AI Paper Atlas

Research map / Detection and segmentation / CNN features

SSD: Single Shot MultiBox Detector

Wei Liu, Dragomir Anguelov, Dumitru Erhan, Christian Szegedy, Scott Reed, Cheng-Yang Fu, Alexander C. Berg

ECCV 2016 · Detection and segmentation › CNN features · approach: Region-based and query-based detectors · 31,619 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 the extensive data augmentation sampling strategy (ablation)SSD300 · PASCAL VOC2007 testmAP: +8.8% mAPImproved
add default boxes with 1/3 and 3 aspect ratios (ablation)SSD300 · PASCAL VOC2007 testmAP: -0.6%Improved
add default boxes with 1/2 and 2 aspect ratios (ablation)SSD300 · PASCAL VOC2007 testmAP: -2.1%Improved
use atrous subsampled VGG16 instead of full VGG16 (ablation)SSD300 · PASCAL VOC2007 testmAP and speed: 74.2 vs 74.3No clear effect
add prediction from multiple feature layers instead of only conv7 (ablation)SSD300 · PASCAL VOC2007 testmAP: 62.4 -> 74.3Improved
add conv11_2 as a prediction layer (ablation)SSD300 · PASCAL VOC2007 testmAP: 74.6 -> 74.3No clear effect
keep boxes on the image boundary instead of ignoring them (ablation)SSD300 · PASCAL VOC2007 testmAP: 63.4 -> 74.3Improved
add image expansion (zoom out) augmentation (ablation)SSD300 · PASCAL VOC2007 test (07+12)mAP: 74.3 -> 77.2Improved
add image expansion (zoom out) augmentation (ablation)SSD512 · PASCAL VOC2007 test (07+12)mAP: 76.8 -> 79.8Improved
add image expansion (zoom out) augmentation (ablation)SSD300 · COCO test-dev2015mAP@[0.5:0.95]: 23.2 -> 25.1Improved
increase input size from 300x300 to 512x512 (ablation)SSD · PASCAL VOC2007 test (07+12)mAP: 74.3 -> 76.8Improved
add COCO pretraining before fine-tuning on VOC (ablation)SSD300 · PASCAL VOC2007 testmAP: 74.3 -> 79.6Improved

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