AI Paper Atlas

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

HashNet: Deep Learning to Hash by Continuation

Zhangjie Cao, Mingsheng Long, Jianmin Wang, Philip S. Yu

ICCV 2017 · Label-efficient and robust learning › Recognition and long-tail · approach: Correspondence and causal representation learning · 799 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 weighted maximum likelihood (ablation)HashNet · ImageNet (64 bits)MAP: 0.5992 -> 0.6835Improved
add weighted maximum likelihood (ablation)HashNet · ImageNet (16 bits)MAP: 0.3350 -> 0.5059Improved
add weighted maximum likelihood (ablation)HashNet · NUS-WIDE (64 bits)MAP: 0.6933 -> 0.7163Improved
add weighted maximum likelihood (ablation)HashNet · MS COCO (64 bits)MAP: 0.7348 -> 0.7362No clear effect
train with continuation to learn sgn codes instead of tanh plus binarization (ablation)HashNet · ImageNet (64 bits)MAP: 0.6061 -> 0.6835Improved
train with continuation to learn sgn codes instead of tanh plus binarization (ablation)HashNet · NUS-WIDE (64 bits)MAP: 0.7020 -> 0.7163Improved
train with continuation to learn sgn codes instead of tanh plus binarization (ablation)HashNet · MS COCO (64 bits)MAP: 0.7138 -> 0.7362Improved
use continuous similarity from label overlap (ablation)HashNet · NUS-WIDE (64 bits)MAP: 0.7163 -> 0.7259Improved
use continuous similarity from label overlap (ablation)HashNet · ImageNetMAP: 0.6835 -> 0.6835No clear effect
use HashNet instead of DHNdeep hashing · ImageNet (16 bits)MAP: 0.3106 -> 0.5059Improved
use HashNet instead of DHN (zero-shot protocol)deep hashing · ImageNet zero-shot (16 bits)MAP: 0.2891 -> 0.4411Improved
use HashNet instead of DHNdeep hashing · MS COCO (64 bits)MAP: 0.6944 -> 0.7362Improved

Later papers that compared with this method

6 later accepted papers report HashNet as a baseline in their results tables; 5 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