Papers › Unsupervised Learning of Landmarks by Descriptor Vector Exchange

Unsupervised Learning of Landmarks by Descriptor Vector Exchange

18 Aug 2019ICCV 2019 10arXiv:1908.06427archive 2025-07-28

James Thewlis, Samuel Albanie, Hakan Bilen, Andrea Vedaldi

Equivariance to random image transformations is an effective method to learn landmarks of object categories, such as the eyes and the nose in faces, without manual supervision. However, this method does not explicitly guarantee that the learned landmarks are consistent with changes between different instances of the same object, such as different facial identities. In this paper, we develop a new perspective on the equivariance approach by noting that dense landmark detectors can be interpreted as local image descriptors equipped with invariance to intra-category variations. We then propose a direct method to enforce such an invariance in the standard equivariant loss. We do so by exchanging descriptor vectors between images of different object instances prior to matching them geometrically. In this manner, the same vectors must work regardless of the specific object identity considered. We use this approach to learn vectors that can simultaneously be interpreted as local descriptors and dense landmarks, combining the advantages of both. Experiments on standard benchmarks show that this approach can match, and in some cases surpass state-of-the-art performance amongst existing methods that learn landmarks without supervision. Code is available at www.robots.ox.ac.uk/~vgg/research/DVE/.

PaperPDFConference PDFCode

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

Code

jamt9000/DVE officialpytorchNOASSERTION 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

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Facial Landmark DetectionObjectUnsupervised Facial Landmark Detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Unsupervised Facial Landmark Detection 300W DVE NME 4.65 #1 of 4 Archive leaderboard report
Unsupervised Facial Landmark Detection AFLW (Zhang CVPR 2018 crops) DVE NME 6.54 #2 of 4 Archive leaderboard report
Unsupervised Facial Landmark Detection AFLW-MTFL DVE NME 7.53 #1 of 3 Archive leaderboard report
Unsupervised Facial Landmark Detection MAFL DVE NME 2.86 #3 of 13 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