AI Paper Atlas

Research map / Detection and segmentation / CNN features

Towards Real-World Prohibited Item Detection: A Large-Scale X-Ray Benchmark

Boying Wang, Libo Zhang, Longyin Wen, Xianglong Liu, Yanjun Wu

ICCV 2021 · Detection and segmentation › CNN features · approach: Forgery detection · 139 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 selective channel-wise attention (ablation)Cascade Mask R-CNN · PIDray hidden testdetection AP: 48.0 -> 48.3Improved
add selective channel-wise attention (ablation)Cascade Mask R-CNN · PIDray hidden testsegmentation AP: 36.1 -> 36.5Improved
add selective spatial attention to SCA (ablation)SDANet · PIDray hidden testdetection AP: 48.3 -> 48.9Improved
add dependency refinement module (ablation)SDANet (SCA+SSA) · PIDray hidden testdetection AP: 48.9 -> 49.5Improved
add dependency refinement module (ablation)SDANet (SCA+SSA) · PIDray hidden testsegmentation AP: 36.7 -> 37.4Improved
use SE instead of DR (ablation)SDANet w/o DR · PIDray hidden testdetection AP: 48.9 -> 49.1No clear effect
use CBAM instead of DR (ablation)SDANet w/o DR · PIDray hidden testdetection AP: 48.9 -> 47.0Hurt
replace FPN with BiFPN (ablation)Cascade Mask R-CNN · PIDray overalldetection AP: 61.0 -> 58.7Hurt
replace FPN with PAFPN (ablation)Cascade Mask R-CNN · PIDray overalldetection AP: 61.0 -> 60.2Hurt
replace FPN with selective dense attention (SDANet)Cascade Mask R-CNN · PIDray hidden testdetection AP: 48.0 -> 49.5Improved
replace FPN with selective dense attention (SDANet)Cascade Mask R-CNN · PIDray easy testdetection AP: 70.9 -> 71.2Improved
replace FPN with selective dense attention (SDANet)Cascade Mask R-CNN · MS COCOAP: 42.9 -> 43.5Improved

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