Related papers: VisualBackProp: efficient visualization of CNNs
In recent years, image forensics has attracted more and more attention, and many forensic methods have been proposed for identifying image processing operations. Up to now, most existing methods are based on hand crafted features, and just…
Model pruning has become a useful technique that improves the computational efficiency of deep learning, making it possible to deploy solutions in resource-limited scenarios. A widely-used practice in relevant work assumes that a…
This paper presents a new variational inference framework for image restoration and a convolutional neural network (CNN) structure that can solve the restoration problems described by the proposed framework. Earlier CNN-based image…
In this paper, we present a novel approach for contour detection with Convolutional Neural Networks. A multi-scale CNN learning framework is designed to automatically learn the most relevant features for contour patch detection. Our method…
We propose a novel approach to image classification inspired by complex nonlinear biological visual processing, whereby classical convolutional neural networks (CNNs) are equipped with learnable higher-order convolutions. Our model…
This paper presents a novel approach to increase the performance bounds of image steganography under the criteria of minimizing distortion. The proposed approach utilizes a steganalysis convolutional neural network (CNN) framework to…
We introduce the concept of "dynamic image", a novel compact representation of videos useful for video analysis, particularly in combination with convolutional neural networks (CNNs). A dynamic image encodes temporal data such as RGB or…
This paper describes a novel approach to perform vehicle trajectory predictions employing graphic representations. The vehicles are represented using Gaussian distributions into a Bird Eye View. Then the U-net model is used to perform…
Convolutional Neural Networks (CNN) have redefined the state-of-the-art in many real-world applications, such as facial recognition, image classification, human pose estimation, and semantic segmentation. Despite their success, CNNs are…
We present an approach to utilize large amounts of web data for learning CNNs. Specifically inspired by curriculum learning, we present a two-step approach for CNN training. First, we use easy images to train an initial visual…
We propose a novel deep-learning-based system for vessel segmentation. Existing methods using CNNs have mostly relied on local appearances learned on the regular image grid, without considering the graphical structure of vessel shape. To…
We propose a technique for producing "visual explanations" for decisions from a large class of CNN-based models, making them more transparent. Our approach - Gradient-weighted Class Activation Mapping (Grad-CAM), uses the gradients of any…
In the Internet, ubiquitous presence of redundant, unedited, raw videos has made video summarization an important problem. Traditional methods of video summarization employ a heuristic set of hand-crafted features, which in many cases fail…
In this work, we present a novel background subtraction system that uses a deep Convolutional Neural Network (CNN) to perform the segmentation. With this approach, feature engineering and parameter tuning become unnecessary since the…
Convolutional Neural Networks (CNNs) have recently emerged as the dominant model in computer vision. If provided with enough training data, they predict almost any visual quantity. In a discrete setting, such as classification, CNNs are not…
CNNs have excelled at performing place recognition over time, particularly when the neural network is optimized for localization in the current environmental conditions. In this paper we investigate the concept of feature map filtering,…
Vision-transformers (ViTs) and large-scale convolution-neural-networks (CNNs) have reshaped computer vision through pretrained feature representations that enable strong transfer learning for diverse tasks. However, their efficiency as…
In this paper we evaluate the quality of the activation layers of a convolutional neural network (CNN) for the gen- eration of object proposals. We generate hypotheses in a sliding-window fashion over different activation layers and show…
Convolutional neural networks (CNNs) are one of the driving forces for the advancement of computer vision. Despite their promising performances on many tasks, CNNs still face major obstacles on the road to achieving ideal machine…
The ability to automatically detect certain types of cells or cellular subunits in microscopy images is of significant interest to a wide range of biomedical research and clinical practices. Cell detection methods have evolved from…