{"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/revbifpn-the-fully-reversible-bidirectional","title":"RevBiFPN: The Fully Reversible Bidirectional Feature Pyramid Network","arxiv_id":"2206.14098","date":"2022-06-28","proceeding":null,"authors":["Vitaliy Chiley","Vithursan Thangarasa","Abhay Gupta","Anshul Samar","Joel Hestness","Dennis Decoste"],"abstract":"This work introduces RevSilo, the first reversible bidirectional multi-scale feature fusion module. Like other reversible methods, RevSilo eliminates the need to store hidden activations by recomputing them. However, existing reversible methods do not apply to multi-scale feature fusion and are, therefore, not applicable to a large class of networks. Bidirectional multi-scale feature fusion promotes local and global coherence and has become a de facto design principle for networks targeting spatially sensitive tasks, e.g., HRNet (Sun et al., 2019a) and EfficientDet (Tan et al., 2020). These networks achieve state-of-the-art results across various computer vision tasks when paired with high-resolution inputs. However, training them requires substantial accelerator memory for saving large, multi-resolution activations. These memory requirements inherently cap the size of neural networks, limiting improvements that come from scale. Operating across resolution scales, RevSilo alleviates these issues. Stacking RevSilos, we create RevBiFPN, a fully reversible bidirectional feature pyramid network. RevBiFPN is competitive with networks such as EfficientNet while using up to 19.8x lesser training memory for image classification. When fine-tuned on MS COCO, RevBiFPN provides up to a 2.5% boost in AP over HRNet using fewer MACs and a 2.4x reduction in training-time memory.","url_abs":"https://arxiv.org/abs/2206.14098v2","url_pdf":"https://arxiv.org/pdf/2206.14098v2.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":"revbifpn-the-fully-reversible-bidirectional","repo_url":"https://github.com/cerebrasresearch/revbifpn","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"instance-segmentation","task_name":"Instance Segmentation"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"image-classification","task_name":"image-classification"}],"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":"bifpn","method_name":"BiFPN"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"depthwise-convolution","method_name":"Depthwise Convolution"},{"method_slug":"depthwise-separable-convolution","method_name":"Depthwise Separable Convolution"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"efficientdet","method_name":"EfficientDet"},{"method_slug":"hrnet","method_name":"HRNet"},{"method_slug":"inverted-residual-block","method_name":"Inverted Residual Block"},{"method_slug":"pointwise-convolution","method_name":"Pointwise Convolution"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"revsilo","method_name":"RevSilo"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"squeeze-and-excitation-block","method_name":"Squeeze-and-Excitation Block"}],"datasets_introduced":[],"methods_introduced":[{"slug":"revsilo","name":"RevSilo","full_name":"RevSilo"}],"results":[{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"RevBiFPN-S6","rank_in_archive_order":344,"of":1060,"metrics":{"GFLOPs":"38.1","Number of params":"142.3M","Top 1 Accuracy":"84.2%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"RevBiFPN-S5","rank_in_archive_order":399,"of":1060,"metrics":{"GFLOPs":"21.8","Number of params":"82M","Top 1 Accuracy":"83.7%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"RevBiFPN-S4","rank_in_archive_order":481,"of":1060,"metrics":{"GFLOPs":"10.6","Number of params":"48.7M","Top 1 Accuracy":"83%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"RevBiFPN-S3","rank_in_archive_order":665,"of":1060,"metrics":{"GFLOPs":"3.33","Number of params":"19.6M","Top 1 Accuracy":"81.1%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"RevBiFPN-S2","rank_in_archive_order":791,"of":1060,"metrics":{"GFLOPs":"1.37","Number of params":"10.6M","Top 1 Accuracy":"79%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"RevBiFPN-S1","rank_in_archive_order":930,"of":1060,"metrics":{"GFLOPs":"0.62","Number of params":"5.11M","Top 1 Accuracy":"75.9%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"RevBiFPN-S0","rank_in_archive_order":991,"of":1060,"metrics":{"GFLOPs":"0.31","Number of params":"3.42M","Top 1 Accuracy":"72.8%"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2206.14098","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.14098"}},"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/cerebrasresearch/revbifpn","reach":null}],"summary":{"ran_violates":2,"ran_fixture":1},"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":0,"samples":[{"code_sha256_prefix":"5c8094a5d91d9708","entry":"s_based_k","repo":"cerebrasresearch/revbifpn","repo_kind":"official","path":"revbifpn.py","file_url":"https://github.com/cerebrasresearch/revbifpn/blob/HEAD/revbifpn.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"5c8094a5d91d9708"}},{"code_sha256_prefix":"cc69e1100f9dc8d9","entry":"s_based_k_alt","repo":"cerebrasresearch/revbifpn","repo_kind":"official","path":"revbifpn.py","file_url":"https://github.com/cerebrasresearch/revbifpn/blob/HEAD/revbifpn.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"cc69e1100f9dc8d9"}},{"code_sha256_prefix":"53b32895c0219461","entry":"stochastic_depth_fn","repo":"cerebrasresearch/revbifpn","repo_kind":"official","path":"revbifpn.py","file_url":"https://github.com/cerebrasresearch/revbifpn/blob/HEAD/revbifpn.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"53b32895c0219461"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}