{"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/locally-masked-convolution-for-autoregressive","title":"Locally Masked Convolution for Autoregressive Models","arxiv_id":"2006.12486","date":"2020-06-22","proceeding":null,"authors":["Ajay Jain","Pieter Abbeel","Deepak Pathak"],"abstract":"High-dimensional generative models have many applications including image compression, multimedia generation, anomaly detection and data completion. State-of-the-art estimators for natural images are autoregressive, decomposing the joint distribution over pixels into a product of conditionals parameterized by a deep neural network, e.g. a convolutional neural network such as the PixelCNN. However, PixelCNNs only model a single decomposition of the joint, and only a single generation order is efficient. For tasks such as image completion, these models are unable to use much of the observed context. To generate data in arbitrary orders, we introduce LMConv: a simple modification to the standard 2D convolution that allows arbitrary masks to be applied to the weights at each location in the image. Using LMConv, we learn an ensemble of distribution estimators that share parameters but differ in generation order, achieving improved performance on whole-image density estimation (2.89 bpd on unconditional CIFAR10), as well as globally coherent image completions. Our code is available at https://ajayjain.github.io/lmconv.","url_abs":"https://arxiv.org/abs/2006.12486v3","url_pdf":"https://arxiv.org/pdf/2006.12486v3.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":"locally-masked-convolution-for-autoregressive","repo_url":"https://github.com/ajayjain/lmconv","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"anomaly-detection","task_name":"Anomaly Detection"},{"task_slug":"density-estimation","task_name":"Density Estimation"},{"task_slug":"image-compression","task_name":"Image Compression"},{"task_slug":"image-generation","task_name":"Image Generation"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-generation-on-binarized-mnist","task":"Image Generation","dataset":"Binarized MNIST","model":"Locally Masked PixelCNN (8 orders)","rank_in_archive_order":2,"of":10,"metrics":{"bits/dimension":"0.143","nats":"77.58"},"uses_additional_data":false},{"leaderboard":"/sota/image-generation-on-celeba-256x256","task":"Image Generation","dataset":"CelebA 256x256","model":"Locally Masked PixelCNN","rank_in_archive_order":7,"of":17,"metrics":{"bpd":"0.74"},"uses_additional_data":false},{"leaderboard":"/sota/image-generation-on-mnist","task":"Image Generation","dataset":"MNIST","model":"Locally Masked PixelCNN (8 orders)","rank_in_archive_order":1,"of":15,"metrics":{"bits/dimension":"0.65"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2006.12486","atlas_url":"https://app.syntology.ai/?focus=2006.12486","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":"2006.12486"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2006.12486\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2006.12486"},"call":"get_concepts_for_paper(arxiv_id=\"2006.12486\")"}],"by_repo":[{"repo":"ajayjain/lmconv","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":"95b81f7667d9299ee658f6161eb267abf1881025419cc317481cdc749f6538f3","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}