AI Paper Atlas

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

Hashing with Mutual Information

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

TPAMI 2019 · Label-efficient and robust learning › Recognition and long-tail · approach: Correspondence and causal representation learning · 99 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
use mutual information objective instead of DTSH triplet losshashing with VGG-F · CIFAR-10 (500 per class training)mAP: 0.765 -> 0.791 (32 bits), 0.774 -> 0.816 (48 bits)Improved
use mutual information objective instead of DTSHhashing with VGG-F · NUSWIDE (500 per label training)mAP@5K: 0.773 -> 0.773 (12 bits), 0.820 (DTSH 0.813) at 24 bitsMixed
use mutual information objective with more training datahashing with VGG-F · CIFAR-10 and NUSWIDE (full training set)mAP: 0.926 -> 0.943 (CIFAR 48 bits), 0.756 -> 0.798 (NUSWIDE 16 bits)Improved
use mutual information objective instead of HashNethashing with AlexNet · ImageNet100mAP@1K: 0.506 -> 0.569 (16 bits)Improved
use mutual information objective with one-layer embedding on GISTshallow hashing · 22K LabelMemAP: 0.369 -> 0.384 (16 bits), 0.582 -> 0.598 (64 bits)Improved
learn hashing with MI objective (online, 20K examples) from LSH initMIHash single-layer on fc7 · CIFAR-10mAP: 0.22 -> 0.68Improved
increase steepness gamma from 1 (ablation)MIHash · CIFAR-10 (500 per class training), 32 bitsmAP: 0.791 -> 0.768 (5), 0.749 (10), 0.776 (20)No clear effect
vary minibatch size M from 256 (ablation)MIHash · CIFAR-10 (500 per class training), 32 bitsmAP: 0.791 -> 0.771 (64), 0.765 (128), 0.783 (512)No clear effect
MI objective value correlates with mAPrandom LSH-style hash mappings · CIFAR-10mAP: Pearson Correlation Coefficient score of 0.98Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

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