{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/dctd-deep-conditional-target-densities-for","title":"Energy-Based Models for Deep Probabilistic Regression","arxiv_id":"1909.12297","date":"2019-09-26","proceeding":"ECCV 2020 8","authors":["Fredrik K. Gustafsson","Martin Danelljan","Goutam Bhat","Thomas B. Schön"],"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.","url_abs":"https://arxiv.org/abs/1909.12297v4","url_pdf":"https://arxiv.org/pdf/1909.12297v4.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"dctd-deep-conditional-target-densities-for","repo_url":"https://github.com/fregu856/ebms_regression","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"dctd-deep-conditional-target-densities-for","repo_url":"https://github.com/soran-ghaderi/torchebm","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"head-pose-estimation","task_name":"Head Pose Estimation"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"pose-estimation","task_name":"Pose Estimation"},{"task_slug":"visual-object-tracking","task_name":"Visual Object Tracking"},{"task_slug":"visual-tracking","task_name":"Visual Tracking"},{"task_slug":"object-detection-1","task_name":"object-detection"},{"task_slug":"regression-1","task_name":"regression"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/visual-object-tracking-on-trackingnet","task":"Visual Object Tracking","dataset":"TrackingNet","model":"ATOM(Resnet18)+EnergyRegression","rank_in_archive_order":40,"of":40,"metrics":{"Normalized Precision":"80.1","Precision":"69.7","Success Rate":"74.5"},"uses_additional_data":false},{"leaderboard":"/sota/visual-object-tracking-on-uav123","task":"Visual Object Tracking","dataset":"UAV123","model":"ATOM(Resnet18)+EnergyRegression","rank_in_archive_order":14,"of":16,"metrics":{"AUC":"0.672"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}