AI Paper Atlas

Research map / Detection and segmentation / Weakly supervised detection and segmentation

Improving Pedestrian Attribute Recognition With Weakly-Supervised Multi-Scale Attribute-Specific Localization

Chufeng Tang, Lu Sheng, Zhaoxiang Zhang, Xiaolin Hu

ICCV 2019 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Weakly supervised object localization · 155 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 ALM at a single level (incep_5b) (ablation)BN-Inception baseline · RAPmA: 75.76 -> 77.45Improved
add ALMs at three feature levels instead of one (ablation)ALM single level · RAPmA: 77.45 -> 78.89Improved
combine levels by element-wise addition (FPN-like) (ablation)multi-level ALM · RAPmA: 78.89 -> 78.51Hurt
combine levels by concatenation instead of addition (ablation)multi-level ALM · RAPmA: 78.51 -> 79.93Improved
add channel-attention sub-network (ablation)top-down concatenation · RAPmA: 79.93 -> 80.61Improved
use element-wise maximum instead of averaging in deep supervision voting (ablation)ALM with deep supervision · RAPmA: 80.70 -> 81.87Improved
add ALMs to the full model (remove all ALMs) (ablation)full model · RAPmA: 78.91 -> 81.87Improved
attribute-specific box localization instead of rigid body parts (ablation)ALM framework · RAPmA: 76.56 -> 81.87Improved
attribute-specific box localization instead of attention masks (ablation)ALM framework · RAPmA: 78.35 -> 81.87Improved
add the full proposed method to the BN-Inception baseline (ablation)BN-Inception · PA-100KmA: 77.47 -> 80.68Improved
add the full proposed method to the BN-Inception baselineBN-Inception · PETAmA: 82.66 -> 86.30Improved
add the full proposed method to the BN-Inception baselineBN-Inception · RAPmA: 75.76 -> 81.87Improved

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