How to Train Your Energy-Based Model for Regression

by   Fredrik K. Gustafsson, et al.

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, setting a new state-of-the-art on five datasets. Notably, our tracker achieves 63.7 LaSOT and 78.7


Probabilistic Regression for Visual Tracking

Visual tracking is fundamentally the problem of regressing the state of ...

Accurate 3D Object Detection using Energy-Based Models

Accurate 3D object detection (3DOD) is crucial for safe navigation of co...

RepPoints V2: Verification Meets Regression for Object Detection

Verification and regression are two general methodologies for prediction...

Improved Techniques for Learning to Dehaze and Beyond: A Collective Study

This paper reviews the collective endeavors by the team of authors in ex...

DCTD: Deep Conditional Target Densities for Accurate Regression

While deep learning-based classification is generally addressed using st...

Learning Proposals for Practical Energy-Based Regression

Energy-based models (EBMs) have experienced a resurgence within machine ...

Representation Based Regression for Object Distance Estimation

In this study, we propose a novel approach to predict the distances of t...

Code Repositories


Official implementation of "Energy-Based Models for Deep Probabilistic Regression" (ECCV 2020) and "How to Train Your Energy-Based Model for Regression" (BMVC 2020).

view repo