AI Paper Atlas

Research map / Detection and segmentation / CNN features

Highly Efficient Salient Object Detection with 100K Parameters

Shang-Hua Gao, Yong-Qiang Tan, Ming-Ming Cheng, Chengze Lu, Yunpeng Chen, Shuicheng Yan

ECCV 2020 · Detection and segmentation › CNN features · approach: Region-based and query-based detectors · 224 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
use 3/1 high/low channel split instead of 1/0 in extractor (ablation)Extractor · ECSSDmax F-measure: 88.2 -> 88.6Improved
shift all channels to low resolution (0/1) instead of 1/0 in extractor (ablation)Extractor · ECSSDmax F-measure: 88.2 -> 86.4Mixed
add cross-stages fusion gOctConvs to the extractor (ablation)CSNet 5/5 · ECSSDmax F-measure: 88.6 -> 90.0Improved
use extreme low-resolution-only split 0/1 with cross-stages fusion (ablation)CSNet · ECSSDmax F-measure: 90.0 -> 88.2Mixed
replace fixed 5/5 split with learnable channels (x2-L)CSNet · ECSSDmax F-measure: 90.0 -> 91.6Improved
replace fixed 5/5 split with learnable channels (x1-L)CSNet · ECSSDmax F-measure: 90.0 -> 90.0No clear effect
add dynamic weight decay to Pruning Filters (ablation)Pruning Filters pruning · ECSSDmax F-measure: 88.7 -> 89.4Improved
add dynamic weight decay to Geometric-Median pruning (ablation)Geometric-Median pruning · ECSSDmax F-measure: 88.7 -> 89.6Improved
add dynamic weight decay to BatchNorm weights during training (ablation)CSNet-L · ECSSDtest MAE / convergenceImproved
increase initial channel width from x1 to x2.0 before pruning (ablation)CSNet-L · ECSSDmax F-measure: 90.0 -> 91.6Improved
prune the width x2.0 model (ablation)CSNet · ECSSDmax F-measure: 91.5 -> 91.6No clear effect
add CSF part to ResNet50 versus PoolNet decoderResNet50 · ECSSDmax F-measure: .940 -> .940No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 4 of 4 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