AI Paper Atlas

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

Hierarchy of Alternating Specialists for Scene Recognition

Hyo Jin Kim, Jan-Michael Frahm

ECCV 2018 · Label-efficient and robust learning › Recognition and long-tail · approach: Correspondence and causal representation learning · 17 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
replace class-based coarse grouping (HD-CNN*) with confusing-cluster specialistsAlexNet* hierarchy · SUN-190Top-1 accuracy (%): 63.65 -> 66.41Improved
add hierarchy levels (Lev 1 to Lev 3) with alternating architecture (ablation)AlexNet* specialists · SUN-190Top-1 accuracy (%): 66.13 -> 66.41Improved
add hierarchy levels (Lev 1 to Lev 3) with alternating architecture (ablation)AlexNet* specialists · Places-205Top-1 accuracy (%): 50.21 -> 51.54Improved
add alternating architecture instead of ordered pooling only (ablation)hierarchy of specialists · SUN-190 Lev 3Top-1 accuracy (%): 64.43 -> 66.41Improved
add alternating architecture instead of orderless pooling only (ablation)hierarchy of specialists · SUN-190 Lev 3Top-1 accuracy (%): 63.08 -> 66.41Improved
add alternating architecture instead of ordered pooling only (ablation)hierarchy of specialists · Places-205 Lev 3Top-1 accuracy (%): 50.28 -> 51.54Improved
add alternating architecture instead of orderless pooling only (ablation)hierarchy of specialists · CIFAR-100 Lev 3Top-1 accuracy (%): 66.62 -> 67.70Improved
use alternating specialists instead of late fusion of both representationsAlexNet* generalist · SUN-190Top-1 accuracy (%): 64.45 -> 66.41Improved
add specialist hierarchy to base NIN-C100NIN-C100 · CIFAR-100Top-1 accuracy (%): 64.73 -> 67.70Improved
add specialist hierarchy to base modelAlexNet* · Places-205Top-1 accuracy (%): 48.67 -> 51.54Improved
increase HD-CNN* number of clusters from 2 to 8 (ablation)HD-CNN* · SUN-190Top-1 accuracy (%): 63.11 -> 63.65 top-1; top-5 88.81 -> 84.08Mixed
increase ensemble size from 2 to 8 models (ablation)simple ensemble · SUN-190Top-1 accuracy (%): 64.19 -> 64.99Improved

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