Papers › RevBiFPN: The Fully Reversible Bidirectional Feature Pyramid Network

RevBiFPN: The Fully Reversible Bidirectional Feature Pyramid Network

28 Jun 2022arXiv:2206.14098archive 2025-07-28

Vitaliy Chiley, Vithursan Thangarasa, Abhay Gupta, Anshul Samar, Joel Hestness, Dennis Decoste

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.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 3 code samples harvested from 1 repository linked to this paper: 3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 2 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified. Where Syntology's instrument failed: 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 3 samples from 1 repository, 3 ran (2 with no instrument failure; 1 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

cerebrasresearch/revbifpn officialmentioned in papermentioned on GitHubpytorchSyntology: 3 samples, 3 ran (1 instrument-failed) · 0 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

3 samples harvested: 3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 2 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

2ran · violated contract
1ran; the contract check could not run

Licence: 0 of the 3 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from cerebrasresearch/revbifpn. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: 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. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

cerebrasresearch/revbifpn official repository 3 samples, 3 ran (1 instrument-failed) · 0 unverified
s_based_k revbifpn.py ran · violated contract fingerprinted BSD-3-Clause (permissive) · 5c8094a5d91d9708 · report fixture: signature stride:int/0/int, p:int/0/int · returned int · level recorded 2026-09-22
s_based_k_alt revbifpn.py ran · violated contract fingerprinted BSD-3-Clause (permissive) · cc69e1100f9dc8d9 · report fixture: signature stride:int/0/int, p:int/0/int · returned int · level recorded 2026-09-22
stochastic_depth_fn revbifpn.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant BSD-3-Clause (permissive) · 53b32895c0219461 · report fixture: signature x:Tensor/3/float, p:float/0/float, mode:str/0/str, training:bool/0/bool · returned Tensor · level recorded 2026-09-22

Tasks

General ClassificationImage ClassificationInstance SegmentationObject Detectionimage-classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Classification ImageNet RevBiFPN-S6 GFLOPs 38.1 #344 of 1060 Archive leaderboard report
Image Classification ImageNet RevBiFPN-S6 Number of params 142.3M #344 of 1060 Archive leaderboard report
Image Classification ImageNet RevBiFPN-S6 Top 1 Accuracy 84.2% #344 of 1060 Archive leaderboard report
Image Classification ImageNet RevBiFPN-S5 GFLOPs 21.8 #399 of 1060 Archive leaderboard report
Image Classification ImageNet RevBiFPN-S5 Number of params 82M #399 of 1060 Archive leaderboard report
Image Classification ImageNet RevBiFPN-S5 Top 1 Accuracy 83.7% #399 of 1060 Archive leaderboard report
Image Classification ImageNet RevBiFPN-S4 GFLOPs 10.6 #481 of 1060 Archive leaderboard report
Image Classification ImageNet RevBiFPN-S4 Number of params 48.7M #481 of 1060 Archive leaderboard report
Image Classification ImageNet RevBiFPN-S4 Top 1 Accuracy 83% #481 of 1060 Archive leaderboard report
Image Classification ImageNet RevBiFPN-S3 GFLOPs 3.33 #665 of 1060 Archive leaderboard report
Image Classification ImageNet RevBiFPN-S3 Number of params 19.6M #665 of 1060 Archive leaderboard report
Image Classification ImageNet RevBiFPN-S3 Top 1 Accuracy 81.1% #665 of 1060 Archive leaderboard report
Image Classification ImageNet RevBiFPN-S2 GFLOPs 1.37 #791 of 1060 Archive leaderboard report
Image Classification ImageNet RevBiFPN-S2 Number of params 10.6M #791 of 1060 Archive leaderboard report
Image Classification ImageNet RevBiFPN-S2 Top 1 Accuracy 79% #791 of 1060 Archive leaderboard report
Image Classification ImageNet RevBiFPN-S1 GFLOPs 0.62 #930 of 1060 Archive leaderboard report
Image Classification ImageNet RevBiFPN-S1 Number of params 5.11M #930 of 1060 Archive leaderboard report
Image Classification ImageNet RevBiFPN-S1 Top 1 Accuracy 75.9% #930 of 1060 Archive leaderboard report
Image Classification ImageNet RevBiFPN-S0 GFLOPs 0.31 #991 of 1060 Archive leaderboard report
Image Classification ImageNet RevBiFPN-S0 Number of params 3.42M #991 of 1060 Archive leaderboard report
Image Classification ImageNet RevBiFPN-S0 Top 1 Accuracy 72.8% #991 of 1060 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Introduced by this paper: RevSilo

1x1 ConvolutionAverage PoolingBatch NormalizationBiFPNConvolutionDense ConnectionsDepthwise ConvolutionDepthwise Separable ConvolutionDropoutEfficientDetHRNetInverted Residual BlockPointwise ConvolutionReLUResidual ConnectionRevSiloSigmoid ActivationSqueeze-and-Excitation Block

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections