AI Paper Atlas

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

Higher-Order Integration of Hierarchical Convolutional Activations for Fine-Grained Visual Categorization

Sijia Cai, Wangmeng Zuo, Lei Zhang

ICCV 2017 · Label-efficient and robust learning › Recognition and long-tail · approach: Correspondence and causal representation learning · 207 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 degree-2 polynomial kernel instead of linear kernel (ablation)relu5_3 predictor · CUB (fine-tuned)accuracy (%): 79.2 -> 83.7Improved
raise polynomial degree from 2 to 6 (ablation)relu5_3 predictor · CUB (fine-tuned)accuracy (%): 83.7 -> 79.5Hurt
raise polynomial degree from 2 to 3 (ablation)relu5_3 predictor · CUB (fine-tuned)accuracy (%): 83.7 -> 83.3Hurt
add fine-tuning (ablation)degree-2 relu5_3 predictor · CUBaccuracy (%): 78.3 -> 83.7Improved
add relu5_2 activations (ablation)degree-2 relu5_3 predictor · CUB (fine-tuned)accuracy (%): 83.7 -> 85.3Improved
add relu5_1 activations to relu5_3 (ablation)degree-2 relu5_3 predictor · CUB (fine-tuned)accuracy (%): 83.7 -> 83.6No clear effect
add relu5_1 to relu5_3+relu5_2 (ablation)degree-2 two-layer integration · CUB (fine-tuned)accuracy (%): 85.3 -> 85.1No clear effect
use degree-2 kernel instead of degree-1 in two-layer integration (ablation)relu5_3+relu5_2 · CUB (fine-tuned)accuracy (%): 80.4 -> 85.3Improved
increase number of 1x1 filters Dr from 8,192 to 32,768 (ablation)polynomial module · CUBaccuracy (%)No clear effect
replace hypercolumn-style concatenation with max pooling by degree-2 integration (ablation)three-layer integration · CUBaccuracy (%): 80.9 -> 85.1Improved
replace HED-style prediction fusion with degree-2 integration (ablation)three-layer integration · CUBaccuracy (%): 82.3 -> 85.1Improved
raise polynomial degree from 2 to 6 (ablation)polynomial module · CUB testing speedFPS: 29.8 -> 10.4Hurt

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