Real-Time Correlation Tracking via Joint Model Compression and Transfer

by   Ning Wang, et al.

Correlation filters (CF) have received considerable attention in visual tracking because of their computational efficiency. Leveraging deep features via off-the-shelf CNN models (e.g., VGG), CF trackers achieve state-of-the-art performance while consuming a large number of computing resources. This limits deep CF trackers to be deployed to many mobile platforms on which only a single-core CPU is available. In this paper, we propose to jointly compress and transfer off-the-shelf CNN models within a knowledge distillation framework. We formulate a CNN model pretrained from the image classification task as a teacher network, and distill this teacher network into a lightweight student network as the feature extractor to speed up CF trackers. In the distillation process, we propose a fidelity loss to enable the student network to maintain the representation capability of the teacher network. Meanwhile, we design a tracking loss to adapt the objective of the student network from object recognition to visual tracking. The distillation process is performed offline on multiple layers and adaptively updates the student network using a background-aware online learning scheme. Extensive experiments on five challenging datasets demonstrate that the lightweight student network accelerates the speed of state-of-the-art deep CF trackers to real-time on a single-core CPU while maintaining almost the same tracking accuracy.


page 1

page 3

page 5

page 10


Teacher-Students Knowledge Distillation for Siamese Trackers

With the development of Siamese network based trackers, a variety of tec...

A Distilled Model for Tracking and Tracker Fusion

Visual object tracking was generally tackled by reasoning independently ...

AttTrack: Online Deep Attention Transfer for Multi-object Tracking

Multi-object tracking (MOT) is a vital component of intelligent video an...

Weakly-Supervised Domain Adaptation of Deep Regression Trackers via Reinforced Knowledge Distillation

Deep regression trackers are among the fastest tracking algorithms avail...

Online Hybrid Lightweight Representations Learning: Its Application to Visual Tracking

This paper presents a novel hybrid representation learning framework for...

Learning Background-Aware Correlation Filters for Visual Tracking

Correlation Filters (CFs) have recently demonstrated excellent performan...

Efficient Crowd Counting via Structured Knowledge Transfer

Crowd counting is an application-oriented task and its inference efficie...

Please sign up or login with your details

Forgot password? Click here to reset