{"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/poincare-resnet","title":"Poincaré ResNet","arxiv_id":"2303.14027","date":"2023-03-24","proceeding":null,"authors":["Max van Spengler","Erwin Berkhout","Pascal Mettes"],"abstract":"This paper introduces an end-to-end residual network that operates entirely on the Poincar\\'e ball model of hyperbolic space. Hyperbolic learning has recently shown great potential for visual understanding, but is currently only performed in the penultimate layer(s) of deep networks. All visual representations are still learned through standard Euclidean networks. In this paper we investigate how to learn hyperbolic representations of visual data directly from the pixel-level. We propose Poincar\\'e ResNet, a hyperbolic counterpart of the celebrated residual network, starting from Poincar\\'e 2D convolutions up to Poincar\\'e residual connections. We identify three roadblocks for training convolutional networks entirely in hyperbolic space and propose a solution for each: (i) Current hyperbolic network initializations collapse to the origin, limiting their applicability in deeper networks. We provide an identity-based initialization that preserves norms over many layers. (ii) Residual networks rely heavily on batch normalization, which comes with expensive Fr\\'echet mean calculations in hyperbolic space. We introduce Poincar\\'e midpoint batch normalization as a faster and equally effective alternative. (iii) Due to the many intermediate operations in Poincar\\'e layers, we lastly find that the computation graphs of deep learning libraries blow up, limiting our ability to train on deep hyperbolic networks. We provide manual backward derivations of core hyperbolic operations to maintain manageable computation graphs.","url_abs":"https://arxiv.org/abs/2303.14027v3","url_pdf":"https://arxiv.org/pdf/2303.14027v3.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":"poincare-resnet","repo_url":"https://github.com/maxvanspengler/poincare-resnet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[],"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":"convolution","method_name":"Convolution"},{"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":"relu","method_name":"ReLU"},{"method_slug":"residual-block","method_name":"Residual Block"},{"method_slug":"residual-connection","method_name":"Residual Connection"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2303.14027","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.14027"}},"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/maxvanspengler/poincare-resnet","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":5},"by_repo_kind":{"official":{"samples":5,"ran":0,"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":"8da2a89dad7cbb21","entry":"get_standard_transform","repo":"maxvanspengler/poincare-resnet","repo_kind":"official","path":"cifar10/transforms.py","file_url":"https://github.com/maxvanspengler/poincare-resnet/blob/HEAD/cifar10/transforms.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8da2a89dad7cbb21"}},{"code_sha256_prefix":"69b94aef2868dbab","entry":"initialize_optimizer","repo":"maxvanspengler/poincare-resnet","repo_kind":"official","path":"models/optimizers.py","file_url":"https://github.com/maxvanspengler/poincare-resnet/blob/HEAD/models/optimizers.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"69b94aef2868dbab"}},{"code_sha256_prefix":"aa9cabe0d8f959a5","entry":"parse_optimizer_kwargs","repo":"maxvanspengler/poincare-resnet","repo_kind":"official","path":"models/optimizers.py","file_url":"https://github.com/maxvanspengler/poincare-resnet/blob/HEAD/models/optimizers.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"aa9cabe0d8f959a5"}},{"code_sha256_prefix":"756336953a775826","entry":"poincareball_factory","repo":"maxvanspengler/poincare-resnet","repo_kind":"official","path":"models/manifolds/poincare_disk.py","file_url":"https://github.com/maxvanspengler/poincare-resnet/blob/HEAD/models/manifolds/poincare_disk.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"756336953a775826"}},{"code_sha256_prefix":"7ec4cbd55f8261a9","entry":"update_metrics_dict","repo":"maxvanspengler/poincare-resnet","repo_kind":"official","path":"adversarial_attacks.py","file_url":"https://github.com/maxvanspengler/poincare-resnet/blob/HEAD/adversarial_attacks.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"7ec4cbd55f8261a9"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}