{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/strengths-and-weaknesses-of-deep-learning","title":"Strengths and Weaknesses of Deep Learning Models for Face Recognition Against Image Degradations","arxiv_id":"1710.01494","date":"2017-10-04","proceeding":null,"authors":["Klemen Grm","Vitomir Štruc","Anais Artiges","Matthieu Caron","Hazim Kemal Ekenel"],"abstract":"Deep convolutional neural networks (CNNs) based approaches are the\nstate-of-the-art in various computer vision tasks, including face recognition.\nConsiderable research effort is currently being directed towards further\nimproving deep CNNs by focusing on more powerful model architectures and better\nlearning techniques. However, studies systematically exploring the strengths\nand weaknesses of existing deep models for face recognition are still\nrelatively scarce in the literature. In this paper, we try to fill this gap and\nstudy the effects of different covariates on the verification performance of\nfour recent deep CNN models using the Labeled Faces in the Wild (LFW) dataset.\nSpecifically, we investigate the influence of covariates related to: image\nquality -- blur, JPEG compression, occlusion, noise, image brightness,\ncontrast, missing pixels; and model characteristics -- CNN architecture, color\ninformation, descriptor computation; and analyze their impact on the face\nverification performance of AlexNet, VGG-Face, GoogLeNet, and SqueezeNet. Based\non comprehensive and rigorous experimentation, we identify the strengths and\nweaknesses of the deep learning models, and present key areas for potential\nfuture research. Our results indicate that high levels of noise, blur, missing\npixels, and brightness have a detrimental effect on the verification\nperformance of all models, whereas the impact of contrast changes and\ncompression artifacts is limited. It has been found that the descriptor\ncomputation strategy and color information does not have a significant\ninfluence on performance.","url_abs":"http://arxiv.org/abs/1710.01494v1","url_pdf":"http://arxiv.org/pdf/1710.01494v1.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":"strengths-and-weaknesses-of-deep-learning","repo_url":"https://github.com/kgrm/face-recog-eval","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"face-recognition","task_name":"Face Recognition"},{"task_slug":"face-verification","task_name":"Face Verification"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"auxiliary-classifier","method_name":"Auxiliary Classifier"},{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"fire-module","method_name":"Fire Module"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"googlenet","method_name":"GoogLeNet"},{"method_slug":"grouped-convolution","method_name":"Grouped Convolution"},{"method_slug":"inception-module","method_name":"Inception Module"},{"method_slug":"local-response-normalization","method_name":"Local Response Normalization"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"squeezenet","method_name":"SqueezeNet"},{"method_slug":"xavier-initialization","method_name":"Xavier Initialization"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1710.01494","atlas_url":"https://app.syntology.ai/?focus=1710.01494","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"1710.01494"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1710.01494\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1710.01494"},"call":"get_concepts_for_paper(arxiv_id=\"1710.01494\")"}],"by_repo":[{"repo":"kgrm/face-recog-eval","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"19a274e58570ee153502ece474d546c651f6351f9879dbd70c9081b7756f3cec","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}