Related papers: Formal Verification of CNN-based Perception System…

Understanding how cities visually differ from each others is interesting for planners, residents, and historians. We investigate the interpretation of deep features learned by convolutional neural networks (CNNs) for city recognition. Given…

Among the image forensic issues investigated in the last few years, great attention has been devoted to blind camera model attribution. This refers to the problem of detecting which camera model has been used to acquire an image by only…

The huge amount of available data nowadays is a challenge for kernel-based machine learning algorithms like SVMs with respect to runtime and storage capacities. Local approaches might help to relieve these issues and to improve statistical…

In parallel with the success of CNNs to solve vision problems, there is a growing interest in developing methodologies to understand and visualize the internal representations of these networks. How the responses of a trained CNN encode the…

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…

Formal verification is only as good as the specification of a system, which is also true for neural network verification. Existing specifications follow the paradigm of data as specification, where the local neighborhood around a reference…

In this paper, we study the sensitivity of CNN outputs with respect to image transformations and noise in the area of fine-grained recognition. In particular, we answer the following questions (1) how sensitive are CNNs with respect to…

Convolutional neural networks (CNNs) are commonly used for image classification. Saliency methods are examples of approaches that can be used to interpret CNNs post hoc, identifying the most relevant pixels for a prediction following the…

Convolutional neural networks (CNNs) achieve translational invariance by using pooling operations. However, the operations do not preserve the spatial relationships in the learned representations. Hence, CNNs cannot extrapolate to various…

The Convolutional Neural Networks (CNNs) have emerged as a very powerful data dependent hierarchical feature extraction method. It is widely used in several computer vision problems. The CNNs learn the important visual features from…

Deep learning has transformed the way we think of software and what it can do. But deep neural networks are fragile and their behaviors are often surprising. In many settings, we need to provide formal guarantees on the safety, security,…

Convolutional Neural Networks (CNN) has been widely applied in the realm of computer vision. However, given the fact that CNN models are translation invariant, they are not aware of the coordinate information of each pixel. Thus the…

Recent years have witnessed the emergence of a variety of post-hoc interpretations that aim to uncover how natural language processing (NLP) models make predictions. Despite the surge of new interpretation methods, it remains an open…

Image Recognition is a central task in computer vision with applications ranging across search, robotics, self-driving cars and many others. There are three purposes of this document: 1. We follow up on (Fischetti & Jo, December, 2017) and…

The use of neural networks for diagnosis classification is becoming more and more prevalent in the medical imaging community. However, deep learning method outputs remain hard to explain. Another difficulty is to choose among the large…

In this paper we investigate formal verification problems for Neural Network computations. Of central importance will be various robustness and minimization problems such as: Given symbolic specifications of allowed inputs and outputs in…

Convolutional Neural Networks (CNN) for object detection, lane detection, and segmentation now sit at the head of most autonomy pipelines, and yet, their safety analysis remains an important challenge. Formal analysis of perception models…

A major prerequisite for the application of machine learning models in clinical decision making is trust and interpretability. Current explainability studies in the neuroimaging community have mostly focused on explaining individual…

Connectivity and controllability of a complex network are two important issues that guarantee a networked system to function. Robustness of connectivity and controllability guarantees the system to function properly and stably under various…

Convolutional neural networks (CNNs) are similar to "ordinary" neural networks in the sense that they are made up of hidden layers consisting of neurons with "learnable" parameters. These neurons receive inputs, performs a dot product, and…