Author name cluster

Cong Zhao

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

5 papers

1 author row

IS Journal 2025 Journal Article

Edge–Cloud Collaborative Real-Time Video Object Detection for Industrial Surveillance Systems

Siyan Guo
Cong Zhao
Shusen Yang
Yingying Liang
Yimeng Wang
Qing Han

Industrial video surveillance systems play a pivotal role in smart industry, prioritizing safety protection. Object detection resorting to deep neural networks (DNNs) is promising in achieving accurate and autonomous localization and identification of anomalies in video frames, supporting broad intelligent video surveillance applications. However, existing approaches are either computation- or communication-intensive. Limited by the constrained resources of industrial systems, they usually suffer from a high end-to-end (E2E) latency, and cannot be directly applied to latency-sensitive applications. In this article, we present a light-weight edge–cloud collaborative branchy DNN, CombiNet, and customize an intelligent edge device, Edge–Vbox, to construct an effective real-time video object detection solution. In our case study of intelligent smart grid substation operation and maintenance, experimental results using real-world data demonstrate that our approach significantly outperforms state-of-the-art methods in E2E latency, and manages to achieve real-time video object detection with negligible accuracy loss.

Details DOI

AAAI Conference 2024 Conference Paper

Generative Model-Based Feature Knowledge Distillation for Action Recognition

Guiqin Wang
Peng Zhao
Yanjiang Shi
Cong Zhao
Shusen Yang

Knowledge distillation (KD), a technique widely employed in computer vision, has emerged as a de facto standard for improving the performance of small neural networks. However, prevailing KD-based approaches in video tasks primarily focus on designing loss functions and fusing cross-modal information. This overlooks the spatial-temporal feature semantics, resulting in limited advancements in model compression. Addressing this gap, our paper introduces an innovative knowledge distillation framework, with the generative model for training a lightweight student model. In particular, the framework is organized into two steps: the initial phase is Feature Representation, wherein a generative model-based attention module is trained to represent feature semantics; Subsequently, the Generative-based Feature Distillation phase encompasses both Generative Distillation and Attention Distillation, with the objective of transferring attention-based feature semantics with the generative model. The efficacy of our approach is demonstrated through comprehensive experiments on diverse popular datasets, proving considerable enhancements in video action recognition task. Moreover, the effectiveness of our proposed framework is validated in the context of more intricate video action detection task. Our code is available at https://github.com/aaai-24/Generative-based-KD.

PDF Details DOI

IS Journal 2023 Journal Article

ECCVideo: A Scalable Edge Cloud Collaborative Video Analysis System

Qing Han
Xuebin Ren
Peng Zhao
Yimeng Wang
Luhui Wang
Cong Zhao
Xinyu Yang

Video analysis drives a wide range of applications in the fields of public safety, autonomous vehicles, etc. , with the great potential to impact society. Traditional cloud-based approaches are not applicable because of prohibitive bandwidth consumption and high response latency, while simply edge-based video analysis suffers from large computation delay, considering the restricted computing capacity of edge servers. Therefore, in this article, we focus on low-latency edge-cloud collaborative video analytic applications (ECCVApps) by making full use of resources at both the edge and cloud. Particularly, we present an edge-cloud collaborative video analysis system called ECCVideo, to support the unified management of heterogeneous servers and facilitate the development and deployment of large-scale ECCVApps. Under ECCVideo, we design the application architecture of ECCVApps, including presentation paradigm, transparent communication services, and full lifecycle management. To validate the proposed system, a real-time object detection application is deployed on the ECCVideo prototype.

Details DOI

IJCAI Conference 2020 Conference Paper

CDC: Classification Driven Compression for Bandwidth Efficient Edge-Cloud Collaborative Deep Learning

Yuanrui Dong
Peng Zhao
Hanqiao Yu
Cong Zhao
Shusen Yang

The emerging edge-cloud collaborative Deep Learning (DL) paradigm aims at improving the performance of practical DL implementations in terms of cloud bandwidth consumption, response latency, and data privacy preservation. Focusing on bandwidth efficient edge-cloud collaborative training of DNN-based classifiers, we present CDC, a Classification Driven Compression framework that reduces bandwidth consumption while preserving classification accuracy of edge-cloud collaborative DL. Specifically, to reduce bandwidth consumption, for resource-limited edge servers, we develop a lightweight autoencoder with a classification guidance for compression with classification driven feature preservation, which allows edges to only upload the latent code of raw data for accurate global training on the Cloud. Additionally, we design an adjustable quantization scheme adaptively pursuing the tradeoff between bandwidth consumption and classification accuracy under different network conditions, where only fine-tuning is required for rapid compression ratio adjustment. Results of extensive experiments demonstrate that, compared with DNN training with raw data, CDC consumes 14. 9× less bandwidth with an accuracy loss no more than 1. 06%, and compared with DNN training with data compressed by AE without guidance, CDC introduces at least 100% lower accuracy loss.

PDF Details DOI

NeurIPS Conference 2017 Conference Paper

Towards Accurate Binary Convolutional Neural Network

Xiaofan Lin
Cong Zhao
Wei Pan

We introduce a novel scheme to train binary convolutional neural networks (CNNs) -- CNNs with weights and activations constrained to {-1, +1} at run-time. It has been known that using binary weights and activations drastically reduce memory size and accesses, and can replace arithmetic operations with more efficient bitwise operations, leading to much faster test-time inference and lower power consumption. However, previous works on binarizing CNNs usually result in severe prediction accuracy degradation. In this paper, we address this issue with two major innovations: (1) approximating full-precision weights with the linear combination of multiple binary weight bases; (2) employing multiple binary activations to alleviate information loss. The implementation of the resulting binary CNN, denoted as ABC-Net, is shown to achieve much closer performance to its full-precision counterpart, and even reach the comparable prediction accuracy on ImageNet and forest trail datasets, given adequate binary weight bases and activations.

PDF Details