AI Paper Atlas

Research map / Vision-language and multimodal / Cross-modal learning

ENHash: Error Notebook-Guided Fine-Grained Learning for Unsupervised Cross-Modal Hashing

Hao Fu, Zebing Yao, Chuangchuang Tan, Guanghua Gu

AAAI 2026 · Vision-language and multimodal › Cross-modal learning · approach: Cross-modal hashing · 0 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 unsupervised incremental clustering instead of ordinary hierarchical clustering (ablation)ENHash · MS COCO 64-bitMAP@ALL I→T: 0.621 -> 0.669Improved
add unsupervised incremental clustering instead of ordinary hierarchical clustering (ablation)ENHash · MS COCO 64-bitMAP@ALL T→I: 0.627 -> 0.667Improved
add multi-cluster boundary loss to Ldis+Latt (ablation)ENHash · MS COCO 64-bitMAP@ALL I→T: 0.658 -> 0.669Improved
add multi-cluster boundary loss to Ldis+Latt (ablation)ENHash · MS COCO 64-bitMAP@ALL T→I: 0.662 -> 0.667Improved
add cross-modal attraction loss to Ldis+Lmcb (ablation)ENHash · MS COCO 64-bitMAP@ALL I→T: 0.659 -> 0.669Improved
add cross-modal attraction loss to Ldis+Lmcb (ablation)ENHash · MS COCO 64-bitMAP@ALL T→I: 0.662 -> 0.667Improved
add triplet discrimination loss to Latt+Lmcb (ablation)ENHash · MS COCO 64-bitMAP@ALL I→T: 0.369 -> 0.669Improved
use multi-cluster boundary loss instead of attraction loss alongside Ldis (ablation)ENHash · MS COCO 64-bitMAP@ALL I→T: 0.658 -> 0.659No clear effect
ENHash versus UCCH on text-query retrievalENHash · NUS-WIDE 16-bit and 32-bitMAP@ALL T→I: 0.701 -> 0.735 (16-bit); 0.724 -> 0.759 (32-bit)Improved
ENHash versus UCCH on image-query retrievalENHash · MS COCO 16-bitMAP@ALL I→T: 0.605 -> 0.635Improved
ENHash versus SACHENHash · MIRFlickr 128-bitMAP@ALL I→T: 0.734 -> 0.763Improved
ENHash versus supervised fine-grained CMCM on image-queryENHash · FG-XMedia (128-bit)MAP@ALL I→T: 0.349 -> 0.610Improved

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