Related papers: Genie: Show Me the Data for Quantization
Zero-shot learning strives to classify unseen categories for which no data is available during training. In the generalized variant, the test samples can further belong to seen or unseen categories. The state-of-the-art relies on Generative…
Zero-shot learning (ZSL) aims at recognizing classes for which no visual sample is available at training time. To address this issue, one can rely on a semantic description of each class. A typical ZSL model learns a mapping between the…
Multi-label zero-shot learning strives to classify images into multiple unseen categories for which no data is available during training. The test samples can additionally contain seen categories in the generalized variant. Existing…
Generative zero-shot learning (ZSL) methods typically synthesize visual features for unseen classes using predefined semantic attributes, followed by training a fully supervised classification model. While effective, these methods require…
The field of machine learning has recently made significant progress in reducing the requirements for labelled training data when building new models. These `cheaper' learning techniques hold significant potential for the social sciences,…
We propose a visual analytics system to help a user analyze and steer zero-shot learning models. Zero-shot learning has emerged as a viable scenario for categorizing data that consists of no labeled examples, and thus a promising approach…
Recent progress towards learning from limited supervision has encouraged efforts towards designing models that can recognize novel classes at test time (generalized zero-shot learning or GZSL). GZSL approaches assume knowledge of all…
Quantization Neural Networks (QNN) have attracted a lot of attention due to their high efficiency. To enhance the quantization accuracy, prior works mainly focus on designing advanced quantization algorithms but still fail to achieve…
Data generation-based zero-shot learning, although effective in training Small Task-specific Models (STMs) via synthetic datasets generated by Pre-trained Language Models (PLMs), is often limited by the low quality of such synthetic…
Deep learning-based face recognition models follow the common trend in deep neural networks by utilizing full-precision floating-point networks with high computational costs. Deploying such networks in use-cases constrained by computational…
In realistic speech enhancement settings for end-user devices, we often encounter only a few speakers and noise types that tend to reoccur in the specific acoustic environment. We propose a novel personalized speech enhancement method to…
Vision-language models trained with contrastive learning on large-scale noisy data are becoming increasingly popular for zero-shot recognition problems. In this paper we improve the following three aspects of the contrastive pre-training…
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…
While developments in machine learning led to impressive performance gains on big data, many human subjects data are, in actuality, small and sparsely labeled. Existing methods applied to such data often do not easily generalize to…
Recently, transformer has achieved remarkable performance on a variety of computer vision applications. Compared with mainstream convolutional neural networks, vision transformers are often of sophisticated architectures for extracting…
In this short note, we propose a new method for quantizing the weights of a fully trained neural network. A simple deterministic pre-processing step allows us to quantize network layers via memoryless scalar quantization while preserving…
Deep learning as a means to inferencing has proliferated thanks to its versatility and ability to approach or exceed human-level accuracy. These computational models have seemingly insatiable appetites for computational resources not only…
Performing knowledge transfer from a large teacher network to a smaller student is a popular task in modern deep learning applications. However, due to growing dataset sizes and stricter privacy regulations, it is increasingly common not to…
Training neural networks requires significant computational resources and energy. Methods like mixed-precision and quantization-aware training reduce bit usage, yet they still depend heavily on computationally expensive gradient-based…
Feature selection, an effective technique for dimensionality reduction, plays an important role in many machine learning systems. Supervised knowledge can significantly improve the performance. However, faced with the rapid growth of newly…