Oregon State University

Can’t find an event? We’re busy migrating to a new event calendar. Try looking new calendar



Event Details

MS Final Examination – Trevor Fiez

Wednesday, June 14, 2017 12:30 PM - 2:30 PM

An Analysis of Training Methodologies for Deep Visual Tracking
This paper studies the problem of training convolutional neural networks for online visual tracking. A major challenge single object visual tracking is that most training sets with frame-level track annotations are quite small, due to the prohibitive cost of manual annotation. Thus, current training approaches either supplement the annotations with other data sources (e.g., object-detection training data) or generate noisy variants of the track annotations. In either case, the data generation and training methods have ignored the fact that tracking involves sequences of decisions (one per frame) that are dependent on one another. Thus, the objectives optimized by these learning algorithms are not directly tied to the end goal of tracking performance. To further study this issue, we consider the state-of-the-art imitation learning algorithm, DAGGER, for training an online tracker. We observe that the DAGGER faces difficulty when applied to tracking, because online trackers typically experience unrecoverable failures, especially early in training. Our main contribution is to compare different training methods across a variety of datasets on multiple trackers. We also introduce, analyze, and evaluate a variation of DAGGER, called DAGGER with Resets (DAGGER^2), a novel imitation learning framework which maintains the theoretical properties of DAGGER and is more appropriate for training deep trackers. Our experimental results show this principled training approach and random augmentation is able to outperform existing training approaches across multiple visual tracking datasets.

Major Advisor: Alan Fern
Co-Major Advisor: Sinisa Todorovic
Committee: Fuxin Li
GCR: Yelda Turkan

Kelley Engineering Center (campus map)
Calvin Hughes
1 541 737 3168
Calvin.Hughes at oregonstate.edu
Sch Elect Engr/Comp Sci
This event appears on the following calendars: