AI Paper Atlas

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

Semantic Part Detection via Matching: Learning to Generalize to Novel Viewpoints From Limited Training Data

Yutong Bai, Qing Liu, Lingxi Xie, Weichao Qiu, Yan Zheng, Alan L. Yuille

ICCV 2019 · Detection and segmentation › Open-set and few-shot detection · approach: Object-level representation learning · 5 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 3D CAD-model matching (Ours) instead of end-to-end Faster R-CNNsemantic part detection · VSP sedan, 16 training samples, L0mAP (%): 31.64 -> 42.25Improved
use matching approach with 64 training samples instead of Faster R-CNNsemantic part detection · VSP sedan, 64 training samples, L0mAP (%): 55.43 -> 45.39Hurt
use matching approach instead of Faster R-CNN under heaviest occlusionsemantic part detection · VSP sedan, 64 training samples, L3mAP (%): 13.75 -> 16.75Improved
use matching approach instead of DeepVoting under occlusion L2semantic part detection · VSP sedan, 16 training samples, L2mAP (%): 13.92 -> 23.87Improved
increase training images from 16 to 64 for Ours (ablation)Ours · VSP sedan, L0mAP (%): 42.25 -> 45.39Improved
increase training images from 16 to 64 for Faster R-CNN (ablation)Faster R-CNN · VSP sedan, L0mAP (%): 31.64 -> 55.43Improved
use matching approach instead of Faster R-CNN on unseen elevation viewpointssemantic part detection · VSP sedan, unseen elevation 20 deg, 16 samplesmAP (%): 16.02 -> 45.32Improved
use matching approach instead of DeepVoting on unseen viewpointssemantic part detection · VSP sedan, unseen elevation 20 deg, 64 samplesmAP (%): 33.82 -> 45.88Improved
transfer sedan-trained model to minivan (prototype shift) for Ours (ablation)Ours · VSP, 32 training samplesmAP (%): 47.27 -> 35.58Hurt
transfer sedan-trained model to SUV for Ours (ablation)Ours · VSP, 32 training samplesmAP (%): 47.27 -> 42.80Hurt
use matching approach instead of Faster R-CNN on bicyclesemantic part detection · VSP bicycleaccuracy (%): 44.02 -> 67.16Improved
use matching approach instead of DeepVoting on motorbikesemantic part detection · VSP motorbikeaccuracy (%): 31.88 -> 42.81Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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