Related papers: Prior Activation Distribution (PAD): A Versatile R…

Plasticity loss, a critical challenge in neural network training, limits a model's ability to adapt to new tasks or shifts in data distribution. This paper introduces AID (Activation by Interval-wise Dropout), a novel method inspired by…

Gradient-based neural network training traditionally enforces symmetry between forward and backward propagation, requiring activation functions to be differentiable (or sub-differentiable) and strictly monotonic in certain regions to…

Standard deep neural networks (DNNs) are commonly trained in an end-to-end fashion for specific tasks such as object recognition, face identification, or character recognition, among many examples. This specificity often leads to…

Human Activity Recognition (HAR) is a challenging problem that needs advanced solutions than using handcrafted features to achieve a desirable performance. Deep learning has been proposed as a solution to obtain more accurate HAR systems…

In this paper, we introduce Masked Anomaly Detection (MAD), a general self-supervised learning task for multivariate time series anomaly detection. With the increasing availability of sensor data from industrial systems, being able to…

Ear recognition system has been widely studied whereas there are just a few ear presentation attack detection methods for ear recognition systems, consequently, there is no publicly available ear presentation attack detection (PAD)…

Anomaly detection (AD) is a crucial machine learning task that aims to learn patterns from a set of normal training samples to identify abnormal samples in test data. Most existing AD studies assume that the training and test data are drawn…

Recent advancements in on-device training for deep neural networks have underscored the critical need for efficient activation compression to overcome the memory constraints of mobile and edge devices. As activations dominate memory usage…

Activation functions play a key role in neural networks so it becomes fundamental to understand their advantages and disadvantages in order to achieve better performances. This paper will first introduce common types of non linear…

Temporal action detection (TAD) aims to detect the semantic labels and boundaries of action instances in untrimmed videos. Current mainstream approaches are multi-step solutions, which fall short in efficiency and flexibility. In this…

Deep neural networks owe their expressive power to nonlinear activation functions. The effective field theory of signal propagation at initialization reveals a few distinct universality classes of activations that exhibit different depth…

Multi-user shared access (MUSA) is introduced as advanced code domain non-orthogonal complex spreading sequences to support a massive number of machine-type communications (MTC) devices. In this paper, we propose a novel deep neural network…

It is known that sparsity can improve interpretability for deep neural networks. However, existing methods in the area either require networks that are pre-trained with sparsity constraints, or impose sparsity after the fact, altering the…

Deep Neural Networks (DNNs) have recently achieved great success in many tasks, which encourages DNNs to be widely used as a machine learning service in model sharing scenarios. However, attackers can easily generate adversarial examples…

We present an approach for analyzing grouping information contained within a neural network's activations, permitting extraction of spatial layout and semantic segmentation from the behavior of large pre-trained vision models. Unlike prior…

We introduce Deep Linear Discriminant Analysis (DeepLDA) which learns linearly separable latent representations in an end-to-end fashion. Classic LDA extracts features which preserve class separability and is used for dimensionality…

Foundation models are becoming increasingly popular due to their strong generalization capabilities resulting from being trained on huge datasets. These generalization capabilities are attractive in areas such as NIR Iris Presentation…

Diffusion models have demonstrated remarkable capabilities in image generation tasks, including image editing and video creation, representing a good understanding of the physical world. On the other line, diffusion models have also shown…

In the context of high usability in single-class anomaly detection models, recent academic research has become concerned about the more complex multi-class anomaly detection. Although several papers have designed unified models for this…

This paper proposes a method to visualize the discrimination power of intermediate-layer visual patterns encoded by a DNN. Specifically, we visualize (1) how the DNN gradually learns regional visual patterns in each intermediate layer…