Learning Feature Embeddings for Discriminant Model based Tracking

Abstract

After observing that the features used in most online discriminatively trained trackers are not optimal, in this paper, we propose a novel and effective architecture to learn optimal feature embeddings for online discriminative tracking. Our method, called DCFST, integrates the solver of a discriminant model that is differentiable and has a closed-form solution into convolutional neural networks. Then, the resulting network can be trained in an end-to-end way, obtaining optimal feature embeddings for the discriminant model-based tracker. As an instance, we apply the popular ridge regression model in this work to demonstrate the power of DCFST. Extensive experiments on six public benchmarks, OTB2015, NFS, GOT10k, TrackingNet, VOT2018, and VOT2019, show that our approach is efficient and generalizes well to class-agnostic target objects in online tracking, thus achieves state-of-the-art accuracy, while running beyond the real-time speed. Code will be made available.

arXiv comment15 pages, 5 figures, accepted by ECCV2020

References in corpus (6)

• Adam: A Method for Stochastic Optimization
• High-Speed Tracking with Kernelized Correlation Filters
• GOT-10k: A Large High-Diversity Benchmark for Generic Object Tracking in the Wild
• Beyond Correlation Filters: Learning Continuous Convolution Operators for Visual Tracking
• Good Features to Correlate for Visual Tracking
• Parallel Tracking and Verifying: A Framework for Real-Time and High Accuracy Visual Tracking

Cited by in corpus (3)

• Learning to Filter: Siamese Relation Network for Robust Tracking
• Real-Time Visual Object Tracking via Few-Shot Learning
• Meta-Forecasting by combining Global Deep Representations with Local Adaptation