{"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/strike-with-a-pose-neural-networks-are-easily","title":"Strike (with) a Pose: Neural Networks Are Easily Fooled by Strange Poses of Familiar Objects","arxiv_id":"1811.11553","date":"2018-11-28","proceeding":"CVPR 2019 6","authors":["Michael A. Alcorn","Qi Li","Zhitao Gong","Chengfei Wang","Long Mai","Wei-Shinn Ku","Anh Nguyen"],"abstract":"Despite excellent performance on stationary test sets, deep neural networks\n(DNNs) can fail to generalize to out-of-distribution (OoD) inputs, including\nnatural, non-adversarial ones, which are common in real-world settings. In this\npaper, we present a framework for discovering DNN failures that harnesses 3D\nrenderers and 3D models. That is, we estimate the parameters of a 3D renderer\nthat cause a target DNN to misbehave in response to the rendered image. Using\nour framework and a self-assembled dataset of 3D objects, we investigate the\nvulnerability of DNNs to OoD poses of well-known objects in ImageNet. For\nobjects that are readily recognized by DNNs in their canonical poses, DNNs\nincorrectly classify 97% of their pose space. In addition, DNNs are highly\nsensitive to slight pose perturbations. Importantly, adversarial poses transfer\nacross models and datasets. We find that 99.9% and 99.4% of the poses\nmisclassified by Inception-v3 also transfer to the AlexNet and ResNet-50 image\nclassifiers trained on the same ImageNet dataset, respectively, and 75.5%\ntransfer to the YOLOv3 object detector trained on MS COCO.","url_abs":"http://arxiv.org/abs/1811.11553v3","url_pdf":"http://arxiv.org/pdf/1811.11553v3.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":"strike-with-a-pose-neural-networks-are-easily","repo_url":"https://github.com/airalcorn2/strike-with-a-pose","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"GPL-3.0"}}],"tasks":[],"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":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"grouped-convolution","method_name":"Grouped Convolution"},{"method_slug":"inception-v3","method_name":"Inception-v3"},{"method_slug":"inception-v3-module","method_name":"Inception-v3 Module"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"local-response-normalization","method_name":"Local Response Normalization"},{"method_slug":"logistic-regression","method_name":"Logistic Regression"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"rmsprop","method_name":"RMSProp"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"yolov3","method_name":"YOLOv3"},{"method_slug":"k-means-clustering","method_name":"k-Means Clustering"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1811.11553","atlas_url":"https://app.syntology.ai/?focus=1811.11553","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":"1811.11553"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1811.11553\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1811.11553"},"call":"get_concepts_for_paper(arxiv_id=\"1811.11553\")"}],"by_repo":[{"repo":"airalcorn2/strike-with-a-pose","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":"c94aeebcdac4ef39a50041988142cc40459242c2d4c350adb737ee54f6482f88","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}