Related papers: Work-Efficient Parallel Non-Maximum Suppression Ke…

The densest subgraph problem has received significant attention, both in theory and in practice, due to its applications in problems such as community detection, social network analysis, and spam detection. Due to the high cost of obtaining…

We propose a new model for unsupervised document embedding. Leading existing approaches either require complex inference or use recurrent neural networks (RNN) that are difficult to parallelize. We take a different route and develop a…

Deformable Parts Models and Convolutional Networks each have achieved notable performance in object detection. Yet these two approaches find their strengths in complementary areas: DPMs are well-versed in object composition, modeling…

Computing at the edge offers intriguing possibilities for the development of autonomy and artificial intelligence. The advancements in autonomous technologies and the resurgence of computer vision have led to a rise in demand for fast and…

Non-Maximum Suppression (NMS) is essential for object detection and affects the evaluation results by incorporating False Positives (FP) and False Negatives (FN), especially in crowd occlusion scenes. In this paper, we raise the problem of…

Deep neural networks (DNNs) have achieved significant success in a variety of real world applications, i.e., image classification. However, tons of parameters in the networks restrict the efficiency of neural networks due to the large model…

CNN-based face detection methods have achieved significant progress in recent years. In addition to the strong representation ability of CNN, post-processing methods are also very important for the performance of face detection. In general,…

Maximal Clique Enumeration (MCE) is a fundamental graph mining problem, and is useful as a primitive in identifying dense structures in a graph. Due to the high computational cost of MCE, parallel methods are imperative for dealing with…

Nucleus decompositions have been shown to be a useful tool for finding dense subgraphs. The coreness value of a clique represents its density based on the number of other cliques it is adjacent to. One useful output of nucleus decomposition…

Graph Neural Networks (GNNs) have emerged as powerful tools for various graph mining tasks, yet existing scalable solutions often struggle to balance execution efficiency with prediction accuracy. These difficulties stem from iterative…

Graph Neural Networks (GNNs) with attention have been successfully applied for learning visual feature matching. However, current methods learn with complete graphs, resulting in a quadratic complexity in the number of features. Motivated…

Convolutional Neural Networks (CNNs) have advanced significantly in visual representation learning and recognition. However, they face notable challenges in performance and computational efficiency when dealing with real-world, multi-scale…

Deep Neural Networks (DNNs) are increasingly deployed across diverse industries, driving demand for mobile device support. However, existing mobile inference frameworks often rely on a single processor per model, limiting hardware…

The searching procedure of neural architecture search (NAS) is notoriously time consuming and cost prohibitive.To make the search space continuous, most existing gradient-based NAS methods relax the categorical choice of a particular…

Sparse matrix-vector and matrix-matrix multiplication (SpMV and SpMM) are fundamental in both conventional (graph analytics, scientific computing) and emerging (sparse DNN, GNN) domains. Workload-balancing and parallel-reduction are…

Graph neural networks (GNNs), an emerging deep learning model class, can extract meaningful representations from highly expressive graph-structured data and are therefore gaining popularity for wider ranges of applications. However, current…

Convolutional neural networks (CNNs) have demonstrated remarkable results in image classification for benchmark tasks and practical applications. The CNNs with deeper architectures have achieved even higher performance recently thanks to…

We propose a new method to create compact convolutional neural networks (CNNs) by exploiting sparse convolutions. Different from previous works that learn sparsity in models, we directly employ hand-crafted kernels with regular sparse…

Conventional deep convolutional neural networks (CNNs) apply convolution operators uniformly in space across all feature maps for hundreds of layers - this incurs a high computational cost for real-time applications. For many problems such…

Existing approaches to train neural networks that use large images require to either crop or down-sample data during pre-processing, use small batch sizes, or split the model across devices mainly due to the prohibitively limited memory…