Related papers: Covariance-Aware Goodness for Scalable Forward-For…

Event-based vision encodes dynamic scenes as asynchronous spatio-temporal spikes called events. To leverage conventional image processing pipelines, events are typically binned into frames. However, binning functions are discontinuous,…

Improving weight sparsity is a common strategy for producing light-weight deep neural networks. However, pruning models with residual learning is more challenging. In this paper, we introduce Variance-Aware Cross-Layer (VACL), a novel…

The concept of a recently proposed Forward-Forward learning algorithm for fully connected artificial neural networks is applied to a single multi output perceptron for classification. The parameters of the system are trained with respect to…

Vision Transformers (ViTs) have achieved impressive results in computer vision by leveraging self-attention to model long-range dependencies. However, their emphasis on global context often comes at the expense of local feature extraction…

Skeleton-based human action recognition (HAR) has achieved remarkable progress with graph-based architectures. However, most existing methods remain body-centric, focusing on large-scale motions while neglecting subtle hand articulations…

A new wave of work on covariance cleaning and nonlinear shrinkage has delivered asymptotically optimal analytical solutions for large covariance matrices. The same framework has been generalized to empirical cross-covariance matrices, whose…

Convolutional networks (ConvNets) have achieved promising accuracy for various anatomical segmentation tasks. Despite the success, these methods can be sensitive to data appearance variations. Considering the large variability of scans…

Currently, deep learning-based methods for remote sensing pansharpening have advanced rapidly. However, many existing methods struggle to fully leverage feature heterogeneity and redundancy, thereby limiting their effectiveness. We use the…

To meet the demands of applications like robotics and autonomous driving that require real-time responses to dynamic environments, efficient continual learning methods suitable for edge devices have attracted increasing attention. In this…

Network-based transfer learning allows the reuse of deep learning features with limited data, but the resulting models can be unnecessarily large. Although network pruning can improve inference efficiency, existing algorithms usually…

Large Foundation Models (LFMs) have demonstrated significant advantages in civil engineering, but they primarily focus on textual and visual data, overlooking the rich semantic, spatial, and topological features in BIM (Building Information…

The backpropagation algorithm, or backprop, is a widely utilized optimization technique in deep learning. While there's growing evidence suggesting that models trained with backprop can accurately explain neuronal data, no backprop-like…

Effectively integrating multi-scale information is of considerable significance for the challenging multi-class segmentation of fundus lesions because different lesions vary significantly in scales and shapes. Several methods have been…

Despite their impressive performance in object recognition and other tasks under standard testing conditions, deep networks often fail to generalize to out-of-distribution (o.o.d.) samples. One cause for this shortcoming is that modern…

Numerous recent works utilize bi-Lipschitz regularization of neural network layers to preserve relative distances between data instances in the feature spaces of each layer. This distance sensitivity with respect to the data aids in tasks…

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…

Key-value (KV) cache memory management is the primary bottleneck limiting throughput and cost-efficiency in large-scale GPU inference serving. Current systems suffer from three compounding inefficiencies: (1) the absence of unified KV cache…

Deep learning for predicting the electronic-structure Hamiltonian of quantum systems necessitates satisfying the covariance laws, among which achieving SO(3)-equivariance without sacrificing the non-linear expressive capability of networks…

An iterative method of learning has become a paradigm for training deep convolutional neural networks (DCNN). However, utilizing a non-iterative learning strategy can accelerate the training process of the DCNN and surprisingly such…

The inference structures and computational complexity of existing deep neural networks, once trained, are fixed and remain the same for all test images. However, in practice, it is highly desirable to establish a progressive structure for…