AI Paper Atlas

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

DeepKSPD: Learning Kernel-matrix-based SPD Representation for Fine-grained Image Recognition

Melih Engin, Lei Wang, Luping Zhou, Xinwang Liu

ECCV 2018 · Label-efficient and robust learning › Recognition and long-tail · approach: Correspondence and causal representation learning · 68 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 covariance matrix with kernel matrix in SPD representation (KSPD-VGG vs COV-VGG) (ablation)VGG-19 features + SVM · Average over 4 datasetsaccuracy (%): 77.98 -> 80.1Improved
replace covariance matrix with kernel matrix in end-to-end network (DeepKSPD vs DeepCOV) (ablation)end-to-end VGG-19 · Average over 4 datasetsaccuracy (%): 81.35 -> 85.13Improved
add end-to-end learning of descriptors and kernel representation (DeepKSPD vs KSPD-VGG) (ablation)KSPD · Carsaccuracy (%): 83.5 -> 90.1Improved
add end-to-end learning (DeepKSPD vs KSPD-VGG) (ablation)KSPD · MIT Indooraccuracy (%): 77.2 -> 79.6Improved
add end-to-end learning (DeepKSPD vs KSPD-VGG) (ablation)KSPD · Aircraftaccuracy (%): 83.8 -> 86.3Improved
add end-to-end learning (DeepKSPD vs KSPD-VGG) (ablation)KSPD · Birdsaccuracy (%): 78.5 -> 84.5Improved
use SPD representation instead of Fisher vector on VGG-19 features (KSPD-VGG vs FV-VGG)VGG-19 features · Average over 4 datasetsaccuracy (%): 73.1 -> 80.1Improved
use matrix logarithm of covariance (DeepCOV) instead of sign square-root (B-CNN)end-to-end covariance network · Average over 4 datasetsaccuracy (%): 82.5 -> 81.35Hurt
DeepKSPD vs B-CNNend-to-end VGG-19 · Carsaccuracy (%): 87.5 -> 90.1Improved
DeepKSPD vs fine-tuned FV-VGGVGG-19 · Aircraftaccuracy (%): 78.7 -> 86.3Improved
DeepKSPD vs fine-tuned FV-VGGVGG-19 · Birdsaccuracy (%): 74.7 -> 84.5Improved
DeepKSPD vs fine-tuned FV-VGGVGG-19 · Carsaccuracy (%): 85.7 -> 90.1Improved

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