{"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/is-second-order-information-helpful-for-large","title":"Is Second-order Information Helpful for Large-scale Visual Recognition?","arxiv_id":"1703.08050","date":"2017-03-23","proceeding":"ICCV 2017 10","authors":["Peihua Li","Jiangtao Xie","Qilong Wang","WangMeng Zuo"],"abstract":"By stacking layers of convolution and nonlinearity, convolutional networks\n(ConvNets) effectively learn from low-level to high-level features and\ndiscriminative representations. Since the end goal of large-scale recognition\nis to delineate complex boundaries of thousands of classes, adequate\nexploration of feature distributions is important for realizing full potentials\nof ConvNets. However, state-of-the-art works concentrate only on deeper or\nwider architecture design, while rarely exploring feature statistics higher\nthan first-order. We take a step towards addressing this problem. Our method\nconsists in covariance pooling, instead of the most commonly used first-order\npooling, of high-level convolutional features. The main challenges involved are\nrobust covariance estimation given a small sample of large-dimensional features\nand usage of the manifold structure of covariance matrices. To address these\nchallenges, we present a Matrix Power Normalized Covariance (MPN-COV) method.\nWe develop forward and backward propagation formulas regarding the nonlinear\nmatrix functions such that MPN-COV can be trained end-to-end. In addition, we\nanalyze both qualitatively and quantitatively its advantage over the well-known\nLog-Euclidean metric. On the ImageNet 2012 validation set, by combining MPN-COV\nwe achieve over 4%, 3% and 2.5% gains for AlexNet, VGG-M and VGG-16,\nrespectively; integration of MPN-COV into 50-layer ResNet outperforms\nResNet-101 and is comparable to ResNet-152. The source code will be available\non the project page: http://www.peihuali.org/MPN-COV","url_abs":"http://arxiv.org/abs/1703.08050v3","url_pdf":"http://arxiv.org/pdf/1703.08050v3.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":"is-second-order-information-helpful-for-large","repo_url":"https://github.com/jiangtaoxie/MPN-COV","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"object-recognition","task_name":"Object Recognition"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"bottleneck-residual-block","method_name":"Bottleneck Residual Block"},{"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":"kaiming-initialization","method_name":"Kaiming Initialization"},{"method_slug":"local-response-normalization","method_name":"Local Response Normalization"},{"method_slug":"mpn","method_name":"MPN"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-block","method_name":"Residual Block"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[{"slug":"mpn","name":"MPN","full_name":"Matrix-power Normalization"}],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1703.08050","atlas_url":"https://app.syntology.ai/?focus=1703.08050","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":"1703.08050"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1703.08050\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1703.08050"},"call":"get_concepts_for_paper(arxiv_id=\"1703.08050\")"}],"by_repo":[{"repo":"jiangtaoxie/MPN-COV","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":"85f1e3884ad55f37c7590c232af52d0072431a185af7bb01b9682a2782d5419e","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}