AI Paper Atlas

Research map / Detection and segmentation / CNN features

Unsupervised Part Discovery via Descriptor-Based Masked Image Restoration with Optimized Constraints

Jiahao Xia, Yike Wu, Wenjian Huang, Jianguo Zhang, Jian Zhang

ICCV 2025 · Detection and segmentation › CNN features · approach: Local features and context in CNNs · 2 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 foreground loss L_f (ablation)MPAE · PartImageNet Segmentation (K=50)NMI (%): 0.00 -> 55.10Improved
add background loss L_b (ablation)MPAE · PartImageNet Segmentation (K=50)NMI (%): 39.36 -> 55.10Improved
add total variation loss L_v (ablation)MPAE · PartImageNet Segmentation (K=50)NMI (%): 14.37 -> 55.10Improved
add entropy loss L_e (ablation)MPAE · PartImageNet Segmentation (K=50)NMI (%): 52.51 -> 55.10Improved
add reconstruction loss L_r (ablation)MPAE · PartImageNet Segmentation (K=50)NMI (%): 22.32 -> 55.10Improved
add semantic constraint L_s (ablation)MPAE · PartImageNet Segmentation (K=50)NMI (%): 56.42 -> 55.10Mixed
add semantic constraint L_s (ablation)MPAE · PartImageNet Segmentation (K=50)average discovered parts per image: 3.94 -> 9.27Improved
raise masking ratio from 50% to 90% (ablation)MPAE · PartImageNet Segmentation (K=50)NMI (%): 45.50 -> 55.10Improved
use masking ratio 100% instead of 90% (ablation)MPAE · PartImageNet Segmentation (K=50)NMI (%): 55.10 -> 43.39Hurt
add structural difference penalty (VGG-19) to L_r (ablation)MPAE · PartImageNet Segmentation (K=50)NMI (%): 19.65 -> 55.10Improved
increase encoder layers from 1 to 2 (ablation)MPAE · PartImageNet Segmentation (K=50)NMI (%): 50.71 -> 55.10Improved
increase decoder layers from 2 to 6 (ablation)MPAE · PartImageNet Segmentation (K=50)NMI (%): 55.10 -> 52.69Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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