{"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/adaptively-connected-neural-networks","title":"Adaptively Connected Neural Networks","arxiv_id":"1904.03579","date":"2019-04-07","proceeding":"CVPR 2019 6","authors":["Guangrun Wang","Keze Wang","Liang Lin"],"abstract":"This paper presents a novel adaptively connected neural network (ACNet) to\nimprove the traditional convolutional neural networks (CNNs) {in} two aspects.\nFirst, ACNet employs a flexible way to switch global and local inference in\nprocessing the internal feature representations by adaptively determining the\nconnection status among the feature nodes (e.g., pixels of the feature maps)\n\\footnote{In a computer vision domain, a node refers to a pixel of a feature\nmap{, while} in {the} graph domain, a node denotes a graph node.}. We can show\nthat existing CNNs, the classical multilayer perceptron (MLP), and the recently\nproposed non-local network (NLN) \\cite{nonlocalnn17} are all special cases of\nACNet. Second, ACNet is also capable of handling non-Euclidean data. Extensive\nexperimental analyses on {a variety of benchmarks (i.e.,} ImageNet-1k\nclassification, COCO 2017 detection and segmentation, CUHK03 person\nre-identification, CIFAR analysis, and Cora document categorization)\ndemonstrate that {ACNet} cannot only achieve state-of-the-art performance but\nalso overcome the limitation of the conventional MLP and CNN\n\\footnote{Corresponding author: Liang Lin (linliang@ieee.org)}. The code is\navailable at\n\\url{https://github.com/wanggrun/Adaptively-Connected-Neural-Networks}.","url_abs":"http://arxiv.org/abs/1904.03579v1","url_pdf":"http://arxiv.org/pdf/1904.03579v1.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":"adaptively-connected-neural-networks","repo_url":"https://github.com/wanggrun/Adaptively-Connected-Neural-Networks","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"document-classification","task_name":"Document Classification"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"person-re-identification","task_name":"Person Re-Identification"}],"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":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"kaiming-initialization","method_name":"Kaiming Initialization"},{"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"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/document-classification-on-cora","task":"Document Classification","dataset":"Cora","model":"ACNet","rank_in_archive_order":1,"of":6,"metrics":{"Accuracy":"83.5%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"ACNet (ResNet-50)","rank_in_archive_order":873,"of":1060,"metrics":{"Number of params":"29.38M","Top 1 Accuracy":"77.5%"},"uses_additional_data":false},{"leaderboard":"/sota/instance-segmentation-on-coco-minival","task":"Instance Segmentation","dataset":"COCO minival","model":"Mask R-CNN (ResNet-50, ACNet)","rank_in_archive_order":91,"of":93,"metrics":{"mask AP":"35.2"},"uses_additional_data":false},{"leaderboard":"/sota/object-detection-on-coco-minival","task":"Object Detection","dataset":"COCO minival","model":"Mask R-CNN (ResNet-50, ACNet)","rank_in_archive_order":188,"of":220,"metrics":{"box AP":"39.5"},"uses_additional_data":false},{"leaderboard":"/sota/person-re-identification-on-cuhk03","task":"Person Re-Identification","dataset":"CUHK03","model":"TriNet + Era + Reranking (ACNet, bs=32)","rank_in_archive_order":19,"of":19,"metrics":{"Rank-1":"64.8"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1904.03579","atlas_url":"https://app.syntology.ai/?focus=1904.03579","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":"1904.03579"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1904.03579\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1904.03579"},"call":"get_concepts_for_paper(arxiv_id=\"1904.03579\")"}],"by_repo":[{"repo":"wanggrun/Adaptively-Connected-Neural-Networks","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":"3a26155acdc76005685116ff53d09ddbd6b9a5bffb73c7862b889d16aadb2a33","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}