Papers › Reversible Column Networks

Reversible Column Networks

22 Dec 2022arXiv:2212.11696archive 2025-07-28

Yuxuan Cai, Yizhuang Zhou, Qi Han, Jianjian Sun, Xiangwen Kong, Jun Li, Xiangyu Zhang

We propose a new neural network design paradigm Reversible Column Network (RevCol). The main body of RevCol is composed of multiple copies of subnetworks, named columns respectively, between which multi-level reversible connections are employed. Such architectural scheme attributes RevCol very different behavior from conventional networks: during forward propagation, features in RevCol are learned to be gradually disentangled when passing through each column, whose total information is maintained rather than compressed or discarded as other network does. Our experiments suggest that CNN-style RevCol models can achieve very competitive performances on multiple computer vision tasks such as image classification, object detection and semantic segmentation, especially with large parameter budget and large dataset. For example, after ImageNet-22K pre-training, RevCol-XL obtains 88.2% ImageNet-1K accuracy. Given more pre-training data, our largest model RevCol-H reaches 90.0% on ImageNet-1K, 63.8% APbox on COCO detection minival set, 61.0% mIoU on ADE20k segmentation. To our knowledge, it is the best COCO detection and ADE20k segmentation result among pure (static) CNN models. Moreover, as a general macro architecture fashion, RevCol can also be introduced into transformers or other neural networks, which is demonstrated to improve the performances in both computer vision and NLP tasks. We release code and models at https://github.com/megvii-research/RevCol

PaperPDFCodeCode Syntology ran

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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2212.11696")

Code

Syntology Ran 8 of 11 code samples harvested from 1 repository linked to this paper; 3 have no recorded run. Of those that ran: 8 ran with no contract checked.

By repository: official repository: 11 samples from 1 repository, 8 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

megvii-research/revcol officialmentioned in papermentioned on GitHubpytorchApache-2.0 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

11 samples harvested; 8 ran; 0 honoured the contract we drafted; 3 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

8ran
3unverified

Licence: 0 of the 11 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 megvii-research/revcol. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

Classifier megvii-research/revcol/models/revcol.py official repository ran fingerprinted Apache-2.0 (permissive) · 62fc75450a52fc56 · report
ConvNextBlock megvii-research/revcol/models/revcol.py official repository ran fingerprinted Apache-2.0 (permissive) · 008b0e076048797d · report
Decoder megvii-research/revcol/models/revcol.py official repository ran Apache-2.0 (permissive) · 0aa0f3056567a82f · report
Fusion megvii-research/revcol/models/revcol.py official repository ran Apache-2.0 (permissive) · 7bc303c0be07360e · report
LayerNorm megvii-research/revcol/models/revcol.py official repository ran fingerprinted Apache-2.0 (permissive) · 3d31e56894e46115 · report
ReverseFunction megvii-research/revcol/models/revcol.py official repository ran Apache-2.0 (permissive) · 1939d987f30fd46b · report
SimDecoder megvii-research/revcol/models/revcol.py official repository ran fingerprinted Apache-2.0 (permissive) · 9da4f6ea726fdfb1 · report
UpSampleConvnext megvii-research/revcol/models/revcol.py official repository ran fingerprinted Apache-2.0 (permissive) · a214203738550dde · report
FullNet megvii-research/revcol/models/revcol.py official repository unverified Apache-2.0 (permissive) · c57688066cd3ac52 · report
Level megvii-research/revcol/models/revcol.py official repository unverified Apache-2.0 (permissive) · d6bc6096b81fd178 · report
SubNet megvii-research/revcol/models/revcol.py official repository unverified Apache-2.0 (permissive) · 6d63037ed95088f7 · report

Tasks

Image ClassificationObject DetectionSegmentationSemantic Segmentationimage-classificationobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Classification ImageNet RevCol-H Number of params 2158M #11 of 1060 Archive leaderboard report
Image Classification ImageNet RevCol-H Top 1 Accuracy 90.0% #11 of 1060 Archive leaderboard report
Object Detection COCO minival RevCol-H(DINO) box AP 63.8 #12 of 220 Archive leaderboard report
Object Detection COCO test-dev RevCol-H(DINO) box mAP 63.8 #13 of 225 Archive leaderboard report
Semantic Segmentation ADE20K RevCol-H (Mask2Former) Params (M) 2439 #10 of 235 Archive leaderboard report
Semantic Segmentation ADE20K RevCol-H (Mask2Former) Validation mIoU 61.0 #10 of 235 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.

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