CHASE: Robust Visual Tracking via Cell-Level Differentiable Neural Architecture Search

A strong visual object tracker nowadays relies on its well-crafted modules, which typically consist of manually-designed network architectures to deliver high-quality tracking results. Not surprisingly, the manual design process becomes a particularly challenging barrier, as it demands sufficient prior experience, enormous effort, intuition and perhaps some good luck. Meanwhile, neural architecture search has gaining grounds in practical applications such as image segmentation, as a promising method in tackling the issue of automated search of feasible network structures. In this work, we propose a novel cell-level differentiable architecture search mechanism to automate the network design of the tracking module, aiming to adapt backbone features to the objective of a tracking network during offline training. The proposed approach is simple, efficient, and with no need to stack a series of modules to construct a network. Our approach is easy to be incorporated into existing trackers, which is empirically validated using different differentiable architecture search-based methods and tracking objectives. Extensive experimental evaluations demonstrate the superior performance of our approach over five commonly-used benchmarks. Meanwhile, our automated searching process takes 41 (18) hours for the second (first) order DARTS method on the TrackingNet dataset.


page 1

page 2


Flexible Channel Dimensions for Differentiable Architecture Search

Finding optimal channel dimensions (i.e., the number of filters in DNN l...

Network Graph Based Neural Architecture Search

Neural architecture search enables automation of architecture design. De...

NASGEM: Neural Architecture Search via Graph Embedding Method

Neural Architecture Search (NAS) automates and prospers the design of ne...

RandomNet: Towards Fully Automatic Neural Architecture Design for Multimodal Learning

Almost all neural architecture search methods are evaluated in terms of ...

Heart-Darts: Classification of Heartbeats Using Differentiable Architecture Search

Arrhythmia is a cardiovascular disease that manifests irregular heartbea...

Scheduled Differentiable Architecture Search for Visual Recognition

Convolutional Neural Networks (CNN) have been regarded as a capable clas...

Are Labels Necessary for Neural Architecture Search?

Existing neural network architectures in computer vision — whether desig...

Please sign up or login with your details

Forgot password? Click here to reset