{"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/augmenting-convolutional-networks-with","title":"Augmenting Convolutional networks with attention-based aggregation","arxiv_id":"2112.13692","date":"2021-12-27","proceeding":null,"authors":["Hugo Touvron","Matthieu Cord","Alaaeldin El-Nouby","Piotr Bojanowski","Armand Joulin","Gabriel Synnaeve","Hervé Jégou"],"abstract":"We show how to augment any convolutional network with an attention-based global map to achieve non-local reasoning. We replace the final average pooling by an attention-based aggregation layer akin to a single transformer block, that weights how the patches are involved in the classification decision. We plug this learned aggregation layer with a simplistic patch-based convolutional network parametrized by 2 parameters (width and depth). In contrast with a pyramidal design, this architecture family maintains the input patch resolution across all the layers. It yields surprisingly competitive trade-offs between accuracy and complexity, in particular in terms of memory consumption, as shown by our experiments on various computer vision tasks: object classification, image segmentation and detection.","url_abs":"https://arxiv.org/abs/2112.13692v1","url_pdf":"https://arxiv.org/pdf/2112.13692v1.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":"augmenting-convolutional-networks-with","repo_url":"https://github.com/facebookresearch/deit","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"augmenting-convolutional-networks-with","repo_url":"https://github.com/DarshanDeshpande/jax-models","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":null},{"paper_slug":"augmenting-convolutional-networks-with","repo_url":"https://github.com/dongkyuk/PatchConvNet-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"augmenting-convolutional-networks-with","repo_url":"https://github.com/keras-team/keras-io/blob/master/examples/vision/patch_convnet.py","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null},{"paper_slug":"augmenting-convolutional-networks-with","repo_url":"https://github.com/mindspore-courses/External-Attention-MindSpore/blob/main/model/backbone/PatchConvnet.py","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"image-segmentation","task_name":"Image Segmentation"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"ca","method_name":"Class Attention"},{"method_slug":"layerscale","method_name":"LayerScale"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"PatchConvNet-L120-21k-384","rank_in_archive_order":108,"of":1060,"metrics":{"Number of params":"334.3M","Top 1 Accuracy":"87.1%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"PatchConvNet-B60-21k-384","rank_in_archive_order":139,"of":1060,"metrics":{"Number of params":"99.4M","Top 1 Accuracy":"86.5%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"PatchConvNet-S60-21k-512","rank_in_archive_order":230,"of":1060,"metrics":{"Number of params":"25.2M","Top 1 Accuracy":"85.4%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"PatchConvNet-B120","rank_in_archive_order":360,"of":1060,"metrics":{"Number of params":"188.6M","Top 1 Accuracy":"84.1%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"PatchConvNet-B60","rank_in_archive_order":423,"of":1060,"metrics":{"Number of params":"99.4M","Top 1 Accuracy":"83.5%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"PatchConvNet-S120","rank_in_archive_order":458,"of":1060,"metrics":{"Number of params":"47.7M","Top 1 Accuracy":"83.2%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"PatchConvNet-S60","rank_in_archive_order":574,"of":1060,"metrics":{"Number of params":"25.2M","Top 1 Accuracy":"82.1%"},"uses_additional_data":false},{"leaderboard":"/sota/object-detection-on-coco-minival","task":"Object Detection","dataset":"COCO minival","model":"PatchConvNet-S120 (Mask R-CNN)","rank_in_archive_order":100,"of":220,"metrics":{"box AP":"47.0"},"uses_additional_data":false},{"leaderboard":"/sota/object-detection-on-coco-minival","task":"Object Detection","dataset":"COCO minival","model":"PatchConvNet-S60 (Mask R-CNN)","rank_in_archive_order":106,"of":220,"metrics":{"box AP":"46.4"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-ade20k","task":"Semantic Segmentation","dataset":"ADE20K","model":"PatchConvNet-L120 (UperNet)","rank_in_archive_order":84,"of":235,"metrics":{"Validation mIoU":"52.9"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-ade20k","task":"Semantic Segmentation","dataset":"ADE20K","model":"PatchConvNet-B120\n(UperNet)","rank_in_archive_order":86,"of":235,"metrics":{"Validation mIoU":"52.8"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-ade20k","task":"Semantic Segmentation","dataset":"ADE20K","model":"PatchConvNet-B60 (UperNet)","rank_in_archive_order":102,"of":235,"metrics":{"Validation mIoU":"51.1"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-ade20k","task":"Semantic Segmentation","dataset":"ADE20K","model":"PatchConvNet-S60 (UperNet)","rank_in_archive_order":134,"of":235,"metrics":{"Validation mIoU":"49.3"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-ade20k-val","task":"Semantic Segmentation","dataset":"ADE20K val","model":"PatchConvNet-L120 (UperNet)","rank_in_archive_order":41,"of":95,"metrics":{"mIoU":"52.9"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-ade20k-val","task":"Semantic Segmentation","dataset":"ADE20K val","model":"PatchConvNet-B120 (UperNet)","rank_in_archive_order":43,"of":95,"metrics":{"mIoU":"52.8"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-ade20k-val","task":"Semantic Segmentation","dataset":"ADE20K val","model":"PatchConvNet-B60 (UperNet)","rank_in_archive_order":47,"of":95,"metrics":{"mIoU":"51.1"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-ade20k-val","task":"Semantic Segmentation","dataset":"ADE20K val","model":"PatchConvNet-S60 (UperNet)","rank_in_archive_order":59,"of":95,"metrics":{"mIoU":"49.3"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2112.13692","atlas_url":"https://app.syntology.ai/?focus=2112.13692","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.13692"},"calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2112.13692"},"returns":"the samples harvested from this paper, each with its run record; it does not verify the paper"},{"tool":"get_code","arguments_in":"samples[].code_sha256","returns":"one stored sample by its code_sha256; not shown on this site"}]},"developers":"https://syntology.ai/developers","held":true,"reason":"in_graph_layer","checked_against":null,"agent_calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2112.13692"},"call":"get_harvested_code_for_paper(arxiv_id=\"2112.13692\")"},{"tool":"get_code","arguments_in":{"code_sha256":"syntology.samples[].code_sha256"},"call":"get_code(code_sha256=\"…\")"},{"tool":"get_citation_path","arguments":{"paper_1":"2112.13692"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2112.13692\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2112.13692"},"call":"get_concepts_for_paper(arxiv_id=\"2112.13692\")"}],"by_repo":[{"repo":"facebookresearch/deit","kind":"official","samples":1,"ran":1,"instrument":1,"unverified":0},{"repo":"DarshanDeshpande/jax-models","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":8,"harvested_for":["1603.09382","2102.12122","2103.14030","2103.17239","2105.01601","2105.15203","2111.06377","2201.03545"],"harvested_for_calls":[{"arxiv_id":"1603.09382","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1603.09382"},"call":"get_harvested_code_for_paper(arxiv_id=\"1603.09382\")"},{"arxiv_id":"2102.12122","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2102.12122"},"call":"get_harvested_code_for_paper(arxiv_id=\"2102.12122\")"},{"arxiv_id":"2103.14030","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2103.14030"},"call":"get_harvested_code_for_paper(arxiv_id=\"2103.14030\")"},{"arxiv_id":"2103.17239","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2103.17239"},"call":"get_harvested_code_for_paper(arxiv_id=\"2103.17239\")"},{"arxiv_id":"2105.01601","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2105.01601"},"call":"get_harvested_code_for_paper(arxiv_id=\"2105.01601\")"},{"arxiv_id":"2105.15203","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2105.15203"},"call":"get_harvested_code_for_paper(arxiv_id=\"2105.15203\")"},{"arxiv_id":"2111.06377","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2111.06377"},"call":"get_harvested_code_for_paper(arxiv_id=\"2111.06377\")"},{"arxiv_id":"2201.03545","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2201.03545"},"call":"get_harvested_code_for_paper(arxiv_id=\"2201.03545\")"}]},{"repo":"dongkyuk/PatchConvNet-pytorch","kind":"listed","samples":1,"ran":1,"instrument":0,"unverified":0},{"repo":"keras-team/keras-io","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2212.13345"],"harvested_for_calls":[{"arxiv_id":"2212.13345","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2212.13345"},"call":"get_harvested_code_for_paper(arxiv_id=\"2212.13345\")"}]},{"repo":"mindspore-courses/External-Attention-MindSpore","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","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","read_at":"2026-10-05T00:36:11+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","ran_record":{"url":"https://syntology.ai/api/ran/2112.13692.json","schema":"syntology.ran_record/1","counts_crosswalk":{"n_samples":"syntology.counts.lifted","n_ran":"syntology.counts.executed","n_ran_checked":"syntology.counts.checked","n_instrument":"syntology.counts.instrument_failures","n_unverified":"syntology.counts.no_recorded_run"},"note":"live record, measured at request time; may be newer than this page's graph read","badge":"https://syntology.ai/api/ran/2112.13692.svg"},"claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/facebookresearch/deit","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/keras-team/keras-io/blob/master/examples/vision/patch_convnet.py","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/dongkyuk/PatchConvNet-pytorch","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/DarshanDeshpande/jax-models","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mindspore-courses/External-Attention-MindSpore/blob/main/model/backbone/PatchConvnet.py","reach":null}],"summary":{"ran_draft_wrong":1,"ran":1},"n_samples":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_instrument_is":"failures of Syntology's instrument, not of the code","every_run_is_an_instrument_failure":false,"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"by_repo_kind":{"official":{"samples":1,"ran":1,"n_ran_checked":0,"n_instrument":1,"repositories":1},"listed":{"samples":1,"ran":1,"n_ran_checked":1,"n_instrument":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"inline_ok_is":"inline_ok is true only when both licence gates allow Syntology to serve this code's text: this paper's link (inline_ok_link, from the licence of this paper's copy) and the stored copy of the same code that Syntology serves, which may have been first harvested from another repository. withheld_clause is Syntology's own wording of which gate keeps the text a pointer and why, and is null when inline_ok is true. This site shows no code text either way; n_pointer_only_for_licence counts samples with inline_ok false (both gates), n_pointer_only_link_allows those of them whose inline_ok_link is true","n_pointer_only_link_allows":0,"fixture_fields_is":{"signature_and_fixture_out_type":"the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right","level_recorded_at":"when Syntology's graph wrote the sample's verification level, not when the code executed; absent where the level was written before the date was kept, and never filled in with the build date","present_on":"samples that ran only; a key is absent, never empty, where the graph records nothing"},"n_ran_with_level_date":2,"n_ran_without_level_date":0,"n_ran_signature_not_shown":0,"levels_written_between":{"first":"2026-09-22","last":"2026-09-24","is":"the first and last UTC dates on which Syntology's graph wrote a verification level for a sample on this page that ran, not when the code executed"},"code_page_min_papers":5,"code_page_is":"a page for the entry name across every paper's harvested code; the name is a string, not an identity","samples":[{"code_sha256":"ba6aa5f07daca9cd","code_sha256_prefix":"ba6aa5f07daca9cd","entry":"conv3x3","repo":"facebookresearch/deit","repo_kind":"official","path":"patchconvnet_models.py","file_url":"https://github.com/facebookresearch/deit/blob/HEAD/patchconvnet_models.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"signature":"in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int","fixture_out_type":"Sequential","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/conv3x3","census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"ba6aa5f07daca9cd"}},{"code_sha256":"af6a4caff0775c04","code_sha256_prefix":"af6a4caff0775c04","entry":"get_activation","repo":"dongkyuk/PatchConvNet-pytorch","repo_kind":"listed","path":"model/custom_blocks.py","file_url":"https://github.com/dongkyuk/PatchConvNet-pytorch/blob/HEAD/model/custom_blocks.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"act:str/0/str","fixture_out_type":"ReLU","level_recorded_at":"2026-09-24T21:54:21.362907+00:00","code_page":"/code/get-activation","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"af6a4caff0775c04"}}]},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"1340c03660d6c7002d15c6707e732537991c956d8a8f5a481baaaa72448efce7","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}