AI Paper Atlas

Research map / Detection and segmentation / CNN features

Mining Mid-level Visual Patterns with Deep CNN Activations

Yao Li, Lingqiao Liu, Chunhua Shen, Anton van den Hengel

IJCV 2016 · Detection and segmentation › CNN features · approach: Local features and context in CNNs · 55 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
encode with Bag-of-Elements instead of Bag-of-Patterns (ablation)MDPM · Pascal VOC 2007mAPImproved
add merging of mid-level elements before encoding (BoE-M vs BoE-S) (ablation)MDPM BoE · Pascal VOC 2007mAPImproved
add pattern merging instead of pattern selection only (ablation)MDPM BoE (VGG-VD, 50 elements) · Pascal VOC 2007mAP (%): 86.2 -> 87.3Improved
use more mid-level elements (10 to 50) (ablation)MDPM BoE · Pascal VOC 2007mAPImproved
increase transaction length from 10 to 20 (ablation)MDPM BoE (VGG-VD) · Pascal VOC 2007mAP (%): 85.4 -> 87.3Improved
increase transaction length from 20 to 30 (ablation)MDPM BoE (VGG-VD) · Pascal VOC 2007mAP (%): 87.3 -> 87.6No clear effect
raise merging threshold Th from 50 to 150 (ablation)MDPM BoE (VGG-VD) · Pascal VOC 2007mAP (%): 86.4 -> 87.3Improved
raise merging threshold Th from 150 to 200 (ablation)MDPM BoE (VGG-VD) · Pascal VOC 2007mAP (%): 87.3 -> 87.0No clear effect
use BoE with VGG-VD instead of global FC featureMDPM · Pascal VOC 2007mAP (%): 79.6 -> 87.3Improved
use BoE with VGG-VD instead of global FC featureMDPM · MIT Indooraccuracy (%): 68.87 -> 77.63Improved
replace pre-trained VGG-VD with fine-tuned VGG-VD for miningMDPM · MIT Indooraccuracy (%): 77.63 -> 71.82Hurt
replace LDA-Retrained detectors with pattern miningMDPM · MIT Indooraccuracy (%): 62.30 -> 69.69Improved

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