Related papers: Task-Specific Zero-shot Quantization-Aware Trainin…

Due to its fast retrieval and storage efficiency capabilities, hashing has been widely used in nearest neighbor retrieval tasks. By using deep learning based techniques, hashing can outperform non-learning based hashing technique in many…

Model quantization is challenging due to many tedious hyper-parameters such as precision (bitwidth), dynamic range (minimum and maximum discrete values) and stepsize (interval between discrete values). Unlike prior arts that carefully tune…

Quantization is emerging as an efficient approach to promote hardware-friendly deep learning and run deep neural networks on resource-limited hardware. However, it still causes a significant decrease to the network in accuracy. We summarize…

Trained on large datasets, deep learning (DL) can accurately classify videos into hundreds of diverse classes. However, video data is expensive to annotate. Zero-shot learning (ZSL) proposes one solution to this problem. ZSL trains a model…

Class-agnostic object counting aims to count object instances of an arbitrary class at test time. It is challenging but also enables many potential applications. Current methods require human-annotated exemplars as inputs which are often…

How to efficiently serve ever-larger trained natural language models in practice has become exceptionally challenging even for powerful cloud servers due to their prohibitive memory/computation requirements. In this work, we present an…

We introduce Delta-Aware Quantization (DAQ), a data-free post-training quantization framework that preserves the knowledge acquired during post-training. Standard quantization objectives minimize reconstruction error but are agnostic to the…

Recent research works have proposed machine learning models for classifying IoT devices connected to a network. However, there is still a practical challenge of not having all devices (and hence their traffic) available during the training…

Humans are able to learn to recognize new objects even from a few examples. In contrast, training deep-learning-based object detectors requires huge amounts of annotated data. To avoid the need to acquire and annotate these huge amounts of…

We introduce a novel run-time method for significantly reducing the accuracy loss associated with quantizing BERT-like models to 8-bit integers. Existing methods for quantizing models either modify the training procedure,or they require an…

Quantization-aware training (QAT) is a representative model compression method to reduce redundancy in weights and activations. However, most existing QAT methods require end-to-end training on the entire dataset, which suffers from long…

We propose a novel method for training a conditional generative adversarial network (CGAN) without the use of training data, called zero-shot learning of a CGAN (ZS-CGAN). Zero-shot learning of a conditional generator only needs a…

Vision Transformers (ViTs) are essential in computer vision but are computationally intensive, too. Model quantization, particularly to low bit-widths like 4-bit, aims to alleviate this difficulty, yet existing Post-Training Quantization…

Recent advancements in machine learning achieved by Deep Neural Networks (DNNs) have been significant. While demonstrating high accuracy, DNNs are associated with a huge number of parameters and computations, which leads to high memory…

Traditionally, quantization is designed to minimize the reconstruction error of a data source. When considering downstream classification tasks, other measures of distortion can be of interest; such as the 0-1 classification loss.…

In this work, we present a novel meta-learning algorithm, i.e. TTNet, that regresses model parameters for novel tasks for which no ground truth is available (zero-shot tasks). In order to adapt to novel zero-shot tasks, our meta-learner…

Zero-shot object detection aims at incorporating class semantic vectors to realize the detection of (both seen and) unseen classes given an unconstrained test image. In this study, we reveal the core challenges in this research area: how to…

Post-training quantization has emerged as the most widely used strategy for deploying large language models at low precision. Still, current methods show perplexity degradation at bit-widths less than or equal to 4, partly because…

Zero-shot Hashing (ZSH) is to learn hashing models for novel/target classes without training data, which is an important and challenging problem. Most existing ZSH approaches exploit transfer learning via an intermediate shared semantic…

Large-scale image datasets are fundamental to deep learning, but their high storage demands pose challenges for deployment in resource-constrained environments. While existing approaches reduce dataset size by discarding samples, they often…