相关论文: Extreme Model Compression for Edge Vision-Language…

Vision Transformers (ViT) have shown their competitive advantages performance-wise compared to convolutional neural networks (CNNs) though they often come with high computational costs. To this end, previous methods explore different…

Deploying large-scale transformer models on edge devices presents significant challenges due to strict constraints on memory, compute, and latency. In this work, we propose a lightweight yet effective multi-stage optimization pipeline…

Real-world deployment of Vision-Language Models (VLMs) is hindered by high computational demands, as existing architectures inefficiently process all tokens uniformly. We introduce Adaptive Token Pruning (ATP), a dynamic inference mechanism…

Learning-based Neural Video Codecs (NVCs) have emerged as a compelling alternative to standard video codecs, demonstrating promising performance, and simple and easily maintainable pipelines. However, NVCs often fall short of compression…

Video semantic segmentation (VSS) is a computationally expensive task due to the per-frame prediction for videos of high frame rates. In recent work, compact models or adaptive network strategies have been proposed for efficient VSS.…

This paper proposes a neural rendering approach that represents a scene as "compressed light-field tokens (CLiFTs)", retaining rich appearance and geometric information of a scene. CLiFT enables compute-efficient rendering by compressed…

In learning-based approaches to image compression, codecs are developed by optimizing a computational model to minimize a rate-distortion objective. Currently, the most effective learned image codecs take the form of an entropy-constrained…

High-energy large-scale particle colliders generate data at extraordinary rates. Developing real-time high-throughput data compression algorithms to reduce data volume and meet the bandwidth requirement for storage has become increasingly…

Neural Radiance Fields (NeRFs) have emerged as powerful tools for capturing detailed 3D scenes through continuous volumetric representations. Recent NeRFs utilize feature grids to improve rendering quality and speed; however, these…

Brain-inspired Spiking Neural Networks (SNNs) have the characteristics of event-driven and high energy-efficient, which are different from traditional Artificial Neural Networks (ANNs) when deployed on edge devices such as neuromorphic…

This paper proposes a novel communication-efficient split learning (SL) framework, named SplitFC, which reduces the communication overhead required for transmitting intermediate feature and gradient vectors during the SL training process.…

Recent synthetic speech detection models typically adapt a pre-trained SSL model via finetuning, which is computationally demanding. Parameter-Efficient Fine-Tuning (PEFT) offers an alternative. However, existing methods lack the specific…

The compression of deep neural networks (DNNs) to reduce inference cost becomes increasingly important to meet realistic deployment requirements of various applications. There have been a significant amount of work regarding network…

This study presents an iterative adaptive compression model for high-resolution DPX-derived TIFF files used in cinematographic workflows and digital preservation. The model employs SSIM and PSNR metrics to dynamically adjust compression…

Spiking neural networks (SNNs), as one of the brain-inspired models, has spatio-temporal information processing capability, low power feature, and high biological plausibility. The effective spatio-temporal feature makes it suitable for…

Learned image compression methods have shown superior rate-distortion performance and remarkable potential compared to traditional compression methods. Most existing learned approaches use stacked convolution or window-based self-attention…

For neural video codec, it is critical, yet challenging, to design an efficient entropy model which can accurately predict the probability distribution of the quantized latent representation. However, most existing video codecs directly use…

While transformer models have been highly successful, they are computationally inefficient. We observe that for each layer, the full width of the layer may be needed only for a small subset of tokens inside a batch and that the "effective"…

Large language models (LLMs) are popular around the world due to their powerful understanding capabilities. As the core component of LLMs, accelerating Transformer through parallelization has gradually become a hot research topic. Mask…

Although Vision Transformers (ViTs) have become the standard architecture in computer vision, their massive sizes lead to significant computational overhead. Token compression techniques have attracted considerable attention to address this…