相关论文: Class Based Thresholding in Early Exit Semantic Se…

We develop a hyperparameter optimisation algorithm, Automated Budget Constrained Training (AutoBCT), which balances the quality of a model with the computational cost required to tune it. The relationship between hyperparameters, model…

Early-exit neural networks enable adaptive computation by allowing confident predictions to exit at intermediate layers, achieving 2-8$\times$ inference speedup. Despite widespread deployment, their generalization properties lack…

Pre-training with self-supervised models, such as Hidden-unit BERT (HuBERT) and wav2vec 2.0, has brought significant improvements in automatic speech recognition (ASR). However, these models usually require an expensive computational cost…

We develop a novel approach for confidently accelerating inference in the large and expensive multilayer Transformers that are now ubiquitous in natural language processing (NLP). Amortized or approximate computational methods increase…

Visual Language Models require substantial computational resources for inference due to the additional input tokens needed to represent visual information. However, these visual tokens often contain redundant and unimportant information,…

Sampling-based algorithms, such as Rapidly Exploring Random Trees (RRT) and its variants, have been used extensively for motion planning. Control barrier functions (CBFs) have been recently proposed to synthesize controllers for…

In this paper, we propose a novel approach to minimize the inference delay in semantic segmentation using split learning (SL), tailored to the needs of real-time computer vision (CV) applications for resource-constrained devices. Semantic…

We introduce the Temporal Contrastive Transformer (TCT), a representation learning framework designed to capture contextual temporal dynamics in sequences of financial transactions. The model is trained using a self-supervised contrastive…

Large pre-trained sentence encoders like BERT start a new chapter in natural language processing. A common practice to apply pre-trained BERT to sequence classification tasks (e.g., classification of sentences or sentence pairs) is by…

In this paper, we hypothesize that the effects of the degree of typicality in natural semantic categories can be generated based on the structure of artificial categories learned with deep learning models. Motivated by the human approach to…

The growing deployment of Internet of Things (IoT) devices in smart cities and industrial environments increases vulnerability to stealthy, multi-stage advanced persistent threats (APTs) that exploit wireless communication. Detection is…

We prove theoretically that generalization improves not only through data scaling but also by compressing internal representations. To operationalize this insight, we introduce the Information Bottleneck Language Modeling (IBLM) objective,…

The fast growing capabilities of large-scale deep learning models, such as Bert, GPT and ViT, are revolutionizing the landscape of NLP, CV and many other domains. Training such models, however, poses an unprecedented demand for computing…

The Cognitive Categorical Transformer (CCT) is a 306M-parameter architecture that augments a pretrained GPT-2 Small backbone with cognitively grounded components derived from category theory and several inspirations from cognitive science.…

Chinese word segmentation (CWS) is a fundamental task for Chinese language understanding. Recently, neural network-based models have attained superior performance in solving the in-domain CWS task. Last year, Bidirectional Encoder…

Recent studies of large-scale contrastive pretraining in the text embedding domain show that using single-source minibatches, rather than mixed-source minibatches, can substantially improve overall model accuracy. In this work, we explore…

Despite recent advances in architectures for mobile devices, deep learning computational requirements remains prohibitive for most embedded devices. To address that issue, we envision sharing the computational costs of inference between…

We propose a Class-Based Styling method (CBS) that can map different styles for different object classes in real-time. CBS achieves real-time performance by carrying out two steps simultaneously. While a semantic segmentation method is used…

We present a method that "meta" classifies whether seg-ments predicted by a semantic segmentation neural networkintersect with the ground truth. For this purpose, we employ measures of dispersion for predicted pixel-wise class probability…

We propose Curriculum by Masking (CBM), a novel state-of-the-art curriculum learning strategy that effectively creates an easy-to-hard training schedule via patch (token) masking, offering significant accuracy improvements over the…