Related papers: Reg4Pru: Regularisation Through Random Token Routi…

Large Vision-Language Models (LVLMs) incur substantial inference costs due to the processing of a vast number of visual tokens. Existing methods typically struggle to model progressive visual token reduction as a multi-step decision process…

With the rise of smartphones and the internet-of-things, data is increasingly getting generated at the edge on local, personal devices. For privacy, latency and energy saving reasons, this shift is causing machine learning algorithms to…

Pruning neural networks, i.e., removing some of their parameters whilst retaining their accuracy, is one of the main ways to reduce the latency of a machine learning pipeline, especially in resource- and/or bandwidth-constrained scenarios.…

Convolutional Neural Networks (CNNs) have demonstrated exceptional performance in recent years. Compressing these models not only reduces storage requirements, making deployment to edge devices feasible, but also accelerates inference,…

Pruning neural networks at initialization would enable us to find sparse models that retain the accuracy of the original network while consuming fewer computational resources for training and inference. However, current methods are…

The success of convolutional neural networks (CNNs) in computer vision applications has been accompanied by a significant increase of computation and memory costs, which prohibits its usage on resource-limited environments such as mobile or…

While transformer-based models achieve strong performance on text classification, we explore whether masking input tokens can further enhance their effectiveness. We propose token masking regularization, a simple yet theoretically motivated…

Deploying pre-trained transformer models like BERT on downstream tasks in resource-constrained scenarios is challenging due to their high inference cost, which grows rapidly with input sequence length. In this work, we propose a…

Structured pruning is an effective compression technique to reduce the computation of neural networks, which is usually achieved by adding perturbations to reduce network parameters at the cost of slightly increasing training loss. A more…

Structured pruning greatly eases the deployment of large neural networks in resource-constrained environments. However, current methods either involve strong domain expertise, require extra hyperparameter tuning, or are restricted only to a…

Deep Reinforcement Learning (Deep RL) has been receiving increasingly more attention thanks to its encouraging performance on a variety of control tasks. Yet, conventional regularization techniques in training neural networks (e.g., $L_2$…

Vision transformers have achieved leading performance on various visual tasks yet still suffer from high computational complexity. The situation deteriorates in dense prediction tasks like semantic segmentation, as high-resolution inputs…

While specialized Medical Vision-Language Models (VLMs) have achieved remarkable success in interpreting 2D and 3D medical modalities, their deployment for 3D volumetric data remains constrained by significant computational inefficiencies.…

The ever-increasing number of parameters in deep neural networks poses challenges for memory-limited applications. Regularize-and-prune methods aim at meeting these challenges by sparsifying the network weights. In this context we quantify…

Recent advances in vision-language models have demonstrated remarkable performance across diverse multi-modal tasks, including document question answering that leverages structured visual cues from text, tables, and figures. However, unlike…

Deep Neural Networks (DNNs) are ubiquitous in today's computer vision land-scape, despite involving considerable computational costs. The mainstream approaches for runtime acceleration consist in pruning connections (unstructured pruning)…

Various applications in the field of autonomous driving are based on convolutional neural networks (CNNs), especially for processing camera data. The optimization of such CNNs is a major challenge in continuous development. Newly learned…

Affective computing systems are increasingly embedded in pervasive and interactive environments, such as adaptive games, assistive technologies, and resource-constrained platforms, where computational efficiency must be balanced with…

Vision Transformers (ViTs) have achieved state-of-the-art accuracy on various computer vision tasks. However, their high computational complexity prevents them from being applied to many real-world applications. Weight and token pruning are…

Vision Large Language Models (VLLMs) incur high computational costs due to their reliance on hundreds of visual tokens to represent images. While token pruning offers a promising solution for accelerating inference, this paper, however,…