Related papers: Design of Supervision-Scalable Learning Systems: M…

Existing deep neural networks, say for image classification, have been shown to be vulnerable to adversarial images that can cause a DNN misclassification, without any perceptible change to an image. In this work, we propose shock absorbing…

Unsupervised learning permits the development of algorithms that are able to adapt to a variety of different data sets using the same underlying rules thanks to the autonomous discovery of discriminating features during training. Recently,…

Incorporating heterogeneous representations from different architectures has facilitated various vision tasks, e.g., some hybrid networks combine transformers and convolutions. However, complementarity between such heterogeneous…

Discriminative self-supervised learning allows training models on any random group of internet images, and possibly recover salient information that helps differentiate between the images. Applied to ImageNet, this leads to object centric…

Self-supervised contrastive learning is an effective approach for addressing the challenge of limited labelled data. This study builds upon the previously established two-stage patch-level, multi-label classification method for…

A continual learning (CL) algorithm learns from a non-stationary data stream. The non-stationarity is modeled by some schedule that determines how data is presented over time. Most current methods make strong assumptions on the schedule and…

Neural networks are vulnerable to adversarial attacks, i.e., small input perturbations can significantly affect the outputs of a neural network. Therefore, to ensure safety of neural networks in safety-critical environments, the robustness…

As the volume of digital image data increases, the effectiveness of image classification intensifies. This study introduces a robust multi-label classification system designed to assign multiple labels to a single image, addressing the…

As audio-visual systems are being deployed for safety-critical tasks such as surveillance and malicious content filtering, their robustness remains an under-studied area. Existing published work on robustness either does not scale to…

Machine learning (ML) systems have introduced significant advances in various fields, due to the introduction of highly complex models. Despite their success, it has been shown multiple times that machine learning models are prone to…

Classic algorithms and machine learning systems like neural networks are both abundant in everyday life. While classic computer science algorithms are suitable for precise execution of exactly defined tasks such as finding the shortest path…

Achieving robustness against adversarial input perturbation is an important and intriguing problem in machine learning. In the area of semantic image segmentation, a number of adversarial training approaches have been proposed as a defense…

With the advent of vision-language models (VLMs) that can perform in-context and prompt-based learning, how can we design prompting approaches that robustly generalize to distribution shift and can be used on novel classes outside the…

Inspired by the work of Tsiamis et al. \cite{tsiamis2022learning}, in this paper we study the statistical hardness of learning to stabilize linear time-invariant systems. Hardness is measured by the number of samples required to achieve a…

Deep neural networks have demonstrated high accuracy in image classification tasks. However, they were shown to be weak against adversarial examples: a small perturbation in the image which changes the classification output dramatically. In…

In many applications, training machine learning models involves using large amounts of human-annotated data. Obtaining precise labels for the data is expensive. Instead, training with weak supervision provides a low-cost alternative. We…

In this dissertation we study statistical and online learning problems from an optimization viewpoint.The dissertation is divided into two parts : I. We first consider the question of learnability for statistical learning problems in the…

Scribble-based weakly supervised semantic segmentation leverages only a few annotated pixels as labels to train a segmentation model, presenting significant potential for reducing the human labor involved in the annotation process. This…

Self-supervised learning holds promise in leveraging large numbers of unlabeled data. However, its success heavily relies on the highly-curated dataset, e.g., ImageNet, which still needs human cleaning. Directly learning representations…

It has been hypothesized that some form of "modular" structure in artificial neural networks should be useful for learning, compositionality, and generalization. However, defining and quantifying modularity remains an open problem. We cast…