AI Paper Atlas

Research map / Detection and segmentation / CNN features

Delving Into Salient Object Subitizing and Detection

Shengfeng He, Jianbo Jiao, Xiaodan Zhang, Guoqiang Han, Rynson W.H. Lau

ICCV 2017 · Detection and segmentation › CNN features · approach: RGB salient object detection · 56 citations (OpenAlex)

Read the paper

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 subitizing-driven adaptive weight layer versus independent detection networksalient object detection network · Pascal-SF-measure: 0.721 -> 0.794Improved
add subitizing-driven adaptive weight layer versus independent detection networksalient object detection network · Pascal-SMAE: 0.143 -> 0.114Improved
adaptive weight layer versus shared multi-task networkmulti-task saliency network · Pascal-SF-measure: 0.770 -> 0.794Improved
adaptive weight layer versus concatenated networkmulti-task saliency network · Pascal-SMAE: 0.125 -> 0.114Improved
adaptive weight layer versus cascaded networkmulti-task saliency network · Pascal-SF-measure: 0.753 -> 0.794Improved
share Conv5 only between subitizing and detection (ablation)shared network · MSOdetection MAE (difference vs independent) and subitizing mAP: -0.53 MAE; +4.17 mAPImproved
share Conv3-5 between subitizing and detection (ablation)shared network · MSOdetection MAE (difference) and subitizing mAP: +0.42 MAE; -3.56 mAPMixed
share Conv1-5 (all layers) between subitizing and detection (ablation)shared network · MSOdetection MAE (difference) and subitizing mAP: -0.43 MAE; -0.62 mAPMixed
vary number of shared layers (ablation)shared network · MSOdetection and subitizingMixed
add subitizing guidance to unconstrained detection versus MAPadaptive weight network · MSO (full)adaptive precision: 0.370 -> 0.654Improved
add subitizing guidance on background-only images versus MAPadaptive weight network · MSO (background images only)MAE: 0.068 -> 0.061Improved
swap tasks so that detection guides subitizing, versus MSO baselineadaptive weight network · Subitizing, 4+ objectsaverage precision (%): 79.0% -> 84.1%Improved

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