AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Pairwise Confusion for Fine-Grained Visual Classification

Abhimanyu Dubey, Otkrist Gupta, Pei Guo, Ramesh Raskar, Ryan Farrell, Nikhil Naik

ECCV 2018 · Label-efficient and robust learning › Recognition and long-tail · approach: Correspondence and causal representation learning · 244 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 Pairwise ConfusionDenseNet-161 · CUB-200-2011top-1 accuracy: 84.21 -> 86.87Improved
add Pairwise ConfusionResNet-50 · NABirdstop-1 accuracy: 63.55 -> 68.15Improved
add Pairwise ConfusionBilinear CNN · six FGVC datasetstop-1 accuracy: average improvement of 1.7%Improved
add Pairwise ConfusionGoogLeNet · ImageNet-Dogs (from scratch)top-1 accuracy: 62.35 -> 64.17Improved
add Pairwise ConfusionGoogLeNet · ImageNet-Random (from scratch)top-1 accuracy: 71.85 -> 72.09Improved
add Pairwise ConfusionResNet-50 · CIFAR-10 (from scratch)top-1 accuracy: 93.17 -> 93.46Improved
add Pairwise ConfusionDenseNet-161 · CIFAR-10 (from scratch)top-1 accuracy: 95.15 -> 95.08No clear effect
add Pairwise ConfusionGoogLeNet · CIFAR-100 (from scratch)top-1 accuracy: 73.35 -> 76.02Improved
add Pairwise ConfusionResNet-50 · ImageNet-1K full (from scratch)top-1 accuracy: 76.15 -> 76.28No clear effect
add Pairwise ConfusionGoogLeNet · CUB-200-2011 Grad-CAM localizationmean IoU: 0.29 -> 0.35Improved
add Pairwise ConfusionVGG-16 · CUB-200-2011 Grad-CAM localizationmean IoU: 0.31 -> 0.34Improved
replace Label Smoothing Regularization with Pairwise Confusion (ablation)ResNet-50 · CUB-200-2011top-1 accuracy: 78.20 -> 80.21Improved

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