ROAM: Recurrently Optimizing Tracking Model
arXiv:1907.12006
Abstract
In this paper, we design a tracking model consisting of response generation and bounding box regression, where the first component produces a heat map to indicate the presence of the object at different positions and the second part regresses the relative bounding box shifts to anchors mounted on sliding-window locations. Thanks to the resizable convolutional filters used in both components to adapt to the shape changes of objects, our tracking model does not need to enumerate different sized anchors, thus saving model parameters. To effectively adapt the model to appearance variations, we propose to offline train a recurrent neural optimizer to update tracking model in a meta-learning setting, which can converge the model in a few gradient steps. This improves the convergence speed of updating the tracking model while achieving better performance. We extensively evaluate our trackers, ROAM and ROAM++, on the OTB, VOT, LaSOT, GOT-10K and TrackingNet benchmark and our methods perform favorably against state-of-the-art algorithms.
arXiv commentCVPR2020 camera ready
References in corpus (17)
- Adam: A Method for Stochastic Optimization
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
- Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
- 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
- Siamese Instance Search for Tracking
- Meta Learning Shared Hierarchies
- Deeper and Wider Siamese Networks for Real-Time Visual Tracking
- Distractor-aware Siamese Networks for Visual Object Tracking
- CREST: Convolutional Residual Learning for Visual Tracking
- VITAL: VIsual Tracking via Adversarial Learning
- TrackingNet: A Large-Scale Dataset and Benchmark for Object Tracking in the Wild
- Learning Gradient Descent: Better Generalization and Longer Horizons
- Unsupervised Deep Tracking
- Visual Tracking via Dynamic Memory Networks