Papers › Pose-Robust Face Recognition via Deep Residual Equivariant Mapping

Pose-Robust Face Recognition via Deep Residual Equivariant Mapping

2 Mar 2018CVPR 2018 6arXiv:1803.00839archive 2025-07-28

Kaidi Cao, Yu Rong, Cheng Li, Xiaoou Tang, Chen Change Loy

Face recognition achieves exceptional success thanks to the emergence of deep learning. However, many contemporary face recognition models still perform relatively poor in processing profile faces compared to frontal faces. A key reason is that the number of frontal and profile training faces are highly imbalanced - there are extensively more frontal training samples compared to profile ones. In addition, it is intrinsically hard to learn a deep representation that is geometrically invariant to large pose variations. In this study, we hypothesize that there is an inherent mapping between frontal and profile faces, and consequently, their discrepancy in the deep representation space can be bridged by an equivariant mapping. To exploit this mapping, we formulate a novel Deep Residual EquivAriant Mapping (DREAM) block, which is capable of adaptively adding residuals to the input deep representation to transform a profile face representation to a canonical pose that simplifies recognition. The DREAM block consistently enhances the performance of profile face recognition for many strong deep networks, including ResNet models, without deliberately augmenting training data of profile faces. The block is easy to use, light-weight, and can be implemented with a negligible computational overhead.

PaperPDFConference PDFCodeCode 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="1803.00839")

Code

Syntology Ran 1 of 15 code samples harvested from 1 repository linked to this paper; 14 have no recorded run. Of those that ran: 1 ran · our draft was wrong.

By repository: community (archive-listed): 15 samples from 1 repository, 1 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

penincillin/DREAM mentioned on GitHubpytorchBSD-2-Clause 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

15 samples harvested; 1 ran; 0 honoured the contract we drafted; 14 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.

1ran · our draft was wrong
14unverified

Licence: 0 of the 15 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 penincillin/DREAM. “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.

conv3x3 penincillin/DREAM/src/CFP/ResNet.py community (archive-listed) ran · our draft was wrong BSD-2-Clause (permissive) · fac5364e2f53c6db · report
calc_eer penincillin/DREAM/src/CFP/eval_roc.py community (archive-listed) unverified BSD-2-Clause (permissive) · 6edef450883b178e · report
eval_roc penincillin/DREAM/src/CFP/eval_roc.py community (archive-listed) unverified BSD-2-Clause (permissive) · 8dc8afb9def7beab · report
gen_batch penincillin/DREAM/src/stitching/branch_train.py community (archive-listed) unverified BSD-2-Clause (permissive) · 1dc8a5fafca11ad9 · report
get_dict penincillin/DREAM/src/stitching/branch_train.py community (archive-listed) unverified BSD-2-Clause (permissive) · 76c04a1779da3515 · report
get_idle_gpu penincillin/DREAM/src/end2end/slurm.py community (archive-listed) unverified BSD-2-Clause (permissive) · 68b0020055f92a8d · report
load_feat penincillin/DREAM/src/CFP/eval_roc.py community (archive-listed) unverified BSD-2-Clause (permissive) · e53e7c8483ea523a · report
load_imgs penincillin/DREAM/src/CFP/selfDefine.py community (archive-listed) unverified BSD-2-Clause (permissive) · 0e2356a2cc760d35 · report
load_imgs penincillin/DREAM/src/end2end/selfDefine.py community (archive-listed) unverified BSD-2-Clause (permissive) · 6f8560ba80c4fa6e · report
resnet18 penincillin/DREAM/src/CFP/ResNet.py community (archive-listed) unverified BSD-2-Clause (permissive) · fc7697ccba1dfe96 · report
resnet18 penincillin/DREAM/src/IJBA/ResNet.py community (archive-listed) unverified BSD-2-Clause (permissive) · abc2b710282f3b3f · report
resnet18 penincillin/DREAM/src/end2end/ResNet.py community (archive-listed) unverified BSD-2-Clause (permissive) · 16fb1b03af4952ef · report
resnet34 penincillin/DREAM/src/CFP/ResNet.py community (archive-listed) unverified BSD-2-Clause (permissive) · e670ddb9c9a43661 · report
resnet34 penincillin/DREAM/src/IJBA/ResNet.py community (archive-listed) unverified BSD-2-Clause (permissive) · bafccd9145f43de0 · report
resnet34 penincillin/DREAM/src/end2end/ResNet.py community (archive-listed) unverified BSD-2-Clause (permissive) · 321f5f251cf53205 · report

Tasks

Face IdentificationFace RecognitionFace VerificationRobust Face Recognition

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Face Identification IJB-A Deep Residual Equivariant Mapping Accuracy 94.60% #2 of 3 Archive leaderboard report
Face Verification IJB-A Deep Residual Equivariant Mapping TAR @ FAR=0.01 94.40% #7 of 17 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

1x1 ConvolutionAverage PoolingBatch NormalizationBottleneck Residual BlockConvolutionGlobal Average PoolingKaiming InitializationMax PoolingReLUResidual BlockResidual Connection

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