AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

MIHash: Online Hashing With Mutual Information

Fatih Cakir, Kun He, Sarah Adel Bargal, Stan Sclaroff

ICCV 2017 · Label-efficient and robust learning › Recognition and long-tail · approach: Correspondence and causal representation learning · 101 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add mutual information Trigger Update to OKHOKH · CIFAR-10 online (32 bits)AUC of mAP: 0.259 -> 0.287Improved
add Trigger Update to OKHOKH · LabelMe online (32 bits)AUC of mAP: 0.198 -> 0.374Improved
add Trigger Update to AdaptHashAdaptHash · CIFAR-10 online (32 bits)AUC of mAP: 0.218 -> 0.250Improved
add Trigger Update to OSHOSH · CIFAR-10 online (32 bits)AUC of mAP: 0.463 -> 0.466No clear effect
add Trigger Update to OSHOSH · Places205 online (32 bits)AUC of mAP: 0.246 -> 0.236Hurt
add Trigger Update to OKHOKH · LabelMe online (32 bits)hash table updates: reduced by a factor of 67Improved
raise TU threshold theta from 0 to at least 0.2 (ablation)OKH · CIFAR-10 online (32 bits)AUC of mAP: 0.287 -> 0.134Hurt
raise TU threshold theta from 0 to at least 0.1 (ablation)OKH · Places205 online (32 bits)AUC of mAP: 0.161 -> 0.014Hurt
train MIHash for full 100 epochs instead of one epoch (ablation)MIHash · CIFAR-10 supervised Setting 1 (48 bits)mAP: 0.609 -> 0.746Improved
use mutual information objective instead of pairwise or triplet objectivesMIHash vs DTSH · CIFAR-10 supervised Setting 1 (48 bits)mAP: 0.702 -> 0.746Improved
use mutual information objective with end-to-end VGG-FMIHash vs DTSH · CIFAR-10 supervised Setting 2 (48 bits)mAP: 0.934 -> 0.942Improved
optimize mutual information with MIHash from random hash mappingMIHash · CIFAR-10 test, 20K onlinemAP: 0.22 -> 0.68Improved

Later papers that compared with this method

4 later accepted papers report MIHash as a baseline in their results tables; 4 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy