Related papers: MobileOne: An Improved One millisecond Mobile Back…

To design fast neural networks, many works have been focusing on reducing the number of floating-point operations (FLOPs). We observe that such reduction in FLOPs, however, does not necessarily lead to a similar level of reduction in…

We present a new family of mobile hybrid vision networks, called iFormer, with a focus on optimizing latency and accuracy on mobile applications. iFormer effectively integrates the fast local representation capacity of convolution with the…

Mixture-of-Experts (MoE) has become the de facto architecture for hundred-billion-parameter language models, yet its advantages at sub-billion scales for on-device deployment remain largely unexplored. To close this gap, we present…

Deep Neural Networks are allowing mobile devices to incorporate a wide range of features into user applications. However, the computational complexity of these models makes it difficult to run them effectively on resource-constrained mobile…

Deploying deep learning models on mobile devices draws more and more attention recently. However, designing an efficient inference engine on devices is under the great challenges of model compatibility, device diversity, and resource…

Fine-tuning large language models (LLMs) with backpropagation\textemdash even for a subset of parameters such as LoRA\textemdash can be much more memory-consuming than inference and is often deemed impractical for resource-constrained…

Unified multimodal models can both understand and generate visual content within a single architecture. Existing models, however, remain data-hungry and too heavy for deployment on edge devices. We present Mobile-O, a compact…

This paper aims at addressing the problem of substantial performance degradation at extremely low computational cost (e.g. 5M FLOPs on ImageNet classification). We found that two factors, sparse connectivity and dynamic activation function,…

The increased importance of mobile photography created a need for fast and performant RAW image processing pipelines capable of producing good visual results in spite of the mobile camera sensor limitations. While deep learning-based…

We tackle the problem of automatic portrait matting on mobile devices. The proposed model is aimed at attaining real-time inference on mobile devices with minimal degradation of model performance. Our model MMNet, based on multi-branch…

Previous research on lightweight models has primarily focused on CNNs and Transformer-based designs. CNNs, with their local receptive fields, struggle to capture long-range dependencies, while Transformers, despite their global modeling…

Recently, Neural architecture search has achieved great success on classification tasks for mobile devices. The backbone network for object detection is usually obtained on the image classification task. However, the architecture which is…

Convolutional Neural Networks (ConvNets) are commonly developed at a fixed resource budget, and then scaled up for better accuracy if more resources are available. In this paper, we systematically study model scaling and identify that…

Deep convolutional neural networks have achieved remarkable success in computer vision. However, deep neural networks require large computing resources to achieve high performance. Although depthwise separable convolution can be an…

With the growing workload of inference tasks on mobile devices, state-of-the-art neural architectures (NAs) are typically designed through Neural Architecture Search (NAS) to identify NAs with good tradeoffs between accuracy and efficiency…

Recent research on vision backbone architectures has predominantly focused on optimizing efficiency for hardware platforms with high parallel processing capabilities. This category increasingly includes embedded systems such as mobile…

Scaling up model size and training data has advanced foundation models for instance-level perception, achieving state-of-the-art in-domain and zero-shot performance across object detection and segmentation. However, their high computational…

Lightweight vision classification models such as MobileNet, ShuffleNet, and EfficientNet are increasingly deployed in mobile and embedded systems, yet their performance has been predominantly benchmarked on ImageNet. This raises critical…

Human pose estimation from image and video is a vital task in many multimedia applications. Previous methods achieve great performance but rarely take efficiency into consideration, which makes it difficult to implement the networks on…

We present a novel high frequency residual learning framework, which leads to a highly efficient multi-scale network (MSNet) architecture for mobile and embedded vision problems. The architecture utilizes two networks: a low resolution…