AI Paper Atlas

Research map / Detection and segmentation / CNN features

Learn to Predict Sets Using Feed-Forward Neural Networks

Hamid Rezatofighi, Tianyu Zhu, Roman Kaskman, Farbod Motlagh, Javen Qinfeng Shi, Anton Milan, Daniel Cremers, Laura Leal-Taixé, Ian D. Reid

TPAMI 2021 · Detection and segmentation › CNN features · approach: Region-based and query-based detectors · 18 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 classifier jointly with cardinality on a shared backbone (JDS) (ablation)Set-DS (BCE-SftMx) · PASCAL VOC 2007 multi-label classificationC-F1: 76.2 -> 82.2Improved
train classifier jointly with cardinality on a shared backbone (JDS) (ablation)Set-DS (BCE-SftMx) · PASCAL VOC 2007 multi-label classificationI-F1: 83.0 -> 92.5Improved
train classifier jointly with cardinality on a shared backbone (JDS) (ablation)Set-DS (BCE-Sftmx) · MS COCO multi-label classificationO-F1: 69.6 -> 70.7Improved
train classifier jointly with cardinality on a shared backbone (JDS) (ablation)Set-DS (BCE-Sftmx) · MS COCO multi-label classificationI-F1: 74.6 -> 75.6Improved
replace negative binomial cardinality loss with softmax categorical loss (ablation)Set-DS (BCE) · PASCAL VOC 2007 multi-label classificationC-F1: 75.8 -> 76.2Improved
replace negative binomial cardinality loss with softmax categorical loss (ablation)Set-DS (BCE) · MS COCO multi-label classificationC-F1: 64.6 -> 64.7No clear effect
learn cardinality jointly with the classifier (ablation)Set network · PASCAL VOC 2007 multi-label classificationmean absolute cardinality error: 0.33 ± 0.53 -> 0.31 ± 0.54No clear effect
use set formulation instead of Faster R-CNN with the same ResNet101 and L1 lossFaster R-CNN · Cropped MOTChallenge pedestrian detectionmAP: 0.68 -> 0.85Improved
use set formulation instead of sequential LSTM-Hungarian detectorLSTM-Hungarian · Cropped MOTChallenge pedestrian detectionmAP: 0.61 -> 0.85Improved
add GIoU to the L1 bounding box loss (ablation)Set (Ours) ResNet101 · Cropped MOTChallenge pedestrian detectionMR: 0.25 -> 0.24No clear effect
add predicted cardinality at inference to DETR-style set detector (ablation)DETR · Cropped MOTChallenge pedestrian detectionF1: 0.86 -> 0.87No clear effect
add predicted cardinality at inference to DETR-style set detector (ablation)DETR · PASCAL VOC 2007 detectionF1: 0.71 -> 0.72Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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