AI Paper Atlas

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

Modeling Label Correlations with Latent Context for Multi-Label Recognition

Zhaomin Chen, Quan Cui, Ruoxi Deng, Jie Hu, Guodao Zhang

ECCV 2024 · Label-efficient and robust learning › Recognition and long-tail · approach: Partial and multi-label learning · 1 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 multi-level context feature fusion (MLFF) to the backbone (ablation)ResNet-101 · MS-COCOmAP: 79.1 -> 80.9Improved
add latent context information embedding (context-aware categorical features) (ablation)ResNet-101 + MLFF · MS-COCOmAP: 80.9 -> 83.2Improved
add Transformer encoder for full-label correlations (ablation)ResNet-101 + MLFF + LCIE · MS-COCOmAP: 83.2 -> 84.0Improved
model correlations from spatial features directly instead of context-aware features (ablation)ResNet-101 + MLFF + LCIE · MS-COCOmAP: 82.7 vs 84.7Hurt
add partial-label correlation modeling with shared encoder (ablation)ResNet-101 full model · MS-COCOmAP: 84.7 -> 86.8Improved
share Transformer encoder parameters between Full and Partial (ablation)ResNet-101 full model · MS-COCOmAP: 85.2 -> 86.8Improved
apply the method with a stronger Swin-L (ImageNet-21K) backboneSwin-L (21K) · MS-COCOmAP: 89.0 -> 90.9Improved
use proposed method instead of Q2L (same input size)multi-label recognition · MS-COCO 448x448mAP: 84.9 -> 86.8Improved
use proposed method with 90% of labels discardedResNet-101 · MS-COCO partial labels (90% discarded)mAP: 56.6 -> 72.0Improved
use proposed method on noisy NUS-WIDE labelsResNet-101 · NUS-WIDEmAP: 65.1 -> 67.1Improved

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