Energy-Based Models for Deep Probabilistic Regression

September 26, 2019 Β· Entered Twilight Β· πŸ› arXiv.org

πŸŒ… TWILIGHT: Old Age
Predates the code-sharing era β€” a pioneer of its time

"Last commit was 5.0 years ago (β‰₯5 year threshold)"

Evidence collected by the PWNC Scanner

Repo contents: 1dregression, LICENSE, README.md, detection, ebms_regression.png

Authors Fredrik K. Gustafsson, Martin Danelljan, Goutam Bhat, Thomas B. Schân arXiv ID 1909.12297 Category cs.LG: Machine Learning Cross-listed cs.CV, stat.ML Citations 4 Venue arXiv.org Repository https://github.com/fregu856/ebms_regression ⭐ 106 Last Checked 2 months ago
Abstract
While deep learning-based classification is generally tackled using standardized approaches, a wide variety of techniques are employed for regression. In computer vision, one particularly popular such technique is that of confidence-based regression, which entails predicting a confidence value for each input-target pair (x,y). While this approach has demonstrated impressive results, it requires important task-dependent design choices, and the predicted confidences lack a natural probabilistic meaning. We address these issues by proposing a general and conceptually simple regression method with a clear probabilistic interpretation. In our proposed approach, we create an energy-based model of the conditional target density p(y|x), using a deep neural network to predict the un-normalized density from (x,y). This model of p(y|x) is trained by directly minimizing the associated negative log-likelihood, approximated using Monte Carlo sampling. We perform comprehensive experiments on four computer vision regression tasks. Our approach outperforms direct regression, as well as other probabilistic and confidence-based methods. Notably, our model achieves a 2.2% AP improvement over Faster-RCNN for object detection on the COCO dataset, and sets a new state-of-the-art on visual tracking when applied for bounding box estimation. In contrast to confidence-based methods, our approach is also shown to be directly applicable to more general tasks such as age and head-pose estimation. Code is available at https://github.com/fregu856/ebms_regression.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

πŸ“œ Similar Papers

In the same crypt β€” Machine Learning