AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

Do Semantic Parts Emerge in Convolutional Neural Networks?

Abel González-García, Davide Modolo, Vittorio Ferrari

IJCV 2017 · Detection and segmentation › Open-set and few-shot detection · approach: Object-level representation learning · 96 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 bounding-box regression to filter stimulus detections (ablation)best single filter, AlexNet-Object layer 5 · PASCAL-Part trainpart detection mAP: 6.1 -> 19.0Improved
add GA filter combination instead of the single best filter (ablation)AlexNet-Object layer 5 · PASCAL-Part trainpart detection mAP: +5.2 mAP (19.0 -> 24.2)Improved
add GA filter combination in layer 1 (ablation)AlexNet-Object layer 1 · PASCAL-Part trainpart detection mAP: +0.6 mAP onlyNo clear effect
select filters with GA instead of TopFilters (ablation)AlexNet-Object layer 5 · PASCAL-Part trainpart detection mAP: 18.8 -> 24.2Improved
use all filters simultaneously instead of GA combination (ablation)AlexNet-Object layer 5 · PASCAL-Part trainpart detection mAP: 24.2 -> 9.2Hurt
train for scene recognition (Places) instead of object detectionAlexNet · PASCAL-Part trainpart detection mAP: -6.1% mAP compared to AlexNet-Object (24.2 -> 18.1)Hurt
add ILSVRC12 pre-training before object detection training (ablation)AlexNet-Object · PASCAL-Part train layer 5part detection mAP: 18.2 -> 24.2Improved
fine-tune for object detection on VOC12 instead of image classification onlyAlexNet · PASCAL-Part train layer 5part detection mAP: 23.2 -> 24.2Improved
use deeper VGG16 instead of AlexNetobject detection finetuned network · PASCAL-Part train layer 5part detection mAP: 24.2 -> 26.1Improved
fine-tune VGG16 for detection instead of classification onlyVGG16 · PASCAL-Part train layer 5_3part detection mAP: 22.1 -> 26.1Improved
use higher network layerAlexNet-Object GA · PASCAL-Part trainpart detection mAP: 9.6 -> 14.4 -> 19.1 -> 21.1 -> 24.2Improved
larger average part sizeAlexNet-Object layer 5 GA · PASCAL-Part trainpart AP correlation: Pearson correlation 0.7Improved

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