AI Paper Atlas

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

Unconstrained Foreground Object Search

Yinan Zhao, Brian Price, Scott Cohen, Danna Gurari

ICCV 2019 · Detection and segmentation › Open-set and few-shot detection · approach: Object-level representation learning · 13 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
train the background encoder instead of using frozen pretrained weights (ablation)UFO Search · CAIS (top-100 retrievals)mAP (%): 13.79 -> 32.17Improved
add discriminator-filtered training triplets (ablation)UFO Search · CAIS (top-100 retrievals)mAP (%): 28.97 -> 32.17Improved
train with triplet ranking loss instead of MSE regression (ablation)No Discriminator · CAIS (top-100 retrievals)mAP (%): 24.87 -> 28.97Improved
use the decoupled encoder instead of the discriminator at test time (ablation)UFO Search · CAIS (top-100 retrievals)mAP (%): 25.77 -> 32.17Improved
use the encoder instead of the discriminator for retrieval from 60,000 objects (ablation)UFO Search · 60,000-object databaseretrieval time: 365.6 -> 0.1 secondsImproved
add discriminator-guided sampling heuristics (similar scenes, similar objects) (ablation)training data generation · object database over 60,000random samples needed: 731 -> 32Improved
add discriminator-filtered training triplets (ablation)UFO Search · CAIS (all retrievals)mAP (%): 25.69 -> 29.03Improved
train the background encoder instead of frozen weights (ablation)UFO Search · CAIS (all retrievals)mAP (%): 11.54 -> 29.03Improved
add discriminator-filtered training triplets (ablation)UFO Search · MS-COCO user study (P@5)Precision@5 (%): 38.50 -> 41.83Improved
add discriminator-filtered training triplets (ablation)UFO Search · MS-COCO user study (P@25)Precision@25 (%): 35.57 -> 38.83Improved
use triplet loss instead of regression (ablation)No Discriminator · MS-COCO user study (P@25)Precision@25 (%): 30.40 -> 35.57Improved
use UFO Search instead of the best constrained-search baseline (ablation)UFO Search vs CFO-C · CAIS (top-100 retrievals), dogmAP (%): 57.82 -> 36.51Hurt

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