Related papers: Right for the Right Reason: Training Agnostic Netw…

Just like weights, bias terms are the learnable parameters of many popular machine learning models, including neural networks. Biases are thought to enhance the representational power of neural networks, enabling them to solve a variety of…

While deep learning has led to huge progress in complex image classification tasks like ImageNet, unexpected failure modes, e.g. via spurious features, call into question how reliably these classifiers work in the wild. Furthermore, for…

Predictive modeling is increasingly being employed to assist human decision-makers. One purported advantage of replacing or augmenting human judgment with computer models in high stakes settings-- such as sentencing, hiring, policing,…

Fashion understanding is a hot topic in computer vision, with many applications having great business value in the market. Fashion understanding remains a difficult challenge for computer vision due to the immense diversity of garments and…

Adversarial examples raise questions about whether neural network models are sensitive to the same visual features as humans. In this paper, we first detect adversarial examples or otherwise corrupted images based on a class-conditional…

Neural networks achieve the state-of-the-art in image classification tasks. However, they can encode spurious variations or biases that may be present in the training data. For example, training an age predictor on a dataset that is not…

When data is publicly released for human consumption, it is unclear how to prevent its unauthorized usage for machine learning purposes. Successful model training may be preventable with carefully designed dataset modifications, and we…

Systems that perform image manipulation using deep convolutional networks have achieved remarkable realism. Perceptual losses and losses based on adversarial discriminators are the two main classes of learning objectives behind these…

Artificial intelligence systems, which are designed with a capability to learn from the data presented to them, are used throughout society. These systems are used to screen loan applicants, make sentencing recommendations for criminal…

We develop a technique for automatically detecting the classification errors of a pre-trained visual classifier. Our method is agnostic to the form of the classifier, requiring access only to classifier responses to a set of inputs. We…

Neural networks have emerged as powerful tools across various applications, yet their decision-making process often remains opaque, leading to them being perceived as "black boxes." This opacity raises concerns about their interpretability…

Deep Neural Networks (DNNs) are vulnerable to adversarial attacks: carefully constructed perturbations to an image can seriously impair classification accuracy, while being imperceptible to humans. While there has been a significant amount…

Neural networks have a number of shortcomings. Amongst the severest ones is the sensitivity to distribution shifts which allows models to be easily fooled into wrong predictions by small perturbations to inputs that are often imperceivable…

Unlike traditional learning to rank models that depend on hand-crafted features, neural representation learning models learn higher level features for the ranking task by training on large datasets. Their ability to learn new features…

Neural network architectures have been extensively employed in the fair representation learning setting, where the objective is to learn a new representation for a given vector which is independent of sensitive information. Various…

Often in language and other areas of cognition, whether two components of an object are identical or not determines if it is well formed. We call such constraints identity effects. When developing a system to learn well-formedness from…

Recently, a method [7] was proposed to generate contrastive explanations for differentiable models such as deep neural networks, where one has complete access to the model. In this work, we propose a method, Model Agnostic Contrastive…

In decision making tasks under uncertainty, humans display characteristic biases in seeking, integrating, and acting upon information relevant to the task. Here, we reexamine data from previous carefully designed experiments, collected at…

Neural networks have emerged as powerful tools across various applications, yet their decision-making process often remains opaque, leading to them being perceived as "black boxes." This opacity raises concerns about their interpretability…

We consider end-to-end learning approaches for inverse problems of gravimetry. Due to ill-posedness of the inverse gravimetry, the reliability of learning approaches is questionable. To deal with this problem, we propose the strategy of…