{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/your-local-gan-designing-two-dimensional","title":"Your Local GAN: Designing Two Dimensional Local Attention Mechanisms for Generative Models","arxiv_id":"1911.12287","date":"2019-11-27","proceeding":"CVPR 2020 6","authors":["Giannis Daras","Augustus Odena","Han Zhang","Alexandros G. Dimakis"],"abstract":"We introduce a new local sparse attention layer that preserves two-dimensional geometry and locality. We show that by just replacing the dense attention layer of SAGAN with our construction, we obtain very significant FID, Inception score and pure visual improvements. FID score is improved from $18.65$ to $15.94$ on ImageNet, keeping all other parameters the same. The sparse attention patterns that we propose for our new layer are designed using a novel information theoretic criterion that uses information flow graphs. We also present a novel way to invert Generative Adversarial Networks with attention. Our method extracts from the attention layer of the discriminator a saliency map, which we use to construct a new loss function for the inversion. This allows us to visualize the newly introduced attention heads and show that they indeed capture interesting aspects of two-dimensional geometry of real images.","url_abs":"https://arxiv.org/abs/1911.12287v2","url_pdf":"https://arxiv.org/pdf/1911.12287v2.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":"your-local-gan-designing-two-dimensional","repo_url":"https://github.com/giannisdaras/ylg","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"your-local-gan-designing-two-dimensional","repo_url":"https://github.com/Mmhmmmmm/ylg_pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"conditional-image-generation","task_name":"Conditional Image Generation"},{"task_slug":"deep-attention","task_name":"Deep Attention"},{"task_slug":"image-generation","task_name":"Image Generation"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"gan-hinge-loss","method_name":"GAN Hinge Loss"},{"method_slug":"sagan","method_name":"SAGAN"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"spectral-normalization","method_name":"Spectral Normalization"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/conditional-image-generation-on-imagenet","task":"Conditional Image Generation","dataset":"ImageNet 128x128","model":"Your Local GAN","rank_in_archive_order":19,"of":22,"metrics":{"FID":"15.94","Inception score":"57.22"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1911.12287","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.12287"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","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/giannisdaras/ylg","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Mmhmmmmm/ylg_pytorch","reach":{"status":"ok"}}],"summary":{"ran_violates":1},"by_repo_kind":{"official":{"samples":1,"ran":1,"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":1,"samples":[{"code_sha256_prefix":"9c955676c222d3cf","entry":"change_range","repo":"giannisdaras/ylg","repo_kind":"official","path":"ylg/generate_images.py","file_url":"https://github.com/giannisdaras/ylg/blob/HEAD/ylg/generate_images.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"9c955676c222d3cf"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}