Related papers: Learning to Generate Training Datasets for Robust …
Learning invariant representations is an important requirement when training machine learning models that are driven by spurious correlations in the datasets. These spurious correlations, between input samples and the target labels, wrongly…
Generative Adversarial Nets [8] were recently introduced as a novel way to train generative models. In this work we introduce the conditional version of generative adversarial nets, which can be constructed by simply feeding the data, y, we…
Despite the growing prevalence of artificial neural networks in real-world applications, their vulnerability to adversarial attacks remains a significant concern, which motivates us to investigate the robustness of machine learning models.…
Adversarial examples pose a security threat to many critical systems built on neural networks (such as face recognition systems, and self-driving cars). While many methods have been proposed to build robust models, how to build certifiably…
Semantic segmentation is a computer vision task where classification is performed at a pixel level. Due to this, the process of labeling images for semantic segmentation is time-consuming and expensive. To mitigate this cost there has been…
With the advent of generative adversarial networks, synthesizing images from textual descriptions has recently become an active research area. It is a flexible and intuitive way for conditional image generation with significant progress in…
This paper describes a general, scalable, end-to-end framework that uses the generative adversarial network (GAN) objective to enable robust speech recognition. Encoders trained with the proposed approach enjoy improved invariance by…
Most contemporary robots have depth sensors, and research on semantic segmentation with RGBD images has shown that depth images boost the accuracy of segmentation. Since it is time-consuming to annotate images with semantic labels per…
We cannot guarantee that training datasets are representative of the distribution of inputs that will be encountered during deployment. So we must have confidence that our models do not over-rely on this assumption. To this end, we…
The detection of computer-generated text is an area of rapidly increasing significance as nascent generative models allow for efficient creation of compelling human-like text, which may be abused for the purposes of spam, disinformation,…
Semantic segmentation of medical images is pivotal in applications like disease diagnosis and treatment planning. While deep learning has excelled in automating this task, a major hurdle is the need for numerous annotated segmentation…
Adversarial training has been actively studied in recent computer vision research to improve the robustness of models. However, due to the huge computational cost of generating adversarial samples, adversarial training methods are often…
Existing weakly or semi-supervised semantic segmentation methods utilize image or box-level supervision to generate pseudo-labels for weakly labeled images. However, due to the lack of strong supervision, the generated pseudo-labels are…
Adversarial training is a widely-applied approach to training deep neural networks to be robust against adversarial perturbation. However, although adversarial training has achieved empirical success in practice, it still remains unclear…
The performance of deep segmentation models often degrades due to distribution shifts in image intensities between the training and test data sets. This is particularly pronounced in multi-centre studies involving data acquired using…
A variety of real-world tasks involve the classification of images into pre-determined categories. Designing image classification algorithms that exhibit robustness to acquisition noise and image distortions, particularly when the available…
Neural networks achieve outstanding accuracy in classification and regression tasks. However, understanding their behavior still remains an open challenge that requires questions to be addressed on the robustness, explainability and…
Performance achievable by modern deep learning approaches are directly related to the amount of data used at training time. Unfortunately, the annotation process is notoriously tedious and expensive, especially for pixel-wise tasks like…
Throughout the past five years, the susceptibility of neural networks to minimal adversarial perturbations has moved from a peculiar phenomenon to a core issue in Deep Learning. Despite much attention, however, progress towards more robust…
The reliability of segmentation models in the medical domain depends on the model's robustness to perturbations in the input space. Robustness is a particular challenge in medical imaging exhibiting various sources of image noise,…