{"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/a-simple-efficient-and-scalable-contrastive","title":"A simple, efficient and scalable contrastive masked autoencoder for learning visual representations","arxiv_id":"2210.16870","date":"2022-10-30","proceeding":null,"authors":["Shlok Mishra","Joshua Robinson","Huiwen Chang","David Jacobs","Aaron Sarna","Aaron Maschinot","Dilip Krishnan"],"abstract":"We introduce CAN, a simple, efficient and scalable method for self-supervised learning of visual representations. Our framework is a minimal and conceptually clean synthesis of (C) contrastive learning, (A) masked autoencoders, and (N) the noise prediction approach used in diffusion models. The learning mechanisms are complementary to one another: contrastive learning shapes the embedding space across a batch of image samples; masked autoencoders focus on reconstruction of the low-frequency spatial correlations in a single image sample; and noise prediction encourages the reconstruction of the high-frequency components of an image. The combined approach results in a robust, scalable and simple-to-implement algorithm. The training process is symmetric, with 50% of patches in both views being masked at random, yielding a considerable efficiency improvement over prior contrastive learning methods. Extensive empirical studies demonstrate that CAN achieves strong downstream performance under both linear and finetuning evaluations on transfer learning and robustness tasks. CAN outperforms MAE and SimCLR when pre-training on ImageNet, but is especially useful for pre-training on larger uncurated datasets such as JFT-300M: for linear probe on ImageNet, CAN achieves 75.4% compared to 73.4% for SimCLR and 64.1% for MAE. The finetuned performance on ImageNet of our ViT-L model is 86.1%, compared to 85.5% for SimCLR, and 85.4% for MAE. The overall FLOPs load of SimCLR is 70% higher than CAN for ViT-L models.","url_abs":"https://arxiv.org/abs/2210.16870v1","url_pdf":"https://arxiv.org/pdf/2210.16870v1.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":"a-simple-efficient-and-scalable-contrastive","repo_url":"https://github.com/bwconrad/can","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"self-supervised-learning","task_name":"Self-Supervised Learning"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"}],"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":"colorjitter","method_name":"ColorJitter"},{"method_slug":"contrastive-learning","method_name":"Contrastive Learning"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"diffusion","method_name":"Diffusion"},{"method_slug":"feedforward-network","method_name":"Feedforward Network"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"kaiming-initialization","method_name":"Kaiming Initialization"},{"method_slug":"mae","method_name":"MAE"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"nt-xent","method_name":"NT-Xent"},{"method_slug":"random-gaussian-blur","method_name":"Random Gaussian Blur"},{"method_slug":"random-resized-crop","method_name":"Random Resized Crop"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-block","method_name":"Residual Block"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"simclr","method_name":"SimCLR"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2210.16870","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.16870"}},"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/bwconrad/can","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":1,"unverified":6},"by_repo_kind":{"listed":{"samples":7,"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":0,"samples":[{"code_sha256_prefix":"a448d12e56c7a36f","entry":"gather","repo":"bwconrad/can","repo_kind":"listed","path":"src/loss.py","file_url":"https://github.com/bwconrad/can/blob/HEAD/src/loss.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a448d12e56c7a36f"}},{"code_sha256_prefix":"ac32c55f2147ecc0","entry":"get_1d_sincos_pos_embed","repo":"bwconrad/can","repo_kind":"listed","path":"src/network/pos_embed.py","file_url":"https://github.com/bwconrad/can/blob/HEAD/src/network/pos_embed.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ac32c55f2147ecc0"}},{"code_sha256_prefix":"3185afc3e87293ed","entry":"get_2d_sincos_pos_embed","repo":"bwconrad/can","repo_kind":"listed","path":"src/network/pos_embed.py","file_url":"https://github.com/bwconrad/can/blob/HEAD/src/network/pos_embed.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3185afc3e87293ed"}},{"code_sha256_prefix":"f10004e059714d42","entry":"get_2d_sincos_pos_embed_from_grid","repo":"bwconrad/can","repo_kind":"listed","path":"src/network/pos_embed.py","file_url":"https://github.com/bwconrad/can/blob/HEAD/src/network/pos_embed.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f10004e059714d42"}},{"code_sha256_prefix":"bf724860a92f3c7f","entry":"info_nce_loss","repo":"bwconrad/can","repo_kind":"listed","path":"src/loss.py","file_url":"https://github.com/bwconrad/can/blob/HEAD/src/loss.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bf724860a92f3c7f"}},{"code_sha256_prefix":"897d09cf62083d7b","entry":"init_logger","repo":"bwconrad/can","repo_kind":"listed","path":"src/pl_utils.py","file_url":"https://github.com/bwconrad/can/blob/HEAD/src/pl_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"897d09cf62083d7b"}},{"code_sha256_prefix":"5d89cbb035fd02a1","entry":"masked_mse_loss","repo":"bwconrad/can","repo_kind":"listed","path":"src/loss.py","file_url":"https://github.com/bwconrad/can/blob/HEAD/src/loss.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5d89cbb035fd02a1"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}