AI Paper Atlas

Research map / Architectures and efficiency / CNN design

Instance-Sensitive Fully Convolutional Networks

Jifeng Dai, Kaiming He, Yi Li, Shaoqing Ren, Jian Sun

ECCV 2016 · Architectures and efficiency › CNN design · approach: Filter design and trained-filter analysis · 433 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 on full-size images instead of 224x224 crops (ablation)InstanceFCN · PASCAL VOC 2012 val (segment proposals)AR@10: 37.4 -> 38.9Improved
train on full-size images instead of 224x224 crops (ablation)InstanceFCN · PASCAL VOC 2012 val (segment proposals)AR@1000: 51.4 -> 52.6Improved
use fully convolutional instance-sensitive maps instead of sliding fc mask regression (both on 224x224 crops) (ablation)InstanceFCN vs ~DeepMask · PASCAL VOC 2012 val (segment proposals)AR@10: 31.2 -> 37.4Improved
use fully convolutional instance-sensitive maps instead of sliding fc mask regression (both on 224x224 crops) (ablation)InstanceFCN vs ~DeepMask · PASCAL VOC 2012 val (segment proposals)AR@1000: 47.0 -> 51.4Improved
increase relative positions from k=3 to k=5 (ablation)InstanceFCN · PASCAL VOC 2012 val (segment proposals)AR@10: 38.3 -> 38.9Improved
increase relative positions from k=3 to k=5 (ablation)InstanceFCN · PASCAL VOC 2012 val (segment proposals)AR@1000: 52.1 -> 52.6Improved
increase relative positions from k=5 to k=7 (ablation)InstanceFCN · PASCAL VOC 2012 val (segment proposals)AR@1000: 52.6 -> 52.7No clear effect
increase relative positions from k=5 to k=7 (ablation)InstanceFCN · PASCAL VOC 2012 val (segment proposals)AR@10: 38.9 -> 38.8No clear effect
replace MNC proposals with InstanceFCN proposals under MNC classifierMNC classifier · PASCAL VOC 2012 val (instance segmentation)mAP@0.7: 41.5 -> 43.0Improved
replace MNC proposals with InstanceFCN proposals under MNC classifierMNC classifier · PASCAL VOC 2012 val (instance segmentation)mAP@0.5: 63.5 -> 61.5Hurt
use InstanceFCN instead of MNC proposalsMNC · PASCAL VOC 2012 val (segment proposals)AR@10: 33.4 -> 38.9Improved
use InstanceFCN instead of MNC proposalsMNC · PASCAL VOC 2012 val (segment proposals)AR@1000: 53.8 -> 52.6Mixed

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