontinuities and rendering approximations,…
Recently, heatmap regression has been widely explored in facial landmark detection and obtained remarkable performance. However, most of the existing heatmap regression-based facial landmark detection methods neglect to explore the…
We study deep learning approaches to inferring numerical coordinates for points of interest in an input image. Existing convolutional neural network-based solutions to this problem either take a heatmap matching approach or regress to…
Human pose estimation using deep neural networks aims to map input images with large variations into multiple body keypoints which must satisfy a set of geometric constraints and inter-dependency imposed by the human body model. This is a…
Human pose estimation - the process of recognizing human keypoints in a given image - is one of the most important tasks in computer vision and has a wide range of applications including movement diagnostics, surveillance, or self-driving…
Estimating a depth map from a single RGB image has been investigated widely for localization, mapping, and 3-dimensional object detection. Recent studies on a single-view depth estimation are mostly based on deep Convolutional neural…
Deep neural networks have dramatically advanced the state of the art for many areas of machine learning. Recently they have been shown to have a remarkable ability to generate highly complex visual artifacts such as images and text rather…
We propose a novel method that makes use of deep neural networks and gradient decent to perform automated design on complex real world engineering tasks. Our approach works by training a neural network to mimic the fitness function of a…
This paper introduces a novel approach for image and video orientation estimation by leveraging depth distribution in natural images. The proposed method estimates the orientation based on the depth distribution across different quadrants…
This work presents a new approach based on deep learning to automatically extract colormaps from visualizations. After summarizing colors in an input visualization image as a Lab color histogram, we pass the histogram to a pre-trained deep…
Image smoothing is a fundamental low-level vision task that aims to preserve salient structures of an image while removing insignificant details. Deep learning has been explored in image smoothing to deal with the complex entanglement of…
Class activation map (CAM) helps to formulate saliency maps that aid in interpreting the deep neural network's prediction. Gradient-based methods are generally faster than other branches of vision interpretability and independent of human…
Targeting at depicting land covers with pixel-wise semantic categories, semantic segmentation in remote sensing images needs to portray diverse distributions over vast geographical locations, which is difficult to be achieved by the…
Explaining the output of a deep network remains a challenge. In the case of an image classifier, one type of explanation is to identify pixels that strongly influence the final decision. A starting point for this strategy is the gradient of…
Given a grid terrain T and a viewpoint v, the viewshed of v is the set of grid points of T that are visible from v. To decide whether a point p is visible one needs to interpolate the elevation of the terrain along the line-of-sight vp.…
The accurate localization of facial landmarks is at the core of face analysis tasks, such as face recognition and facial expression analysis, to name a few. In this work, we propose a novel localization approach based on a deep learning…
Explaining deep learning models in a way that humans can easily understand is essential for responsible artificial intelligence applications. Attribution methods constitute an important area of explainable deep learning. The attribution…
We propose a deep representation of appearance, i. e., the relation of color, surface orientation, viewer position, material and illumination. Previous approaches have useddeep learning to extract classic appearance representationsrelating…
We consider image classification with estimated depth. This problem falls into the domain of transfer learning, since we are using a model trained on a set of depth images to generate depth maps (additional features) for use in another…
Gradients have been used to quantify feature importance in machine learning models. Unfortunately, in nonlinear deep networks, not only individual neurons but also the whole network can saturate, and as a result an important input feature…