Related papers: f-BRS: Rethinking Backpropagating Refinement for I…

In (\cite{zhang2014nonlinear,zhang2014nonlinear2}), we have viewed machine learning as a coding and dimensionality reduction problem, and further proposed a simple unsupervised dimensionality reduction method, entitled deep distributed…

Background subtraction is a fundamental pre-processing task in computer vision. This task becomes challenging in real scenarios due to variations in the background for both static and moving camera sequences. Several deep learning methods…

While biological vision systems rely heavily on feedback connections to iteratively refine perception, most artificial neural networks remain purely feedforward, processing input in a single static pass. In this work, we propose a…

The brain is a highly reconfigurable machine capable of task-specific adaptations. The brain continually rewires itself for a more optimal configuration to solve problems. We propose a novel strategic synthesis algorithm for feedforward…

Direct training of Spiking Neural Networks (SNNs) on neuromorphic hardware can greatly reduce energy costs compared to GPU-based training. However, implementing Backpropagation (BP) on such hardware is challenging because forward and…

While backpropagation--reverse-mode automatic differentiation--has been extraordinarily successful in deep learning, it requires two passes (forward and backward) through the neural network and the storage of intermediate activations.…

With the increasing imaging and processing capabilities of today's mobile devices, user authentication using iris biometrics has become feasible. However, as the acquisition conditions become more unconstrained and as image quality is…

Image restoration tasks have achieved tremendous performance improvements with the rapid advancement of deep neural networks. However, most prevalent deep learning models perform inference statically, ignoring that different images have…

Recent advances in deep neural networks (DNNs) owe their success to training algorithms that use backpropagation and gradient-descent. Backpropagation, while highly effective on von Neumann architectures, becomes inefficient when scaling to…

The performance of deep neural networks is well-known to be sensitive to the setting of their hyperparameters. Recent advances in reverse-mode automatic differentiation allow for optimizing hyperparameters with gradients. The standard way…

Probabilistic atlas priors have been commonly used to derive adaptive and robust brain MRI segmentation algorithms. Widely-used neuroimage analysis pipelines rely heavily on these techniques, which are often computationally expensive. In…

Deep neural network architectures have recently produced excellent results in a variety of areas in artificial intelligence and visual recognition, well surpassing traditional shallow architectures trained using hand-designed features. The…

In semantic segmentation, accurate prediction masks are crucial for downstream tasks such as medical image analysis and image editing. Due to the lack of annotated data, few-shot semantic segmentation (FSS) performs poorly in predicting…

Deep learning has revolutionized industries like computer vision, natural language processing, and speech recognition. However, back propagation, the main method for training deep neural networks, faces challenges like computational…

There has recently been great progress in automatic segmentation of medical images with deep learning algorithms. In most works observer variation is acknowledged to be a problem as it makes training data heterogeneous but so far no…

Despite the rise of deep learning in numerous areas of computer vision and image processing, iris recognition has not benefited considerably from these trends so far. Most of the existing research on deep iris recognition is focused on new…

Referring image segmentation (RIS) aims to segment objects in an image conditioning on free-from text descriptions. Despite the overwhelming progress, it still remains challenging for current approaches to perform well on cases with various…

Weakly-supervised semantic segmentation (WSSS) using image-level labels has recently attracted much attention for reducing annotation costs. Existing WSSS methods utilize localization maps from the classification network to generate pseudo…

In the domain of computer vision, Parameter-Efficient Tuning (PET) is increasingly replacing the traditional paradigm of pre-training followed by full fine-tuning. PET is particularly favored for its effectiveness in large foundation…

Neural network has attracted great attention for a long time and many researchers are devoted to improve the effectiveness of neural network training algorithms. Though stochastic gradient descent (SGD) and other explicit gradient-based…