AI Paper Atlas

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

Hierarchical Encoding Tree with Modality Mixup for Cross-modal Hashing

Zhiping Xiao, Junyu Luo, Hang Zhou, Yusheng Zhao, Xiao Luo, Pengyun Wang, Wei Ju, Siyu Heng, Ming Zhang

ICLR 2026 · Vision-language and multimodal › Cross-modal learning · approach: Cross-modal hashing

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 intra-modal KNN samples to text-image pairs (ablation)HINT V1 · MIRFlickr-25K I2T 128-bitMAP (%): 73.2 -> 73.8Improved
add hierarchical encoding tree sample selection (ablation)HINT V2 · MIRFlickr-25K I2T 128-bitMAP (%): 73.8 -> 74.2Improved
add hierarchical encoding tree sample selection (ablation)HINT V2 · MS-COCO I2T 128-bitMAP (%): 59.1 -> 60.0Improved
add curriculum-based progressive mixup (ablation)HINT V3 · NUS-WIDE I2T 128-bitMAP (%): 65.9 -> 67.0Improved
add proxy-based consistency learning (ablation)HINT V4 · MIRFlickr-25K T2I 128-bitMAP (%): 74.1 -> 74.6Improved
add proxy-based consistency learning (ablation)HINT V4 · MS-COCO I2T 128-bitMAP (%): 60.7 -> 61.1Improved
use cosine instead of L1 similarity for tree construction (ablation)HINT · MIRFlickr-25K I2TMAP (%): 73.5 -> 75.5Improved
use cosine instead of L2 similarity for tree construction (ablation)HINT · MIRFlickr-25K I2TMAP (%): 74.8 -> 75.5Improved
iteratively update the tree every 5 epochs (ablation)HINT · MIRFlickr-25K I2T / MS-COCO I2TMAP (%): 75.5 -> 75.0; 61.1 -> 60.5Hurt
iteratively update the tree every 5 epochs (ablation)HINT · MIRFlickr-25K T2IMAP (%): 74.6 -> 74.7No clear effect
increase K from 3 to 5 neighbours (ablation)HINT · MIRFlickr-25KMAPHurt
corrupt 10% of pairs: HINT vs DEMODEMO · MIRFlickr-25K I2T 128-bit noisyMAP (%): 71.4 -> 74.4Improved

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