How to Train Your Energy-Based Model for Regression
OPEN ACCESS
Loading...
Author / Producer
Date
2020
Publication Type
Conference Paper
ETH Bibliography
yes
Citations
Altmetric
OPEN ACCESS
Data
Rights / License
Abstract
Energy-based models (EBMs) have become increasingly popular within computer vision in recent years. While they are commonly employed for generative image modeling, recent work has applied EBMs also for regression tasks, achieving state-of-the-art performance on object detection and visual tracking. Training EBMs is however known to be challenging. While a variety of different techniques have been explored for generative modeling, the application of EBMs to regression is not a well-studied problem. How EBMs should be trained for best possible regression performance is thus currently unclear. We therefore accept the task of providing the first detailed study of this problem. To that end, we propose a simple yet highly effective extension of noise contrastive estimation, and carefully compare its performance to six popular methods from literature on the tasks of 1D regression and object detection. The results of this comparison suggest that our training method should be considered the go-to approach. We also apply our method to the visual tracking task, achieving state-of-the-art performance on five datasets. Notably, our tracker achieves 63.7% AUC on LaSOT and 78.7% Success on TrackingNet. Code is available at https://github.com/fregu856/ebms_regression.
Permanent link
Publication status
published
Editor
Book title
BMVC 2020: Accepted Papers
Journal / series
Volume
Pages / Article No.
154
Publisher
British Machine Vision Association
Event
31st British Machine Vision Virtual Conference (BMVC 2020)
Edition / version
Methods
Software
Geographic location
Date collected
Date created
Subject
Energy-based models; Regression; Visual tracking; Object detection; Noise contrastive estimation
Organisational unit
03514 - Van Gool, Luc (emeritus) / Van Gool, Luc (emeritus)
Notes
Due to the Coronavirus (COVID-19) the conference was conducted virtually.