{"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/how-to-train-your-energy-based-model-for","title":"How to Train Your Energy-Based Model for Regression","arxiv_id":"2005.01698","date":"2020-05-04","proceeding":null,"authors":["Fredrik K. Gustafsson","Martin Danelljan","Radu Timofte","Thomas B. Schön"],"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.","url_abs":"https://arxiv.org/abs/2005.01698v2","url_pdf":"https://arxiv.org/pdf/2005.01698v2.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":"how-to-train-your-energy-based-model-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":"how-to-train-your-energy-based-model-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":"object-detection","task_name":"Object Detection"},{"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-lasot","task":"Visual Object Tracking","dataset":"LaSOT","model":"DiMP-NCE+","rank_in_archive_order":40,"of":46,"metrics":{"AUC":"63.7"},"uses_additional_data":false},{"leaderboard":"/sota/visual-object-tracking-on-needforspeed","task":"Visual Object Tracking","dataset":"NeedForSpeed","model":"DiMP-NCE+","rank_in_archive_order":10,"of":10,"metrics":{"AUC":"0.65"},"uses_additional_data":false},{"leaderboard":"/sota/visual-object-tracking-on-otb-100","task":"Visual Object Tracking","dataset":"OTB-100","model":"DiMP-NCE+","rank_in_archive_order":1,"of":2,"metrics":{"AUC":"0.707"},"uses_additional_data":false},{"leaderboard":"/sota/visual-object-tracking-on-trackingnet","task":"Visual Object Tracking","dataset":"TrackingNet","model":"DiMP-NCE+","rank_in_archive_order":39,"of":40,"metrics":{"AUC":"0.787","Normalized Precision":"83.7","Precision":"73.7","Success Rate":"0.787"},"uses_additional_data":false},{"leaderboard":"/sota/visual-object-tracking-on-uav123","task":"Visual Object Tracking","dataset":"UAV123","model":"DiMP-NCE+","rank_in_archive_order":15,"of":16,"metrics":{"AUC":"0.672"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2005.01698","atlas_url":"https://app.syntology.ai/?focus=2005.01698","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.01698"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/fregu856/ebms_regression","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/soran-ghaderi/torchebm","reach":{"status":"unanswered"}}],"summary":{"unverified":3},"by_repo_kind":{"official":{"samples":3,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"3622fbd7127e10a1","entry":"gauss_density_centered","repo":"fregu856/ebms_regression","repo_kind":"official","path":"1dregression/1/kldis_train.py","file_url":"https://github.com/fregu856/ebms_regression/blob/HEAD/1dregression/1/kldis_train.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3622fbd7127e10a1"}},{"code_sha256_prefix":"17bacf3fbd08edd2","entry":"gmm_density_centered","repo":"fregu856/ebms_regression","repo_kind":"official","path":"1dregression/1/kldis_train.py","file_url":"https://github.com/fregu856/ebms_regression/blob/HEAD/1dregression/1/kldis_train.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"17bacf3fbd08edd2"}},{"code_sha256_prefix":"8c554909dd2676ce","entry":"sample_gmm_centered","repo":"fregu856/ebms_regression","repo_kind":"official","path":"1dregression/1/kldis_train.py","file_url":"https://github.com/fregu856/ebms_regression/blob/HEAD/1dregression/1/kldis_train.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8c554909dd2676ce"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}