Papers › MIC: Mining Interclass Characteristics for Improved Metric Learning

MIC: Mining Interclass Characteristics for Improved Metric Learning

25 Sep 2019ICCV 2019 10arXiv:1909.11574archive 2025-07-28

Karsten Roth, Biagio Brattoli, Björn Ommer

Metric learning seeks to embed images of objects suchthat class-defined relations are captured by the embeddingspace. However, variability in images is not just due to different depicted object classes, but also depends on other latent characteristics such as viewpoint or illumination. In addition to these structured properties, random noise further obstructs the visual relations of interest. The common approach to metric learning is to enforce a representation that is invariant under all factors but the ones of interest. In contrast, we propose to explicitly learn the latent characteristics that are shared by and go across object classes. We can then directly explain away structured visual variability, rather than assuming it to be unknown random noise. We propose a novel surrogate task to learn visual characteristics shared across classes with a separate encoder. This encoder is trained jointly with the encoder for class information by reducing their mutual information. On five standard image retrieval benchmarks the approach significantly improves upon the state-of-the-art.

PaperPDFConference PDFCode

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

Code

Confusezius/metric-learning-mining-interclass-characteristics officialmentioned in papermentioned on GitHubpytorch report
Confusezius/ICCV2019_MIC mentioned on GitHubpytorch 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

Image RetrievalMetric LearningRetrieval

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Metric Learning CARS196 ResNet50 (128) + MIC R@1 82.6 #32 of 36 Archive leaderboard report
Metric Learning CUB-200-2011 ResNet50 (128) + MIC R@1 66.1 #19 of 30 Archive leaderboard report
Metric Learning Stanford Online Products ResNet50 (128) + MIC R@1 77.2 #31 of 33 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