Related papers: DeepCache: Principled Cache for Mobile Deep Vision

We propose a learning algorithm to design a light-weight neural multiplexer that given the input and computational resource requirements, calls the model that will consume the minimum compute resources for a successful inference. Mobile…

The disaggregated memory (DM) architecture offers high resource elasticity at the cost of data access performance. While caching frequently accessed data in compute nodes (CNs) reduces access overhead, it requires costly centralized…

Mobile authentication using behavioral biometrics has been an active area of research. Existing research relies on building machine learning classifiers to recognize an individual's unique patterns. However, these classifiers are not…

One of the major differentiators unlocked by learned codecs relative to their hard-coded traditional counterparts is their ability to be optimized directly to appeal to the human visual system. Despite this potential, a perceptual yet…

Many mobile applications have been developed to apply deep learning for video analytics. Although these advanced deep learning models can provide us with better results, they also suffer from the high computational overhead which means…

Deep neural networks have shown promise in several domains, and the learned data (task) specific information is implicitly stored in the network parameters. Extraction and utilization of encoded knowledge representations are vital when data…

Mobile edge caching enables content delivery directly within the radio access network, which effectively alleviates the backhaul burden and reduces round-trip latency. To fully exploit the edge resources, the most popular contents should be…

Action recognition is a vital task in computer vision, and many methods are developed to push it to the limit. However, current action recognition models have huge computational costs, which cannot be deployed to real-world tasks on mobile…

Diffusion models suffer from substantial computational overhead due to their inherently iterative inference process. While feature caching offers a promising acceleration strategy by reusing intermediate outputs across timesteps, naive…

Autonomous vehicles demand high accuracy and robustness of perception algorithms. To develop efficient and scalable perception algorithms, the maximum information should be extracted from the available sensor data. In this work, we present…

Training deep neural networks at the edge on light computational devices, embedded systems and robotic platforms is nowadays very challenging. Continual learning techniques, where complex models are incrementally trained on small batches of…

Internet-scale web applications are becoming increasingly storage-intensive and rely heavily on in-memory object caching to attain required I/O performance. We argue that the emerging serverless computing paradigm provides a well-suited,…

In the present paper, we propose a source camera identification method for mobile devices based on deep learning. Recently, convolutional neural networks (CNNs) have shown a remarkable performance on several tasks such as image recognition,…

Video generation models have demonstrated remarkable performance, yet their broader adoption remains constrained by slow inference speeds and substantial computational costs, primarily due to the iterative nature of the denoising process.…

Vision-Language Models (VLMs) have demonstrated impressive performance across a versatile set of tasks. A key challenge in accelerating VLMs is storing and accessing the large Key-Value (KV) cache that encodes long visual contexts, such as…

In this paper, we propose a novel wireless caching scheme to enhance the physical layer security of video streaming in cellular networks with limited backhaul capacity. By proactively sharing video data across a subset of base stations…

We present MeanCache, a training-free caching framework for efficient Flow Matching inference. Existing caching methods reduce redundant computation but typically rely on instantaneous velocity information (e.g., feature caching), which…

The increasingly complicated and diverse applications have distinct network performance demands, e.g., some desire high throughput while others require low latency. Traditional congestion controls (CC) have no perception of these demands.…

Long-form video question answering (VQA) overwhelms current vision-language models (VLMs) because attention and key-value (KV) caches grow with runtime, forcing either expensive inference or near-sighted sliding windows. We introduce…

Recent breakthroughs in deep learning and artificial intelligence technologies have enabled numerous mobile applications. While traditional computation paradigms rely on mobile sensing and cloud computing, deep learning implemented on…