AI Paper Atlas

Research map / Detection and segmentation / CNN features

DSOD: Learning Deeply Supervised Object Detectors From Scratch

Zhiqiang Shen, Zhuang Liu, Jianguo Li, Yu-Gang Jiang, Yurong Chen, Xiangyang Xue

ICCV 2017 · Detection and segmentation › CNN features · approach: Region-based and query-based detectors · 680 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 transition w/o pooling layer (4 dense blocks) (ablation)DSOD300 DS/32-12-16-0.5 · VOC 2007 test (07+12)mAP: 59.9 -> 61.6Improved
use compression factor 1 instead of 0.5 (ablation)DSOD300 backbone · VOC 2007 test (07+12)mAP: 61.6 -> 64.5Improved
widen bottleneck layers (ablation)DSOD300 backbone · VOC 2007 test (07+12)mAP: 64.5 -> 68.6Improved
widen first conv layer (ablation)DSOD300 backbone · VOC 2007 test (07+12)mAP: 68.6 -> 69.7Improved
increase growth rate from 16 to 48 (ablation)DSOD300 backbone · VOC 2007 test (07+12)mAP: 69.7 -> 74.5Improved
add stem block (ablation)DSOD300 DS/64-192-48-1 · VOC 2007 test (07+12)mAP: 74.5 -> 77.3Improved
use dense prediction layers instead of plain (ablation)DSOD300 DS/64-192-48-1 · VOC 2007 test (07+12)mAP: 77.3 -> 77.7Improved
use dense prediction layers instead of plain (ablation)DSOD300 DS/64-192-48-1 · VOC 2007 test (07+12)speed (fps): 20.6 -> 17.4Hurt
use dense prediction layers instead of plain (ablation)SSD300S VGGNet (from scratch) · VOC 2007 test (07+12)mAP: 69.6 -> 70.4Improved
use dense prediction layers instead of plain (ablation)SSD VGG-16 (pretrained) · VOC 2007 test (07+12)mAP: 75.8 -> 76.1Improved
add deep supervision via dense layer-wise connections (DSOD vs SSD from scratch) (ablation)SSD300S VGG16 from scratch · VOC 2007 test (07+12)mAP: 69.6 -> 77.7Improved
train from scratch instead of fine-tuning ImageNet model (ablation)SSD300 VGGNet · VOC 2007 test (07+12)mAP: 75.8 -> 69.6Hurt

Earlier methods this paper compares with

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