Related papers: Enhancing Multi-view Open-set Learning via Ambigui…
Model explanations such as saliency maps can improve user trust in AI by highlighting important features for a prediction. However, these become distorted and misleading when explaining predictions of images that are subject to systematic…
Recently, there has been a growing interest in developing machine learning (ML) models that can promote fairness, i.e., eliminating biased predictions towards certain populations (e.g., individuals from a specific demographic group). Most…
In most works on deep incremental learning research, it is assumed that novel samples are pre-identified for neural network retraining. However, practical deep classifiers often misidentify these samples, leading to erroneous predictions.…
From uncertainty quantification to real-world object detection, we recognize the importance of machine learning algorithms, particularly in safety-critical domains such as autonomous driving or medical diagnostics. In machine learning,…
We study the understanding of deep neural networks from the scope in which they are trained on. While the accuracy of these models is usually impressive on the aggregate level, they still make mistakes, sometimes on cases that appear to be…
In open-set recognition, existing methods generally learn statically fixed decision boundaries using known classes to reject unknown classes. Though they have achieved promising results, such decision boundaries are evidently insufficient…
Deep neural networks are highly susceptible to learning biases in visual data. While various methods have been proposed to mitigate such bias, the majority require explicit knowledge of the biases present in the training data in order to…
We present a unified framework for studying the identifiability of representations learned from simultaneously observed views, such as different data modalities. We allow a partially observed setting in which each view constitutes a…
Deep learning models have become increasingly useful in many different industries. On the domain of image classification, convolutional neural networks proved the ability to learn robust features for the closed set problem, as shown in many…
Given the complexities inherent in visual scenes, such as object occlusion, a comprehensive understanding often requires observation from multiple viewpoints. Existing multi-viewpoint object-centric learning methods typically employ random…
Novel-view synthesis through diffusion models has demonstrated remarkable potential for generating diverse and high-quality images. Yet, the independent process of image generation in these prevailing methods leads to challenges in…
Model explanations such as saliency maps can improve user trust in AI by highlighting important features for a prediction. However, these become distorted and misleading when explaining predictions of images that are subject to systematic…
Vision systems trained in closed-world scenarios fail when presented with new environmental conditions, new data distributions, and novel classes at deployment time. How to move towards open-world learning is a long-standing research…
Contrastive self-supervised learning has attracted significant research attention recently. It learns effective visual representations from unlabeled data by embedding augmented views of the same image close to each other while pushing away…
In this thesis, we address the challenging problem of unpaired multi-view clustering (UMC), which aims to achieve effective joint clustering using unpaired samples observed across multiple views. Traditional incomplete multi-view clustering…
As a concrete application of multi-view learning, multi-view classification improves the traditional classification methods significantly by integrating various views optimally. Although most of the previous efforts have been demonstrated…
This paper identifies the flaws in existing open-world learning approaches and attempts to provide a complete picture in the form of \textbf{True Open-World Learning}. We accomplish this by proposing a comprehensive generalize-able…
As we all know, multi-view data is more expressive than single-view data and multi-label annotation enjoys richer supervision information than single-label, which makes multi-view multi-label learning widely applicable for various pattern…
One of the most promising approaches for unsupervised learning is combining deep representation learning and deep clustering. Some recent works propose to simultaneously learn representation using deep neural networks and perform clustering…
Meta-learning for few-shot learning entails acquiring a prior over previous tasks and experiences, such that new tasks be learned from small amounts of data. However, a critical challenge in few-shot learning is task ambiguity: even when a…