AI Paper Atlas

Research map / Detection and segmentation / Weakly supervised detection and segmentation

Inter-Image Communication for Weakly Supervised Localization

Xiaolin Zhang, Yunchao Wei, Yi Yang

ECCV 2020 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Weakly supervised object localization · 113 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 Stochastic Consistency (SC) loss (ablation)InceptionV3 plain · ILSVRC valGt-known localization error: 37.32 -> 31.63Improved
add SC loss (ablation)InceptionV3 plain · ILSVRC valTop-1 localization error: 53.71 -> 49.07Improved
add Global Consistency (GC) loss on top of SC (ablation)InceptionV3 + SC · ILSVRC valGt-known localization error: 31.63 -> 31.04Improved
add GC loss on top of SC (ablation)InceptionV3 + SC · ILSVRC valTop-1 localization error: 49.07 -> 48.08Improved
update class centers with momentum rule instead of back-propagation (ablation)GC memory · ILSVRC vallocalization / Gt-known error: 49.03 -> 48.08; 32.09 -> 31.04Improved
enlarge input resolution from 224x224 to 320x320 (ablation)I2C · ILSVRC valGt-known localization error: 31.50 -> 31.04Improved
enlarge input resolution from 224x224 to 320x320 (ablation)I2C · CUB testGt-known localization error: 27.40 -> 22.99Improved
vary lambda1 over 40x range from 0.002 to 0.08 (ablation)SC only · ILSVRC vallocalization error: 49.07 vs 50.82 (best vs worst)No clear effect
vary lambda2 from 0.0001 to 0.1 (ablation)SC + GC · ILSVRC vallocalization error: fluctuates within 0.96%No clear effect
increase number of seeds K from 3 up to 100 (ablation)SC · ILSVRC vallocalization error: fluctuates within 0.46%; lowest at K=3; classification error lowest 28.40% at K=60Hurt
increase lambda1 (SC weight) (ablation)SC only · ILSVRC valclassification vs Gt-known error: best 29.24 / 49.07 / 31.63; worst 32.13 / 50.82 / 34.44Mixed
use I2C with ResNet50 instead of ADL (ResNet50-SE)I2C · ILSVRC valTop-1 localization error: 51.47 -> 45.17Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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