AI Paper Atlas

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

Möbius Transform for Mitigating Perspective Distortions in Representation Learning

Prakash Chandra Chhipa, Meenakshi Subhash Chippa, Kanjar De, Rajkumar Saini, Marcus Liwicki, Mubarak Shah

ECCV 2024 · Detection and segmentation › Open-set and few-shot detection · approach: Object-level representation learning · 4 citations (OpenAlex)

Read the paper

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 MPD augmentation (P=0.6) to supervised ResNet50 training (ablation)ResNet50 · ImageNet-PD PD-BTop-1 accuracy: 61.15 -> 73.01Improved
add MPD augmentation (P=0.6) to supervised ResNet50 training (ablation)ResNet50 · ImageNet val (original)Top-1 accuracy: 76.13 -> 76.19No clear effect
apply MPD with probability 1.0 instead of 0.8 (ablation)supervised:MPD · ImageNet val (original)Top-1 accuracy: 76.34 -> 74.10Hurt
apply MPD IB with probability 1.0 instead of 0.8 (ablation)supervised:MPD IB · ImageNet val (original)Top-1 accuracy: 75.63 -> 74.62Hurt
train ResNet50 with MPD augmentationResNet50 · ImageNet-Xaccuracy: 60.64 -> 63.23Improved
train ResNet50 with MPD augmentationResNet50 · ImageNet-E averageTop-1 accuracy drop: 15.72 -> 13.34Improved
train ResNet50 with MPD augmentation on background-change subsetsResNet50 · ImageNet-E background changesTop-1 accuracyNo clear effect
add MPD-AutoCrowd augmentation to P2P-NetP2P-Net · UCF-CC-50MAE: 172.72 -> 96.80Improved
add MPD-AutoCrowd augmentation to P2P-NetP2P-Net · ShanghaiTech Part BMAE: 6.25 -> 6.61Mixed
add MPD to Clip-ReIdentClip-ReIdent ResNet50x16 · DeepSportRadar re-idmAP (w/o RR): 88.50 -> 91.95Improved
add MPD to Clip-ReIdentClip-ReIdent ViT-L-14 · DeepSportRadar re-idmAP (w/o RR): 96.90 -> 97.02Improved
add MPD-OD augmentation to FasterRCNN and FCOS at P=0.5FasterRCNN, FCOS · COCOdetection accuracy: 3% and 1.6% gainImproved

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