AI Paper Atlas

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

A Shape Transformation-based Dataset Augmentation Framework for Pedestrian Detection

Zhe Chen, Wanli Ouyang, Tongliang Liu, Dacheng Tao

IJCV 2021 · Detection and segmentation › Open-set and few-shot detection · approach: Open-set and unknown object detection · 35 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 shape-guided warping loss L_shape to baseline (ablation)FPN detector · Caltech validation split (ablation)miss rate (%): 10.77 -> 10.58Improved
add shape constraining operation (ablation)STDA · Caltech validation split (ablation)miss rate (%): 10.58 -> 10.31Improved
add cyclic reconstruction loss (ablation)STDA · Caltech validation split (ablation)miss rate (%): 10.31 -> 9.03Improved
add adversarial loss (ablation)STDA · Caltech validation split (ablation)miss rate (%): 9.03 -> 8.56Improved
add environment-aware blending map (ablation)STDA · Caltech validation split (ablation)miss rate (%): 8.56 -> 7.73Improved
add hard positive mining loss (ablation)STDA · Caltech validation split (ablation)miss rate (%): 7.73 -> 7.49Improved
augment Caltech with STDAFPN detector · Caltech testmiss rate (%): 10.4 baseline; around 30% improvementImproved
add multi-scale testing to STDAFPN w STDA · Caltech testmiss rate (%): 30% -> 38% improvementImproved
augment CityPersons with STDAFPN detector · CityPersons valmiss rate (%) Reasonable: 13.9 -> 11.0Improved
add multi-scale testing to STDAFPN w STDA · CityPersons valmiss rate (%) Reasonable: 11.0 -> 10.2Improved
augment Caltech with STDAFPN detector · Caltech test, heavy occlusionmiss rate (%): 59.3 -> 41.9Improved
augment Caltech with STDAFPN detector · Caltech test, partial occlusionmiss rate (%): 22.9 -> 17.2Improved

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