{"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/rethinking-image-mixture-for-unsupervised","title":"Un-Mix: Rethinking Image Mixtures for Unsupervised Visual Representation Learning","arxiv_id":"2003.05438","date":"2020-03-11","proceeding":null,"authors":["Zhiqiang Shen","Zechun Liu","Zhuang Liu","Marios Savvides","Trevor Darrell","Eric Xing"],"abstract":"The recently advanced unsupervised learning approaches use the siamese-like framework to compare two \"views\" from the same image for learning representations. Making the two views distinctive is a core to guarantee that unsupervised methods can learn meaningful information. However, such frameworks are sometimes fragile on overfitting if the augmentations used for generating two views are not strong enough, causing the over-confident issue on the training data. This drawback hinders the model from learning subtle variance and fine-grained information. To address this, in this work we aim to involve the distance concept on label space in the unsupervised learning and let the model be aware of the soft degree of similarity between positive or negative pairs through mixing the input data space, to further work collaboratively for the input and loss spaces. Despite its conceptual simplicity, we show empirically that with the solution -- Unsupervised image mixtures (Un-Mix), we can learn subtler, more robust and generalized representations from the transformed input and corresponding new label space. Extensive experiments are conducted on CIFAR-10, CIFAR-100, STL-10, Tiny ImageNet and standard ImageNet with popular unsupervised methods SimCLR, BYOL, MoCo V1&V2, SwAV, etc. Our proposed image mixture and label assignment strategy can obtain consistent improvement by 1~3% following exactly the same hyperparameters and training procedures of the base methods. Code is publicly available at https://github.com/szq0214/Un-Mix.","url_abs":"https://arxiv.org/abs/2003.05438v5","url_pdf":"https://arxiv.org/pdf/2003.05438v5.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":"rethinking-image-mixture-for-unsupervised","repo_url":"https://github.com/szq0214/Rethinking-Image-Mixture-for-Unsupervised-Learning","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"rethinking-image-mixture-for-unsupervised","repo_url":"https://github.com/szq0214/un-mix","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"rethinking-image-mixture-for-unsupervised","repo_url":"https://github.com/hannaiiyanggit/unicon","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"representation-learning","task_name":"Representation 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":"convolution","method_name":"Convolution"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"feedforward-network","method_name":"Feedforward Network"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"infonce","method_name":"InfoNCE"},{"method_slug":"kaiming-initialization","method_name":"Kaiming Initialization"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"moco","method_name":"MoCo"},{"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=2003.05438","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.05438"}},"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/szq0214/Rethinking-Image-Mixture-for-Unsupervised-Learning","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/hannaiiyanggit/unicon","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/szq0214/un-mix","reach":{"status":"ok"}}],"summary":{"ran_fixture":2,"ran_draft_wrong":1,"unverified":1},"by_repo_kind":{"official":{"samples":4,"ran":3,"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":4,"samples":[{"code_sha256_prefix":"131a82fd65128218","entry":"accuracy","repo":"szq0214/Rethinking-Image-Mixture-for-Unsupervised-Learning","repo_kind":"official","path":"UnMix_MoCo/for_ImageNet/main_moco_unmix.py","file_url":"https://github.com/szq0214/Rethinking-Image-Mixture-for-Unsupervised-Learning/blob/HEAD/UnMix_MoCo/for_ImageNet/main_moco_unmix.py","link_basis":"plan_row","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"131a82fd65128218"}},{"code_sha256_prefix":"5fcdac7381ca1c6f","entry":"knn_predict","repo":"szq0214/un-mix","repo_kind":"official","path":"unmix_c10.py","file_url":"https://github.com/szq0214/un-mix/blob/HEAD/unmix_c10.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5fcdac7381ca1c6f"}},{"code_sha256_prefix":"ec86c87ba5292b45","entry":"test","repo":"szq0214/un-mix","repo_kind":"official","path":"unmix_c10.py","file_url":"https://github.com/szq0214/un-mix/blob/HEAD/unmix_c10.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ec86c87ba5292b45"}},{"code_sha256_prefix":"d34a085d71b8f4b5","entry":"rand_bbox","repo":"szq0214/Rethinking-Image-Mixture-for-Unsupervised-Learning","repo_kind":"official","path":"UnMix_MoCo/for_ImageNet/main_moco_unmix.py","file_url":"https://github.com/szq0214/Rethinking-Image-Mixture-for-Unsupervised-Learning/blob/HEAD/UnMix_MoCo/for_ImageNet/main_moco_unmix.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d34a085d71b8f4b5"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}