{"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/intermediate-layers-matter-in-momentum","title":"Intermediate Layers Matter in Momentum Contrastive Self Supervised Learning","arxiv_id":"2110.14805","date":"2021-10-27","proceeding":"NeurIPS 2021 12","authors":["Aakash Kaku","Sahana Upadhya","Narges Razavian"],"abstract":"We show that bringing intermediate layers' representations of two augmented versions of an image closer together in self-supervised learning helps to improve the momentum contrastive (MoCo) method. To this end, in addition to the contrastive loss, we minimize the mean squared error between the intermediate layer representations or make their cross-correlation matrix closer to an identity matrix. Both loss objectives either outperform standard MoCo, or achieve similar performances on three diverse medical imaging datasets: NIH-Chest Xrays, Breast Cancer Histopathology, and Diabetic Retinopathy. The gains of the improved MoCo are especially large in a low-labeled data regime (e.g. 1% labeled data) with an average gain of 5% across three datasets. We analyze the models trained using our novel approach via feature similarity analysis and layer-wise probing. Our analysis reveals that models trained via our approach have higher feature reuse compared to a standard MoCo and learn informative features earlier in the network. Finally, by comparing the output probability distribution of models fine-tuned on small versus large labeled data, we conclude that our proposed method of pre-training leads to lower Kolmogorov-Smirnov distance, as compared to a standard MoCo. This provides additional evidence that our proposed method learns more informative features in the pre-training phase which could be leveraged in a low-labeled data regime.","url_abs":"https://arxiv.org/abs/2110.14805v1","url_pdf":"https://arxiv.org/pdf/2110.14805v1.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":"intermediate-layers-matter-in-momentum","repo_url":"https://github.com/aakashrkaku/intermdiate_layer_matter_ssl","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"self-supervised-learning","task_name":"Self-Supervised Learning"}],"methods":[{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"infonce","method_name":"InfoNCE"},{"method_slug":"moco","method_name":"MoCo"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2110.14805","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.14805"}},"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/aakashrkaku/intermdiate_layer_matter_ssl","reach":null}],"summary":{"ran_honours":3},"by_repo_kind":{"official":{"samples":3,"ran":3,"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":3,"samples":[{"code_sha256_prefix":"5c273c526536356d","entry":"centering","repo":"aakashrkaku/intermdiate_layer_matter_ssl","repo_kind":"official","path":"breast_cancer_histopathology/CKA.py","file_url":"https://github.com/aakashrkaku/intermdiate_layer_matter_ssl/blob/HEAD/breast_cancer_histopathology/CKA.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5c273c526536356d"}},{"code_sha256_prefix":"c633017bfba675e4","entry":"kernel_HSIC","repo":"aakashrkaku/intermdiate_layer_matter_ssl","repo_kind":"official","path":"breast_cancer_histopathology/CKA.py","file_url":"https://github.com/aakashrkaku/intermdiate_layer_matter_ssl/blob/HEAD/breast_cancer_histopathology/CKA.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c633017bfba675e4"}},{"code_sha256_prefix":"0f137cab706f1953","entry":"rbf","repo":"aakashrkaku/intermdiate_layer_matter_ssl","repo_kind":"official","path":"breast_cancer_histopathology/CKA.py","file_url":"https://github.com/aakashrkaku/intermdiate_layer_matter_ssl/blob/HEAD/breast_cancer_histopathology/CKA.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0f137cab706f1953"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}