相关论文: Pattern Synthesis via Complex-Coefficient Weight V…

Coherent Plane Wave Compounding (CPWC) is widely used for ultrasound imaging. This technique involves sending plane waves into a sample at different transmit angles and recording the resultant backscattered echo at different receive…

We present a general framework based on weighted finite automata and weighted finite-state transducers for describing and implementing speech recognizers. The framework allows us to represent uniformly the information sources and data…

In this paper, we study the compositional learning of images and texts for image retrieval. The query is given in the form of an image and text that describes the desired modifications to the image; the goal is to retrieve the target image…

Additive composition (Foltz et al, 1998; Landauer and Dumais, 1997; Mitchell and Lapata, 2010) is a widely used method for computing meanings of phrases, which takes the average of vector representations of the constituent words. In this…

In this paper, we introduce a novel method of neural network weight compression. In our method, we store weight tensors as sparse, quantized matrix factors, whose product is computed on the fly during inference to generate the target…

We develop a novel deep learning technique, termed Deep Orthogonal Decomposition (DOD), for dimensionality reduction and reduced order modeling of parameter dependent partial differential equations. The approach consists in the construction…

Collocated clothing synthesis (CCS) has emerged as a pivotal topic in fashion technology, primarily concerned with the generation of a clothing item that harmoniously matches a given item. However, previous investigations have relied on…

Modern top-performing object detectors depend heavily on backbone networks, whose advances bring consistent performance gains through exploring more effective network structures. In this paper, we propose a novel and flexible backbone…

The joint understanding of vision and language has been recently gaining a lot of attention in both the Computer Vision and Natural Language Processing communities, with the emergence of tasks such as image captioning, image-text matching,…

Compressing large neural networks is an important step for their deployment in resource-constrained computational platforms. In this context, vector quantization is an appealing framework that expresses multiple parameters using a single…

Convolutional Neural Networks (CNNs) has shown a great success in many areas including complex image classification tasks. However, they need a lot of memory and computational cost, which hinders them from running in relatively low-end…

Adapting large language models to multiple tasks can cause cross-skill interference, where improvements for one skill degrade another. While methods such as LoRA impose orthogonality constraints at the weight level, they do not fully…

We present a generative model for controllable person image synthesis,as shown in Figure , which can be applied to pose-guided person image synthesis, $i.e.$, converting the pose of a source person image to the target pose while preserving…

Tensor completion aimes at recovering missing data, and it is one of the popular concerns in deep learning and signal processing. Among the higher-order tensor decomposition algorithms, the recently proposed fully-connected tensor network…

This paper studies reduced-order modeling of dynamic networks with strongly connected topology. Given a graph clustering of an original complex network, we construct a quotient graph with less number of vertices, where the edge weights are…

The recent WSNet [1] is a new model compression method through sampling filterweights from a compact set and has demonstrated to be effective for 1D convolutionneural networks (CNNs). However, the weights sampling strategy of WSNet…

In this paper, the optimal and precise array response control (OPARC) algorithm proposed in Part I of this two paper series is extended from single point to multi-points. Two computationally attractive parameter determination approaches are…

Quantization based model compression serves as high performing and fast approach for inference that yields models which are highly compressed when compared to their full-precision floating point counterparts. The most extreme quantization…

Program synthesis has emerged as a successful approach to the image parsing task. Most prior works rely on a two-step scheme involving supervised pretraining of a Seq2Seq model with synthetic programs followed by reinforcement learning (RL)…

We present component and connector (C&C) views, which specify structural properties of component and connector models in an expressive and intuitive way. C&C views provide means to abstract away direct hierarchy, direct connectivity, port…