AI Paper Atlas

Research map / Detection and segmentation / CNN features

Scale Normalized Image Pyramids with AutoFocus for Object Detection

Bharat Singh, Mahyar Najibi, Abhishek Sharma, Larry Steven Davis

TPAMI 2021 · Detection and segmentation › CNN features · approach: Region-based and query-based detectors · 24 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
use SNIP scale normalization instead of multi-scale train/testR-FCN ResNet-50 · COCOAP: 35.6 -> 37.8Improved
train on multi-scale without scale normalization (MST) instead of multi-scale test only (ablation)R-FCN ResNet-50 · COCOAP: 35.9 -> 35.6Hurt
restrict training to objects <80px at 1400 resolution (ablation)R-FCN · COCO small objectsmAP: 19.6 -> 16.4Hurt
train at 1400x2000 instead of 800x1400 resolutionR-FCN · COCO small objectsmAP: 19.6 -> 19.9No clear effect
add SNIP to RPN training (ablation)RPN ResNet-50 · COCOAR: 61.3 -> 64.0Improved
add SNIP to RPN and RCN (ablation)D-R-FCN DPN-98 · COCOAP: 41.2 -> 44.7Improved
add SNIP to RPN and RCN (ablation)Faster-RCNN ResNet-101 · COCOAP: 42.6 -> 44.4Improved
add negative chip mining (ablation)SNIPER · COCOAP: 43.4 -> 46.1Improved
add negative chip sampling (ablation)SNIPER RPN · COCOAR: 65.4 -> 65.4No clear effect
add third (highest resolution) scale (ablation)SNIPER · COCOAP: 43.3 -> 46.1Improved
use SNIPER chips instead of full image pyramid (no batch norm)SNIP · COCOAP: 43.6 -> 43.5No clear effect
use SNIPER with image pyramids instead of SSDMobileNet-v2 · COCOAP: 22.1 -> 34.5Improved

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