Related papers: Using MLIR Transform to Design Sliced Convolution …

Data-driven inverse optimization for mixed-integer linear programs (MILPs), which seeks to learn an objective function and constraints consistent with observed decisions, is important for building accurate mathematical models in a variety…

Vision Transformers (ViT) become widely-adopted architectures for various vision tasks. Masked auto-encoding for feature pretraining and multi-scale hybrid convolution-transformer architectures can further unleash the potentials of ViT,…

Automated medical image segmentation can assist doctors to diagnose faster and more accurate. Deep learning based models for medical image segmentation have made great progress in recent years. However, the existing models fail to…

The separation of the data capture and analysis in modern vision systems has led to a massive amount of data transfer between the end devices and cloud computers, resulting in long latency, slow response, and high power consumption.…

Supervised Fine-Tuning (SFT) Large Language Models (LLM) fundamentally rely on high-quality training data. While data selection and data synthesis are two common strategies to improve data quality, existing approaches often face limitations…

In this paper we consider the fundamental operations dilation and erosion of mathematical morphology. Many powerful image filtering operations are based on their combinations. We establish homomorphism between max-plus semi-ring of integers…

Sixth-generation (6G) network slicing is the backbone of future communications systems. It inaugurates the era of extreme ultra-reliable and low-latency communication (xURLLC) and pervades the digitalization of the various vertical…

We introduce a novel weighted convolution operator that enhances traditional convolutional neural networks (CNNs) by integrating a spatial density function into the convolution operator. This extension enables the network to differentially…

Transduction is a powerful paradigm that leverages the structure of unlabeled data to boost predictive accuracy. We present TransCLIP, a novel and computationally efficient transductive approach designed for Vision-Language Models (VLMs).…

Polyp segmentation within colonoscopy video frames using deep learning models has the potential to automate the workflow of clinicians. This could help improve the early detection rate and characterization of polyps which could progress to…

Hardware acceleration for dilated and transposed convolution enables real time execution of related tasks like segmentation, but current designs are specific for these convolutional types or suffer from complex control for reconfigurable…

Object orientation provides a flexible framework for the implementation of the convolution of arbitrary distributions of real-valued random variables. We discuss an algorithm which is based on the discrete Fourier transformation (DFT) and…

The field-of-view is an important metric when designing a model for semantic segmentation. To obtain a large field-of-view, previous approaches generally choose to rapidly downsample the resolution, usually with average poolings or stride 2…

Radio map, or pathloss map prediction, is a crucial method for wireless network modeling and management. By leveraging deep learning to construct pathloss patterns from geographical maps, an accurate digital replica of the transmission…

Achieving superior enhancement performance while maintaining a low parameter count and computational complexity remains a challenge in the field of speech enhancement. In this paper, we introduce LORT, a novel architecture that integrates…

With the rise of Deep Learning (DL), our world braces for AI in every edge device, creating an urgent need for edge-AI SoCs. This SoC hardware needs to support high throughput, reliable and secure AI processing at Ultra Low Power (ULP),…

Robust local feature representations are essential for spatial intelligence tasks such as robot navigation and augmented reality. Establishing reliable correspondences requires descriptors that provide both high discriminative power and…

We develop a method for improving the parallel scalability of the recently developed parallel selected inversion algorithm [Jacquelin, Lin and Yang 2014], named PSelInv, on massively parallel distributed memory machines. In the PSelInv…

Deep convolutional neural networks (ConvNets) of 3-dimensional kernels allow joint modeling of spatiotemporal features. These networks have improved performance of video and volumetric image analysis, but have been limited in size due to…

Vision-language foundation models such as CLIP have achieved tremendous results in global vision-language alignment, but still show some limitations in creating representations for specific image regions. % To address this problem, we…