AI Paper Atlas

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

From Easy to Hard: Progressive Active Learning Framework for Infrared Small Target Detection with Single Point Supervision

Chuang Yu, Jinmiao Zhao, Yunpeng Liu, Sicheng Zhao, Yimian Dai, Xiangyu Yue

ICCV 2025 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Pseudo-labeling for semi-supervised detection · 19 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 model pre-start with EPG easy samples (ablation)PAL (MSDA-Net) · SIRST3-Test (coarse point)IoU (%): 1.23 -> 56.24Improved
add coarse outer updates (COU) to pre-start (ablation)PAL (MSDA-Net) · SIRST3-Test (coarse point)IoU (%): 56.24 -> 61.64Improved
add fine inner updates (FIU) to pre-start (ablation)PAL (MSDA-Net) · SIRST3-Test (coarse point)IoU (%): 56.24 -> 61.66Improved
combine COU and FIU (fine dual-update) (ablation)PAL (MSDA-Net) · SIRST3-Test (coarse point)IoU (%): 61.66 -> 69.38Improved
add decay factor lambda=0.97 (ablation)PAL (MSDA-Net) · SIRST3-Test (coarse point)IoU (%): 67.90 -> 69.38Improved
use EEDM loss instead of Dice loss (ablation)PAL (MSDA-Net) · SIRST3-Test (coarse point)IoU (%): 64.38 -> 69.38Improved
use EEDM loss instead of BCE loss (ablation)PAL (MSDA-Net) · SIRST3-Test (coarse point)IoU (%): 69.26 -> 69.38No clear effect
use EEDM loss instead of Focal loss (ablation)PAL (MSDA-Net) · SIRST3-Test (coarse point)IoU (%): 68.89 -> 69.38Improved
select only easy samples initially (MP) vs all samples (MP-1) (ablation)PAL (MSDA-Net) · SIRST3-Test (coarse point)IoU (%): 32.86 -> 56.24Improved
gradually add hard samples via COU on top of easy-only training with FIU (ablation)PAL (MSDA-Net) · SIRST3-Test (coarse point)IoU (%): 61.66 -> 69.38Improved
update period 5 instead of 1 (ablation)PAL (MSDA-Net) · SIRST3-Test (coarse point)IoU (%): 66.35 -> 69.38Improved
learning rate 1e-3 instead of 5e-5 (ablation)PAL (MSDA-Net) · SIRST3-Test (coarse point)IoU (%): 59.68 -> 69.38Improved

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