AI Paper Atlas

Research map / Detection and segmentation / CNN features

Rapid Salient Object Detection With Difference Convolutional Neural Networks

Zhuo Su, Li Liu, Matthias Müller, Jiehua Zhang, Diana Wofk, Ming‐Ming Cheng, Matti Pietikäinen

TPAMI 2025 · Detection and segmentation › CNN features · approach: Region-based and query-based detectors · 23 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 STDM temporal module (sc+cd+ad) (ablation)STDNet-A · VSOD DAVSODS-measure: .705 -> .755Improved
use CSTDC instead of standard convolution in STDM (ablation)STDNet-A · VSOD DAVSODS-measure: .724 -> .739Improved
use ASTDC instead of standard convolution in STDM (ablation)STDNet-A · VSOD DAVSODS-measure: .724 -> .747Improved
increase frames from 2 to 8 (ablation)STDNet-A · VSOD DAVSODS-measure: .721 -> .755Improved
increase frames from 4 to 8 (ablation)STDNet-A · VSOD DAVSODS-measure: .751 -> .755No clear effect
use replicate padding instead of zero padding (ablation)STDNet-A · VSOD DAVSODS-measure: .731 -> .755Improved
use STDM instead of temporal attention (ablation)STDNet-A · VSOD DAVSODS-measure: .732 -> .755Improved
swap in EfficientNet-B5 backboneSTDNet-A · VSOD DAVSODS-measure: .755 -> .768Improved
use SDNet difference convolutions instead of standard baseline (scale x0.75) (ablation)SDNet · ISOD ECSSD (scale x0.75)F-measure: .887 -> .897Improved
use SDNet instead of PiDiNet difference convolution (scale x1.0, 240 input) (ablation)SDNet · ISOD ECSSDF-measure: .877 -> .890Improved
use SDNet instead of baseline at scale x1.0, 320 input (ablation)SDNet · ISOD ECSSDF-measure: .904 -> .903No clear effect
use pre-trained ImageNet backbone with SDNet-ASDNet-A · ISOD ECSSDS-measure: .893 -> .908Improved

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