An official website of the United States government
Vision transformers (ViTs) have dominated computer vision in recent years. However, ViTs are computationally expensive and not well suited for mobile devices; this led to the prevalence of convolutional neural network (CNN) and ViT-based hybrid models for mobile vision applications. Recently, Vision GNN (ViG) and CNN hybrid models have also been proposed for mobile vision tasks. However, all of these methods remain slower compared to pure CNN-based models. In this work, we propose Multi-Level Dilated Convolutions to devise a purely CNN-based mobile backbone. Using Multi-Level Dilated Convolutions allows for a larger theoretical receptive field than standard convolutions. Different levels of dilation also allow for interactions between the short-range and long-range features in an image. Experiments show that our proposed model outperforms state-of-the-art (SOTA) mobile CNN, ViT, ViG, and hybrid architectures in terms of accuracy and/or speed on image classification, object detection, instance segmentation, and semantic segmentation. Our fastest model, RapidNet-Ti, achieves 76.3% top-1 accuracy on ImageNet-1K with 0.9 ms inference latency on an iPhone 13 mini NPU, which is faster and more accurate than MobileNetV2x1.4 (74.7% top-1 with 1.0 ms latency). Our work shows that pure CNN architectures can beat SOTA hybrid and ViT models in terms of accuracy and speed when designed properly
more »
« less
This content will become publicly available on August 5, 2026
TraceNet: Segment one thing efficiently
Efficient single instance segmentation is critical for unlocking features in on-the-fly mobile imaging applications, such as photo capture and editing. Existing mobile solutions often restrict segmentation to portraits or salient objects due to computational constraints. Recent advancements like the Segment Anything Model improve accuracy but remain computationally expensive for mobile, because it processes the entire image with heavy transformer backbones. To address this, we propose TraceNet, a one-click-driven single instance segmentation model. TraceNet segments a user-specified instance by back-tracing the receptive field of a ConvNet backbone, focusing computations on relevant regions and reducing inference cost and memory usage during mobile inference. Starting from user needs in real mobile applications, we define efficient single-instance segmentation tasks and introduce two novel metrics to evaluate both accuracy and robustness to low-quality input clicks. Extensive evaluations on the MS-COCO and LVIS datasets highlight TraceNet’s ability to generate high-quality instance masks efficiently and accurately while demonstrating robustness to imperfect user inputs.
more »
« less
- PAR ID:
- 10635560
- Publisher / Repository:
- IEEE
- Date Published:
- Page Range / eLocation ID:
- 1 to 5
- Subject(s) / Keyword(s):
- Efficient Segmentation Mobile Application Deep Learning Machine Learning
- Format(s):
- Medium: X
- Location:
- San Jose, California
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Scene reconstruction using Monodepth2 (Monocular Depth Inference) which provides depth maps from a single RGB camera, the outputs are filled with noise and inconsistencies. Instance segmentation using a Mask R-CNN (Region Based Convolution Neural Networks) deep model can provide object segmentation results in 2D but lacks 3D information. In this paper we propose to integrate the results of Instance segmentation via Mask R-CNN’s, CAD model Car Shape Alignment, and depth from Monodepth2 together with classical dynamic vision techniques to create a High-level Semantic Model with separability, robustness, consistency and saliency. The model is useful for both virtualized rendering, semantic augmented reality and automatic driving. Experimental results are provided to validate the approach.more » « less
-
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 devices. Prior work approached the problem of support- ing deep learning in mobile applications by either decreasing model complexity or utilizing powerful cloud servers. These approaches each only focus on a single aspect of mobile inference and thus they often sacrifice overall performance. In this work we introduce a holistic approach to designing mobile deep inference frameworks. We first identify the key goals of accuracy and latency for mobile deep inference and the conditions that must be met to achieve them. We demonstrate our holistic approach through the design of a hypothetical framework called MDINFERENCE. This framework leverages two complementary techniques; a model selection algorithm that chooses from a set of cloud-based deep learning models to improve inference accuracy and an on-device request duplication mechanism to bound latency. Through empirically-driven simulations we show that MDINFERENCE improves aggregate accuracy over static approaches by over 40% without incurring SLA violations. Additionally, we show that with a target latency of 250ms, MDINFERENCE increased the aggregate accuracy in 99.74% cases on faster university networks and 96.84% cases on residential networks.more » « less
-
Intelligent mobile image sensing powered by deep learning analyzes images captured by cameras from mobile devices, such as smartphones or smartwatches. It supports numerous mobile applications, such as image classification, face recognition, and camera scene detection. Unfortunately, mobile devices often lack the resources necessary for deep learning, leading to increased inference latency and rapid battery consumption. Moreover, the inference accuracy may decline over time due to potential data drift. To address these issues, we introduce a new cost-efficient framework, called Corun, designed to simultaneously handle multiple inference queries and continual model retraining/fine-tuning of a pre-trained model on a single commodity GPU in an edge server to significantly improve the inference throughput, upholding the inference accuracy. The scheduling method of Corun undertakes offline profiling to find the maximum number of concurrent inferences that can be executed along with a retraining job on a single GPU without incurring an out-of-memory error or significantly increasing the latency. Our evaluation verifies the cost-effectiveness of Corun. The inference throughput provided by Corun scales with the number of concurrent inference queries. However, the latency of inference queries and the length of a retraining epoch increase at substantially lower rates. By concurrently processing multiple inference and retraining tasks on one GPU instead of using a separate GPU for each task, Corun could reduce the number of GPUs and cost required to deploy mobile image sensing applications based on deep learning at the edge.more » « less
-
In this paper, we propose a novel mobile deep inference platform, MODI, that delivers good inference performance. MODI improves deep learning powered mobile applications performance with optimizations in three complementary aspects. First, MODI provides a number of models and dynamically selects the best one during runtime. Second, MODI extends the set of models each mobile application can use by storing high quality models at the edge servers. Third, MODI manages a centralized model repository and periodically updates models at edge locations, ensuring up-to-date models for mobile applications without incurring high network latency. Our evaluation demonstrates the feasibility of trading off inference accuracy for improved inference speed, as well as the acceptable performance of edge-based inference.more » « less
