AI Paper Atlas

Research map / Detection and segmentation / CNN features

Towards Interpretable Object Detection by Unfolding Latent Structures

Tianfu Wu, Xi Song

ICCV 2019 · Detection and segmentation › CNN features · approach: Region-based and query-based detectors · 30 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 top-k sparsity value-network policy instead of baseline weights (ablation)AOG5,5,1 · PASCAL VOC2007 testAP@0.5: 82.1 -> 80.4Hurt
use adversarial-attack value-network policy instead of baseline weights (ablation)AOG5,5,1 · PASCAL VOC2007 testAP@0.5: 82.1 -> 81.4Hurt
use top-k policy instead of baseline weights (ablation)AOG5,5,1 · COCO val2017AP@0.5: 38.2 -> 37.0Hurt
use adversarial policy instead of baseline weights (ablation)AOG5,5,1 · COCO val2017AP@0.5: 38.2 -> 38.0Hurt
use top-k policy instead of baseline weights (ablation)AOG3,3,1 · PASCAL VOC2007 testAP@0.5: 81.9 -> 81.2Hurt
use adversarial policy instead of top-k policy (ablation)AOG5,5,1 · PASCAL VOC2007 testAP@0.5: 80.4 -> 81.4Improved
use adversarial policy instead of baseline weights (ablation)AOG7,7,1 · PASCAL VOC2007 testAP@0.5: 81.7 -> 81.7No clear effect
use grid 5,5,1 AOG instead of 3,3,1 (base policy) (ablation)AOG + base · PASCAL VOC2007 testAP@0.5: 81.9 -> 82.1Improved
use grid 7,7,1 AOG instead of 5,5,1 (base policy) (ablation)AOG + base · PASCAL VOC2007 testAP@0.5: 82.1 -> 81.7Hurt
replace Faster R-CNN with AOG5,5,1 + base interpretable headFaster R-CNN · PASCAL VOC2007 testAP@0.5: 82.1 -> 82.1No clear effect
replace Faster R-CNN with AOG5,5,1 + base interpretable headFaster R-CNN · COCO val2017AP@0.5: 38.5 -> 38.2Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 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