{"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/with-a-little-help-from-my-friends-nearest","title":"With a Little Help from My Friends: Nearest-Neighbor Contrastive Learning of Visual Representations","arxiv_id":"2104.14548","date":"2021-04-29","proceeding":"ICCV 2021 10","authors":["Debidatta Dwibedi","Yusuf Aytar","Jonathan Tompson","Pierre Sermanet","Andrew Zisserman"],"abstract":"Self-supervised learning algorithms based on instance discrimination train encoders to be invariant to pre-defined transformations of the same instance. While most methods treat different views of the same image as positives for a contrastive loss, we are interested in using positives from other instances in the dataset. Our method, Nearest-Neighbor Contrastive Learning of visual Representations (NNCLR), samples the nearest neighbors from the dataset in the latent space, and treats them as positives. This provides more semantic variations than pre-defined transformations. We find that using the nearest-neighbor as positive in contrastive losses improves performance significantly on ImageNet classification, from 71.7% to 75.6%, outperforming previous state-of-the-art methods. On semi-supervised learning benchmarks we improve performance significantly when only 1% ImageNet labels are available, from 53.8% to 56.5%. On transfer learning benchmarks our method outperforms state-of-the-art methods (including supervised learning with ImageNet) on 8 out of 12 downstream datasets. Furthermore, we demonstrate empirically that our method is less reliant on complex data augmentations. We see a relative reduction of only 2.1% ImageNet Top-1 accuracy when we train using only random crops.","url_abs":"https://arxiv.org/abs/2104.14548v2","url_pdf":"https://arxiv.org/pdf/2104.14548v2.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":"with-a-little-help-from-my-friends-nearest","repo_url":"https://github.com/beresandras/contrastive-classification-keras","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"with-a-little-help-from-my-friends-nearest","repo_url":"https://github.com/lightly-ai/lightly","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"with-a-little-help-from-my-friends-nearest","repo_url":"https://github.com/vturrisi/solo-learn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"with-a-little-help-from-my-friends-nearest","repo_url":"https://github.com/keras-team/keras-io/blob/master/examples/vision/nnclr.py","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"fine-grained-image-classification","task_name":"Fine-Grained Image Classification"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"self-supervised-image-classification","task_name":"Self-Supervised Image Classification"},{"task_slug":"self-supervised-learning","task_name":"Self-Supervised Learning"},{"task_slug":"semi-supervised-image-classification","task_name":"Semi-Supervised Image Classification"},{"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":"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":"nnclr","method_name":"NNCLR"},{"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":"supervised-contrastive-loss","method_name":"Supervised Contrastive Loss"}],"datasets_introduced":[],"methods_introduced":[{"slug":"nnclr","name":"NNCLR","full_name":"Nearest-Neighbor Contrastive Learning of Visual Representations"}],"results":[{"leaderboard":"/sota/fine-grained-image-classification-on-birdsnap","task":"Fine-Grained Image Classification","dataset":"Birdsnap","model":"NNCLR","rank_in_archive_order":5,"of":5,"metrics":{"Accuracy":"61.4%"},"uses_additional_data":false},{"leaderboard":"/sota/fine-grained-image-classification-on-caltech","task":"Fine-Grained Image Classification","dataset":"Caltech-101","model":"NNCLR","rank_in_archive_order":9,"of":18,"metrics":{"Top-1 Error Rate":"8.7%"},"uses_additional_data":false},{"leaderboard":"/sota/fine-grained-image-classification-on-fgvc","task":"Fine-Grained Image Classification","dataset":"FGVC Aircraft","model":"NNCLR","rank_in_archive_order":53,"of":57,"metrics":{"Accuracy":"64.1"},"uses_additional_data":false},{"leaderboard":"/sota/fine-grained-image-classification-on-sun397","task":"Fine-Grained Image Classification","dataset":"SUN397","model":"NNCLR","rank_in_archive_order":5,"of":5,"metrics":{"Accuracy":"62.5"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-cifar-10","task":"Image Classification","dataset":"CIFAR-10","model":"NNCLR","rank_in_archive_order":172,"of":265,"metrics":{"Percentage correct":"93.7"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-cifar-100","task":"Image Classification","dataset":"CIFAR-100","model":"NNCLR","rank_in_archive_order":135,"of":211,"metrics":{"Percentage correct":"79"},"uses_additional_data":true},{"leaderboard":"/sota/image-classification-on-dtd","task":"Image Classification","dataset":"DTD","model":"NNCLR","rank_in_archive_order":10,"of":11,"metrics":{"Accuracy":"75.5"},"uses_additional_data":true},{"leaderboard":"/sota/image-classification-on-flowers-102","task":"Image Classification","dataset":"Flowers-102","model":"NNCLR","rank_in_archive_order":43,"of":52,"metrics":{"Accuracy":"95.1"},"uses_additional_data":true},{"leaderboard":"/sota/image-classification-on-food-101-1","task":"Image Classification","dataset":"Food-101","model":"NNCLR","rank_in_archive_order":10,"of":11,"metrics":{"Accuracy (%)":"76.7"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-oxford-iiit-pets","task":"Image Classification","dataset":"Oxford-IIIT Pet Dataset","model":"NNCLR","rank_in_archive_order":3,"of":5,"metrics":{"Accuracy":"91.8"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-pascal-voc-2007","task":"Image Classification","dataset":"PASCAL VOC 2007","model":"NNCLR","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy":"83"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-stanford-cars","task":"Image Classification","dataset":"Stanford Cars","model":"NNCLR","rank_in_archive_order":24,"of":24,"metrics":{"Accuracy":"67.1"},"uses_additional_data":false},{"leaderboard":"/sota/self-supervised-image-classification-on","task":"Self-Supervised Image Classification","dataset":"ImageNet","model":"NNCLR (ResNet-50, multi-crop)","rank_in_archive_order":71,"of":144,"metrics":{"Number of Params":"25M","Top 1 Accuracy":"75.6%","Top 5 Accuracy":"92.4"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-image-classification-on-1","task":"Semi-Supervised Image Classification","dataset":"ImageNet - 1% labeled data","model":"NNCLR (ResNet-50)","rank_in_archive_order":44,"of":65,"metrics":{"Top 1 Accuracy":"56.4%","Top 5 Accuracy":"80.7"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-image-classification-on-2","task":"Semi-Supervised Image Classification","dataset":"ImageNet - 10% labeled data","model":"NNCLR (ResNet-50)","rank_in_archive_order":40,"of":75,"metrics":{"Top 1 Accuracy":"69.8%","Top 5 Accuracy":"89.3"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2104.14548","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.14548"}},"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/lightly-ai/lightly","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/beresandras/contrastive-classification-keras","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/vturrisi/solo-learn","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/keras-team/keras-io/blob/master/examples/vision/nnclr.py","reach":null}],"summary":{"ran":4,"unverified":1},"by_repo_kind":{"listed":{"samples":5,"ran":4,"repositories":2}},"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":"acc020a5fafd0a3c","entry":"ContrastiveModel","repo":"beresandras/contrastive-classification-keras","repo_kind":"listed","path":"algorithms.py","file_url":"https://github.com/beresandras/contrastive-classification-keras/blob/HEAD/algorithms.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"acc020a5fafd0a3c"}},{"code_sha256_prefix":"f4dca3b21591894a","entry":"NNCLR","repo":"lightly-ai/lightly","repo_kind":"listed","path":"lightly/models/nnclr.py","file_url":"https://github.com/lightly-ai/lightly/blob/HEAD/lightly/models/nnclr.py","link_basis":"first_harvest_node","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":"f4dca3b21591894a"}},{"code_sha256_prefix":"c86c2eda640e0f05","entry":"NNCLRPredictionHead","repo":"lightly-ai/lightly","repo_kind":"listed","path":"lightly/models/nnclr.py","file_url":"https://github.com/lightly-ai/lightly/blob/HEAD/lightly/models/nnclr.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c86c2eda640e0f05"}},{"code_sha256_prefix":"b23b111c2f4e00fd","entry":"NNCLRProjectionHead","repo":"lightly-ai/lightly","repo_kind":"listed","path":"lightly/models/nnclr.py","file_url":"https://github.com/lightly-ai/lightly/blob/HEAD/lightly/models/nnclr.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b23b111c2f4e00fd"}},{"code_sha256_prefix":"a8d39573526af033","entry":"NNCLR","repo":"beresandras/contrastive-classification-keras","repo_kind":"listed","path":"algorithms.py","file_url":"https://github.com/beresandras/contrastive-classification-keras/blob/HEAD/algorithms.py","link_basis":"first_harvest_node","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":"a8d39573526af033"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}