AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

Zoom Better to See Clearer: Human and Object Parsing with Hierarchical Auto-Zoom Net

Fangting Xia, Peng Wang, Liang-Chieh Chen, Alan L. Yuille

ECCV 2016 · Detection and segmentation › Open-set and few-shot detection · approach: Object-level representation learning · 157 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 the object-scale AZN (ablation)HAZN (part-scale only) · PASCAL-Person-PartmIOU (%): 54.78 -> 57.54Improved
add the part-scale AZN (ablation)HAZN (object-scale only) · PASCAL-Person-PartmIOU (%): 56.50 -> 57.54Improved
add object-scale AZN (ablation)HAZN (part-scale only) · PASCAL-Person-Part (human size XS)mIOU (%): 38.2 -> 47.1Improved
add part-scale AZN (ablation)HAZN (object-scale only) · PASCAL-Person-Part (human size XS)mIOU (%): 45.1 -> 47.1Improved
replace DeepLab-LargeFOV with HAZNDeepLab-LargeFOV · PASCAL-Person-PartmIOU (%): 51.78 -> 57.54Improved
replace DeepLab-LargeFOV with HAZN on small humansDeepLab-LargeFOV · PASCAL-Person-Part (human size XS)mIOU (%): 32.5 -> 47.1Improved
add CRF post-processingDeepLab-LargeFOV · PASCAL-Person-PartmIOU (%): 51.78 -> 52.95Improved
use auto-zoom instead of fixed multi-scale averagingMulti-Scale Averaging · PASCAL-Person-PartmIOU (%): 54.91 -> 57.54Improved
use auto-zoom instead of scale attentionMulti-Scale Attention · PASCAL-Person-PartmIOU (%): 56.39 -> 57.54Improved
replace DeepLab-LargeFOV with HAZN for instance-wise parsingDeepLab-LargeFOV · PASCAL-Person-PartAP^r_part (%): 31.32 -> 43.72Improved
replace Multi-Scale Attention with HAZN for instance-wise parsingMulti-Scale Attention · PASCAL-Person-PartAP^r_part (%): 37.53 -> 43.72Improved
replace DeepLab-LargeFOV with HAZN on horsesDeepLab-LargeFOV · Horse-Cow (Horse)mIOU avg: 66.25 -> 72.36Improved

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