Related papers: Quantifying the Variability Collapse of Neural Net…

As an emerging field in Machine Learning, Explainable AI (XAI) has been offering remarkable performance in interpreting the decisions made by Convolutional Neural Networks (CNNs). To achieve visual explanations for CNNs, methods based on…

This paper uses the peridynamic theory, which is well-suited to crack studies, to predict the crack patterns in a moving disk and classify them according to the modes and finally perform regression analysis. In that way, the crack patterns…

In recent years, the rapid development of deep learning technology has brought new prospects to the field of vulnerability detection. Many vulnerability detection methods involve converting source code into images for detection, yet they…

Deep neural networks have achieved impressive performance on a variety of tasks, but their brittleness to distributional shifts remains a significant barrier to real-world deployment. In this paper, we propose a framework to analyse and…

Quantization is an essential step in the efficient deployment of deep learning models and as such is an increasingly popular research topic. An important practical aspect that is not addressed in the current literature is how to analyze and…

We scrutinize the structural and operational aspects of deep learning models, particularly focusing on the nuances of learnable parameters (weight) statistics, distribution, node interaction, and visualization. By establishing correlations…

Label smoothing loss is a widely adopted technique to mitigate overfitting in deep neural networks. This paper studies label smoothing from the perspective of Neural Collapse (NC), a powerful empirical and theoretical framework which…

In networks of independent entities that face similar predictive tasks, transfer machine learning enables to re-use and improve neural nets using distributed data sets without the exposure of raw data. As the number of data sets in business…

Saliency detection has been widely studied because it plays an important role in various vision applications, but it is difficult to evaluate saliency systems because each measure has its own bias. In this paper, we first revisit the…

Classical wisdom in machine learning holds that the generalization error can be decomposed into bias and variance, and these two terms exhibit a \emph{trade-off}. However, in this paper, we show that for an ensemble of deep learning based…

Comparing different neural network representations and determining how representations evolve over time remain challenging open questions in our understanding of the function of neural networks. Comparing representations in neural networks…

Alignment, the tendency of adjacent weight matrices in deep networks to develop compatible subspace orientations, underlies gradient flow, Neural Collapse, and representation similarity across architectures. Despite extensive empirical…

Robustness to small image translations is a highly desirable property for object detectors. However, recent works have shown that CNN-based classifiers are not shift invariant. It is unclear to what extent this could impact object…

Neural collapse is an emergent phenomenon in deep learning that was recently discovered by Papyan, Han and Donoho. We propose a simple "unconstrained features model" in which neural collapse also emerges empirically. By studying this model,…

In recent years, deep architectures have been used for transfer learning with state-of-the-art performance in many datasets. The properties of their features remain, however, largely unstudied under the transfer perspective. In this work,…

Recently, visual perception (VP) and visual imagery (VI) paradigms are investigated in several brain-computer interface (BCI) studies. VP and VI are defined as a changing of brain signals when perceiving and memorizing visual information,…

Deep convolutional classifiers linearly separate image classes and improve accuracy as depth increases. They progressively reduce the spatial dimension whereas the number of channels grows with depth. Spatial variability is therefore…

Various work has suggested that the memorability of an image is consistent across people, and thus can be treated as an intrinsic property of an image. Using computer vision models, we can make specific predictions about what people will…

Deep convolutional neural networks (CNNs) trained on objects and scenes have shown intriguing ability to predict some response properties of visual cortical neurons. However, the factors and computations that give rise to such ability, and…

Neurons in the visual cortex are correlated in their variability. The presence of correlation impacts cortical processing because noise cannot be averaged out over many neurons. In an effort to understand the functional purpose of…