Related papers: Hierarchical Sparse Attention Framework for Comput…

To accelerate deep CNN models, this paper proposes a novel spatially adaptive framework that can dynamically generate pixel-wise sparsity according to the input image. The sparse scheme is pixel-wise refined, regional adaptive under a…

A new line of research for feature selection based on neural networks has recently emerged. Despite its superiority to classical methods, it requires many training iterations to converge and detect informative features. The computational…

Human visual recognition is a sparse process, where only a few salient visual cues are attended to rather than traversing every detail uniformly. However, most current vision networks follow a dense paradigm, processing every single visual…

Can we leverage high-resolution information without the unsustainable quadratic complexity to input scale? We propose Traversal Network (TNet), a novel multi-scale hard-attention architecture, which traverses image scale-space in a top-down…

Hyperspectral image (HSI) classification faces critical challenges, including high spectral dimensionality, complex spectral-spatial correlations, and limited training samples with severe class imbalance. While CNNs excel at local feature…

Inference of standard convolutional neural networks (CNNs) on FPGAs often incurs high latency and a long initiation interval due to the deep nested loops required to densely convolve every input pixel regardless of its feature value.…

We present the performance of a semantic segmentation network, SparseSSNet, that provides pixel-level classification of MicroBooNE data. The MicroBooNE experiment employs a liquid argon time projection chamber for the study of neutrino…

An efficient attention implementation is essential for large models due to its quadratic time complexity. Fortunately, attention commonly exhibits sparsity, i.e., many values in the attention map are near zero, allowing for the omission of…

Semantic segmentation empowers numerous real-world applications, such as autonomous driving and augmented/mixed reality. These applications often operate on high-resolution images (e.g., 8 megapixels) to capture the fine details. However,…

The accuracy of deep convolutional neural networks (CNNs) generally improves when fueled with high resolution images. However, this often comes at a high computational cost and high memory footprint. Inspired by the fact that not all…

We propose Sparse Sinkhorn Attention, a new efficient and sparse method for learning to attend. Our method is based on differentiable sorting of internal representations. Concretely, we introduce a meta sorting network that learns to…

Global context information is vital in visual understanding problems, especially in pixel-level semantic segmentation. The mainstream methods adopt the self-attention mechanism to model global context information. However, pixels belonging…

Training end-to-end networks for classifying gigapixel size histopathological images is computationally intractable. Most approaches are patch-based and first learn local representations (patch-wise) before combining these local…

In computer vision tasks, the ability to focus on relevant regions within an image is crucial for improving model performance, particularly when key features are small, subtle, or spatially dispersed. Convolutional neural networks (CNNs)…

Convolutional neural networks are the most successful models in single image super-resolution. Deeper networks, residual connections, and attention mechanisms have further improved their performance. However, these strategies often improve…

Event cameras are bio-inspired sensors that respond to per-pixel brightness changes in the form of asynchronous and sparse "events". Recently, pattern recognition algorithms, such as learning-based methods, have made significant progress…

Deep learning has excelled in medical image classification, but its clinical application is limited by poor interpretability. Capsule networks, known for encoding hierarchical relationships and spatial features, show potential in addressing…

In the field of medical CT image processing, convolutional neural networks (CNNs) have been the dominant technique.Encoder-decoder CNNs utilise locality for efficiency, but they cannot simulate distant pixel interactions properly.Recent…

Deep neural networks are state-of-the-art models for understanding the content of images, video and raw input data. However, implementing a deep neural network in embedded systems is a challenging task, because a typical deep neural…

The spatial attention mechanism captures long-range dependencies by aggregating global contextual information to each query location, which is beneficial for semantic segmentation. In this paper, we present a sparse spatial attention…