AI Paper Atlas

Research map / Detection and segmentation / 3D detection and driving

Generative Sparse Detection Networks for 3D Single-shot Object Detection

JunYoung Gwak, Christopher Choy, Silvio Savarese

ECCV 2020 · Detection and segmentation › 3D detection and driving · approach: Unified LiDAR 3D detection · 126 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 balanced cross entropy to the sparsity loss (ablation)GSDN with CE losses · ScanNet v2 val (60k iter)mAP@0.25: 33.1 -> 50.7Improved
add balanced cross entropy to the anchor loss (ablation)GSDN with BCE sparsity · ScanNet v2 val (60k iter)mAP@0.25: 50.7 -> 57.2Improved
add balanced cross entropy to the sparsity loss (ablation)GSDN with CE losses · ScanNet v2 val (60k iter)mAP@0.5: 9.26 -> 25.4Improved
add balanced cross entropy to the anchor loss (ablation)GSDN with BCE sparsity · ScanNet v2 val (60k iter)mAP@0.5: 25.4 -> 29.7Improved
deepen encoder from ResNet14 to ResNet34 (ablation)GSDN · ScanNet v2 val (60k iter)mAP@0.25: 52.1 -> 57.2Improved
deepen encoder from ResNet14 to ResNet34 (ablation)GSDN · ScanNet v2 val (60k iter)mAP@0.5: 25.4 -> 29.7Improved
deepen encoder from ResNet18 to ResNet34 (ablation)GSDN · ScanNet v2 val (60k iter)mAP@0.25: 55.1 -> 57.2Improved
use five anchor ratios instead of one (ablation)GSDN · ScanNet v2 val (60k iter)mAP@0.5: 22.7 -> 29.7Improved
use five anchor ratios instead of one (ablation)GSDN · ScanNet v2 val (60k iter)mAP@0.25: 56.3 -> 57.2Improved
use five anchor ratios instead of three (ablation)GSDN · ScanNet v2 val (60k iter)mAP@0.25: 55.3 -> 57.2Improved
lower sparsity pruning confidence tau (ablation)GSDN · ScanNet v2 valmAP@0.25Improved
replace two-stage VoteNet with single-shot GSDNVoteNet · ScanNet v2 valmAP@0.25: 58.6 -> 62.8Improved

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