AI Paper Atlas

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

Binary Hashing with Semidefinite Relaxation and Augmented Lagrangian

Thanh-Toan Do, Anh-Dzung Doan, Duc-Thanh Nguyen, Ngai-Man Cheung

ECCV 2016 · Label-efficient and robust learning › Recognition and long-tail · approach: Contrastive representation theory · 18 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
infer codes with SDR instead of nonlinear optimization (NOPT)two-step supervised hashing · CIFAR10, 8 bitsprecision@2: 29.09 -> 30.57Improved
infer codes with SDR instead of NOPTtwo-step supervised hashing · MNIST, 8 bitsprecision@2: 81.14 -> 86.33Improved
infer codes with SDR instead of NOPTtwo-step supervised hashing · SUN397, 8 bitsprecision@2: 10.08 -> 12.11Improved
infer codes with AL instead of Graphcuttwo-step supervised hashing · CIFAR10, 8 bitsprecision@2: 28.50 -> 30.07Improved
use SDR instead of AL for binary inferencetwo-step hashing · CIFAR10, 32 bitsprecision@2: 48.02 -> 48.43No clear effect
use SDR instead of AL for binary inferencetwo-step hashing · SUN397, 16 bitsprecision@2: 57.20 -> 59.19Improved
use AL instead of SDR for binary inferencetwo-step hashing · SUN397, 24 bitsprecision@2: 62.98 -> 63.14No clear effect
use SDR/AL codes instead of TSHtwo-step supervised hashing · SUN397, 32 bitsprecision@2: 59.30 -> 61.78Improved
use SDR instead of ITQunsupervised hashing · CIFAR10, 32 bitsprecision@2: 15.36 -> 25.87Improved
use SDR instead of NMFunsupervised hashing · CIFAR10, 32 bits classificationaccuracy: 23.59 -> 29.65Improved
use AL with binary constraint in Lagrangian and tailored init instead of ALMunsupervised hashing · MNIST, 32 bits classificationaccuracy: 73.76 -> 81.13Improved

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