Related papers: QuantNAS for super resolution: searching for effic…

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…

Quantizing deep neural networks is an effective method for reducing memory consumption and improving inference speed, and is thus useful for implementation in resource-constrained devices. However, it is still hard for extremely low-bit…

We tackle the problem of unsupervised visual descriptors compression, which is a key ingredient of large-scale image retrieval systems. While the deep learning machinery has benefited literally all computer vision pipelines, the existing…

Binary Neural Networks (BNNs) have gained extensive attention for their superior inferencing efficiency and compression ratio compared to traditional full-precision networks. However, due to the unique characteristics of BNNs, designing a…

Designing convolutional neural networks (CNN) for mobile devices is challenging because mobile models need to be small and fast, yet still accurate. Although significant efforts have been dedicated to design and improve mobile CNNs on all…

Network quantization allows inference to be conducted using low-precision arithmetic for improved inference efficiency of deep neural networks on edge devices. However, designing aggressively low-bit (e.g., 2-bit) quantization schemes on…

One of the key steps in Neural Architecture Search (NAS) is to estimate the performance of candidate architectures. Existing methods either directly use the validation performance or learn a predictor to estimate the performance. However,…

Low-bit quantization of network weights and activations can drastically reduce the memory footprint, complexity, energy consumption and latency of Deep Neural Networks (DNNs). However, low-bit quantization can also cause a considerable drop…

Approximate $k$-nearest neighbor (AKNN) search is a fundamental problem with wide applications. To reduce memory and accelerate search, vector quantization is widely adopted. However, existing quantization methods either rely on codebooks…

In recent years, there has been a significant trend in deep neural networks (DNNs), particularly transformer-based models, of developing ever-larger and more capable models. While they demonstrate state-of-the-art performance, their growing…

Existing deep quantization methods provided an efficient solution for large-scale image retrieval. However, the significant intra-class variations like pose, illumination, and expressions in face images, still pose a challenge for face…

In this work, we developed and tested 3 techniques for vector quantization (VQ) based model weight compression. To mitigate codebook collapse and enable end-to-end training, we adopted cosine similarity-based assignment. Building on ideas…

Neural Architecture Search (NAS) effectively discovers new Convolutional Neural Network (CNN) architectures, particularly for accuracy optimization. However, prior approaches often require resource-intensive training on super networks or…

Deep neural networks, while achieving remarkable success across diverse tasks, demand significant resources, including computation, GPU memory, bandwidth, storage, and energy. Network quantization, as a standard compression and acceleration…

Neural Architecture Search (NAS) for automatically finding the optimal network architecture has shown some success with competitive performances in various computer vision tasks. However, NAS in general requires a tremendous amount of…

Approximate nearest neighbor (ANN) query in high-dimensional Euclidean space is a key operator in database systems. For this query, quantization is a popular family of methods developed for compressing vectors and reducing memory…

Post-Training Quantization (PTQ) and Quantization-Aware Training (QAT) represent two mainstream model quantization approaches. However, PTQ often leads to unacceptable performance degradation in quantized models, while QAT imposes…

Neural Architecture Search (NAS) paves the way for the automatic definition of Neural Network (NN) architectures, attracting increasing research attention and offering solutions in various scenarios. This study introduces a novel NAS…

Network quantization is one of the most hardware friendly techniques to enable the deployment of convolutional neural networks (CNNs) on low-power mobile devices. Recent network quantization techniques quantize each weight kernel in a…

Neural architecture search (NAS) is an attractive approach to automate the design of optimized architectures but is constrained by high computational budget, especially when optimizing for multiple, important conflicting objectives. To…