{"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/octuplet-loss-make-face-recognition-robust-to","title":"Octuplet Loss: Make Face Recognition Robust to Image Resolution","arxiv_id":"2207.06726","date":"2022-07-14","proceeding":null,"authors":["Martin Knoche","Mohamed Elkadeem","Stefan Hörmann","Gerhard Rigoll"],"abstract":"Image resolution, or in general, image quality, plays an essential role in the performance of today's face recognition systems. To address this problem, we propose a novel combination of the popular triplet loss to improve robustness against image resolution via fine-tuning of existing face recognition models. With octuplet loss, we leverage the relationship between high-resolution images and their synthetically down-sampled variants jointly with their identity labels. Fine-tuning several state-of-the-art approaches with our method proves that we can significantly boost performance for cross-resolution (high-to-low resolution) face verification on various datasets without meaningfully exacerbating the performance on high-to-high resolution images. Our method applied on the FaceTransformer network achieves 95.12% face verification accuracy on the challenging XQLFW dataset while reaching 99.73% on the LFW database. Moreover, the low-to-low face verification accuracy benefits from our method. We release our code to allow seamless integration of the octuplet loss into existing frameworks.","url_abs":"https://arxiv.org/abs/2207.06726v2","url_pdf":"https://arxiv.org/pdf/2207.06726v2.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":"octuplet-loss-make-face-recognition-robust-to","repo_url":"https://github.com/martlgap/octuplet-loss","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"octuplet-loss-make-face-recognition-robust-to","repo_url":"https://github.com/Faceplugin-ltd/FaceRecognition-Android","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"face-recognition","task_name":"Face Recognition"},{"task_slug":"face-verification","task_name":"Face Verification"},{"task_slug":null,"task_name":"Triplet"}],"methods":[{"method_slug":"triplet-loss","method_name":"Triplet Loss"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/face-recognition-on-lfw","task":"Face Recognition","dataset":"LFW","model":"FaceTransformer+OctupletLoss","rank_in_archive_order":10,"of":16,"metrics":{"Accuracy":"0.9973"},"uses_additional_data":true},{"leaderboard":"/sota/face-recognition-on-xqlfw","task":"Face Recognition","dataset":"XQLFW","model":"FaceTransformer+OctupletLoss","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy":"0.9512"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}