AI Paper Atlas

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

SUBIC: A Supervised, Structured Binary Code for Image Search

Himalaya Jain, Joaquin Zepeda, Patrick Perez, Remi Gribonval

ICCV 2017 · Label-efficient and robust learning › Recognition and long-tail · approach: Correspondence and causal representation learning · 84 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 supervised block-softmax encoding instead of unsupervised LSQ quantizationVGG-128 features · VOC2007 cross-domain retrievalmAP: 0.4993 -> 0.5600Improved
add supervised encoding instead of unsupervised LSQVGG-128 features · ImageNet val retrievalmAP: 0.1882 -> 0.2543Improved
train FC1 as well (3-layer instead of 2-layer) (ablation)SuBiC · VOC2007 cross-domain retrievalmAP: 0.5600 -> 0.5588No clear effect
train FC1 as well (3-layer instead of 2-layer) (ablation)SuBiC · Caltech-101 cross-domain retrievalmAP: 0.3923 -> 0.4033Improved
train FC1 as well (3-layer instead of 2-layer) (ablation)SuBiC · ImageNet val retrievalmAP: 0.2543 -> 0.2810Improved
increase bit rate from 12 to 48 bits (ablation)SuBiC · Cifar-10 category retrievalmAP: 0.6349 -> 0.6863Improved
use SuBiC instead of the supervised hashing method DSH64-bit codes · Oxford5K instance retrievalmAP: 0.2108 -> 0.2626Improved
use SuBiC 64-bit code instead of PQ for compressed classificationVGG-128 · ImageNet val classificationtop-1 accuracy: 39.88 -> 47.77Improved
binarize the soft code to a 64-bit binary code (ablation)SuBiC · ImageNet val classificationtop-1 accuracy: 50.07 -> 47.77Hurt
binarize the soft code to a 64-bit binary code (ablation)SuBiC · VOC2007 classificationmAP: 70.20 -> 67.86Hurt
set entropy weight ratio gamma/mu to 1 instead of other ratios (ablation)SuBiC · category retrievalmAPImproved
increase mean-entropy weight gamma relative to mu (ablation)SuBiC · ImageNet val and VOC2007 code statisticsone-hot closenessImproved

Later papers that compared with this method

2 later accepted papers report SUBIC as a baseline in their results tables; 2 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