paper-with-me

Papers

ApproxDet: Content and Contention-Aware Approximate Object Detection for Mobiles

2020-10-21 · ran Xu, Chen-Lin Zhang, Pengcheng Wang, Jayoung Lee, Subrata Mitra, Somali Chaterji, Yin Li, Saurabh Bagchi

Advanced video analytic systems, including scene classification and object detection, have seen widespread success in various domains such as smart cities and autonomous transportation. With an ever-growing number of powerful client devices, there is incentive to move these heavy video analytics workloads from the cloud to mobile devices to achieve low latency and real-time processing and to preserve user privacy. However, most video analytic systems are heavyweight and are trained offline with some pre-defined latency or accuracy requirements. This makes them unable to adapt at runtime in the face of three types of dynamism -- the input video characteristics change, the amount of compute resources available on the node changes due to co-located applications, and the user's latency-accuracy requirements change. In this paper we introduce ApproxDet, an adaptive video object detection framework for mobile devices to meet accuracy-latency requirements in the face of changing content and resource contention scenarios. To achieve this, we introduce a multi-branch object detection kernel (layered on Faster R-CNN), which incorporates a data-driven modeling approach on the performance metrics, and a latency SLA-driven scheduler to pick the best execution branch at runtime. We couple this kernel with approximable video object tracking algorithms to create an end-to-end video object detection system. We evaluate ApproxDet on a large benchmark video dataset and compare quantitatively to AdaScale and YOLOv3. We find that ApproxDet is able to adapt to a wide variety of contention and content characteristics and outshines all baselines, e.g., it achieves 52% lower latency and 11.1% higher accuracy over YOLOv3.

📄 PDF Abstract BibTeX arXiv:2010.10754

Code (1)

StarsThu2016/ApproxDet 공식 구현 tf

Tasks

Objectobject-detectionObject DetectionObject TrackingScene ClassificationVideo Object DetectionVideo Object Tracking

Methods 이 논문이 사용한 방법론

Average Pooling 설명 없음
Global Average Pooling Global Average Pooling is a pooling operation designed to replace fully connected layers in classical CNNs. The idea is to generate one feature map for each corresponding…
1x1 Convolution A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction,…
Batch Normalization 설명 없음
Logistic Regression Logistic Regression, despite its name, is a linear model for classification rather than regression. Logistic regression is also known in the literature as logit regression,…
Residual Connection 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

Similar Papers 제목 키워드 기반

DecomPose: Disentangling Cross-Category Optimization Contention for Category-Level 6D Object Pose Estimation

2026-05-15 · Yifan Gao, Lu Zou, Zhangjin Huang, Guoping Wang arxiv

Category-level 6D object pose estimation is typically formulated as a multi-category joint learning problem with fully shared model parameters. However, pronounced geometric heterogeneity across categories entangles inco…

Pose Estimation

Network Contention-Aware Cluster Scheduling with Reinforcement Learning

2023-10-31 · Junyeol Ryu, Jeongyoon Eo

With continuous advances in deep learning, distributed training is becoming common in GPU clusters. Specifically, for emerging workloads with diverse amounts, ratios, and patterns of communication, we observe that networ…

GPUreinforcement-learningReinforcement LearningScheduling

Dora: QoE-Aware Hybrid Parallelism for Distributed Edge AI

2025-12-09 · Jianli Jin, Ziyang Lin, Qianli Dong, Yi Chen 외 arxiv

With the proliferation of edge AI applications, satisfying user quality of experience (QoE) requirements, such as model inference latency, has become a first class objective, as these models operate in resource constrain…

Communication Contention Aware Scheduling of Multiple Deep Learning Training Jobs

2020-02-24 · Qiang Wang, Shaohuai Shi, Canhui Wang, Xiaowen Chu

Distributed Deep Learning (DDL) has rapidly grown its popularity since it helps boost the training performance on high-performance GPU clusters. Efficient job scheduling is indispensable to maximize the overall performan…

Deep LearningGPUScheduling

Taming the Tail: NoI Topology Synthesis for Mixed DL Workloads on Chiplet-Based Accelerators

2025-10-28 · Arnav Shukla, Harsh Sharma, Srikant Bharadwaj, Vinayak Abrol 외 arxiv

Heterogeneous chiplet-based systems improve scaling by disag-gregating CPUs/GPUs and emerging technologies (HBM/DRAM).However this on-package disaggregation introduces a latency inNetwork-on-Interposer(NoI). We observe t…