Related papers: Preventing Model Collapse in Deep Canonical Correl…

Describing the dimension reduction (DR) techniques by means of probabilistic models has recently been given special attention. Probabilistic models, in addition to a better interpretability of the DR methods, provide a framework for further…

Robust classification becomes challenging when each class consists of multiple subclasses. Examples include multi-font optical character recognition and automated protein function prediction. In correlation-based nearest-neighbor…

Neural collapse (NC) refers to the surprising structure of the last layer of deep neural networks in the terminal phase of gradient descent training. Recently, an increasing amount of experimental evidence has pointed to the propagation of…

Healthcare data often come from multiple sites in which the correlations between confounding variables can vary widely. If deep learning models exploit these unstable correlations, they might fail catastrophically in unseen sites. Although…

Recently proposed automatic pathological speech detection approaches rely on spectrogram input representations or wav2vec2 embeddings. These representations may contain pathology irrelevant uncorrelated information, such as changing…

Self-supervised visual representation learning aims to learn useful representations without relying on human annotations. Joint embedding approach bases on maximizing the agreement between embedding vectors from different views of the same…

This study addresses a key limitation in deep learning Automatic Modulation Classification (AMC) models, which perform well at high signal-to-noise ratios (SNRs) but degrade under noisy conditions due to conventional feature extraction…

Computer models play a key role in many scientific and engineering problems. One major source of uncertainty in computer model experiment is input parameter uncertainty. Computer model calibration is a formal statistical procedure to infer…

Multi-view subspace learning (MSL) aims to find a low-dimensional subspace of the data obtained from multiple views. Different from single view case, MSL should take both common and specific knowledge among different views into…

Inverse problems are inherently ill-posed, suffering from non-uniqueness and instability. Classical regularization methods provide mathematically well-founded solutions, ensuring stability and convergence, but often at the cost of reduced…

Multiview canonical correlation analysis (MCCA) seeks latent low-dimensional representations encountered with multiview data of shared entities (a.k.a. common sources). However, existing MCCA approaches do not exploit the geometry of the…

The current learning process of deep learning, regardless of any deep neural network (DNN) architecture and/or learning algorithm used, is essentially a single resolution training. We explore multiresolution learning and show that…

Large training datasets almost always contain examples with inaccurate or incorrect labels. Deep Neural Networks (DNNs) tend to overfit training label noise, resulting in poorer model performance in practice. To address this problem, we…

Deep neural networks (DNNs) fail to learn effectively under label noise and have been shown to memorize random labels which affect their generalization performance. We consider learning in isolation, using one-hot encoded labels as the sole…

Deep convolutional neural networks (DCNNs) are powerful models that yield impressive results at object classification. However, recent work has shown that they do not generalize well to partially occluded objects and to mask attacks. In…

Recognising detailed facial or clothing attributes in images of people is a challenging task for computer vision, especially when the training data are both in very large scale and extremely imbalanced among different attribute classes. To…

Discriminative Canonical Correlation Analysis (DCCA) is a powerful supervised feature extraction technique for two sets of multivariate data, which has wide applications in pattern recognition. DCCA consists of two parts: (i) mean-centering…

The visual-question localized-answering (VQLA) system can serve as a knowledgeable assistant in surgical education. Except for providing text-based answers, the VQLA system can highlight the interested region for better surgical scene…

Robot manipulation relying on learned object-centric descriptors became popular in recent years. Visual descriptors can easily describe manipulation task objectives, they can be learned efficiently using self-supervision, and they can…

We present a unified theoretical framework connecting the first property of Deep Neural Collapse (DNC1) to the emergence of implicit low-rank bias in nonlinear networks trained with $L^2$ weight decay regularization. Our main contributions…