AI Paper Atlas

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

Supervised Learning of Semantics-Preserving Hash via Deep Convolutional Neural Networks

Huei‐Fang Yang, Kevin Lin, Chu‐Song Chen

TPAMI 2017 · Label-efficient and robust learning › Recognition and long-tail · approach: Correspondence and causal representation learning · 341 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 binarization term E2 (beta=1) to label-consistency loss (ablation)SSDH · CIFAR-10 (48 bits)mAP (%): 90.70 -> 91.19Improved
add equal-sparsity term E3 (gamma=1) on top of E1 and E2 (ablation)SSDH · CIFAR-10 (48 bits)mAP (%): 91.19 -> 91.45Improved
use L2 instead of L1 norm loss (ablation)SSDH · CIFAR-10 (12 bits)mAP (%): 87.25 -> 90.59Improved
use L2 instead of L1 norm loss (ablation)SSDH · MNIST (12 bits)mAP (%): 98.90 -> 99.31No clear effect
use L2 margin instead of L1 margin in maximum-margin loss (ablation)SSDH · NUS-WIDE (12 bits)mAP (%): 71.73 -> 85.17Improved
use L2 margin instead of L1 margin in maximum-margin loss (ablation)SSDH · UT-ZAP50K (48 bits)mAP (%): 65.94% -> 71.91%Improved
replace two-stage fine-tuned AlexNet + CCA-ITQ with end-to-end SSDHhashing on Yahoo-1M · Yahoo-1M (128 bits)mAP (%): 61.69 -> 66.63Improved
replace AlexNet with VGG16 backboneSSDH · ILSVRC2012 (512 bits)mAP (%): 46.07 -> 61.47Improved
replace AlexNet with VGG16 backboneSSDH · CIFAR-10 (48 bits)mAP (%): 91.45 -> 92.69Improved
use VGG11 backbone instead of VGG16SSDH · CIFAR-10 (48 bits)mAP (%): 92.69 -> 88.40Hurt
replace VGG16 fully connected layers with average pooling (VGG-Avg)SSDH · CIFAR-10 (48 bits)mAP (%): 92.69 -> 90.75Mixed
remove 50% of labels of multi-label training imagesSSDH (VGG16) · NUS-WIDE (48 bits)mAP (%): 88.97% -> 88.02%No clear effect

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