AI Paper Atlas

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

Hashing with Binary Matrix Pursuit

Fatih Cakir, Kun He, Stan Sclaroff

ECCV 2018 · Label-efficient and robust learning › Recognition and long-tail · approach: Correspondence and causal representation learning · 31 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 regressed bit weights (weighted Hamming) over constant step sizes (ablation)HBMP · NUSWIDE nus-1 (16 bits)mAP@5K: 0.675 -> 0.757Improved
add regressed bit weights over constant step sizes (ablation)HBMP · NUSWIDE nus-2 (16 bits)mAP@50K: 0.746 -> 0.804Improved
add regressed bit weights over constant step sizes (ablation)HBMP · NUSWIDE multi-level (16 bits)NDCG: 0.905 -> 0.914Improved
add regressed bit weights over constant step sizes, long codes (ablation)HBMP · 22K LabelMe multi-level (96 bits)NDCG: 0.865 -> 0.917Improved
add regressed bit weights over constant step sizes, short codes (ablation)HBMP · 22K LabelMe multi-level (16 bits)NDCG: 0.837 -> 0.823Hurt
add regressed bit weights over constant step sizes (ablation)HBMP · CIFAR-10 cifar-2 (16 bits)mAP: 0.941 -> 0.942No clear effect
add regressed bit weights over constant step sizes (ablation)HBMP · ImageNet100 (64 bits)mAP@1K: 0.751 -> 0.742No clear effect
infer codes on classes instead of training instances (ablation)two-stage hashing · 10-class synthetic affinitymAP: difference can be as large as 0.40Improved
infer codes on classes instead of instances (residual convergence) (ablation)two-stage hashing · 10-class synthetic affinityresidual norm: 40 bit codes reconstruct class affinity matrixImproved
increase hash function capacity from single layer on GIST to fine-tuned VGG-F (ablation)hash function learning · CIFAR-10 training set, 32-bit codesunmatched bit ratio: above 0.25 -> well below 10%Improved
two-stage HBMP versus MIHashHBMP · CIFAR-10 cifar-1 (12 bits)mAP: 0.738 -> 0.799Improved
two-stage HBMP versus MIHashHBMP · ImageNet100 (64 bits)mAP@1K: 0.694 -> 0.742Improved

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