AI Paper Atlas

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

Significance of Softmax-based Features in Comparison to Distance Metric Learning-based Features

Shota Horiguchi, Daiki Ikami, Kiyoharu Aizawa

TPAMI 2019 · Label-efficient and robust learning › Recognition and long-tail · approach: Correspondence and causal representation learning

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 softmax-trained features with PCA and L2 normalization instead of DML (clustering loss)GoogLeNet · CUB test (64-d)Recall@1: 48.2 -> 51.1Improved
use softmax-trained features with PCA and L2 instead of clustering lossGoogLeNet · CAR test (64-d)Recall@1: 58.1 -> 69.4Improved
use softmax-trained features instead of DML on Online ProductsGoogLeNet · OP test (64-d)Recall@1: 67.0 -> 62.4Hurt
add PCA instead of random projection for dimension reduction (ablation)softmax features + L2 · CUB test (64-d)Recall@1: 47.5 -> 51.1Improved
add PCA instead of FC reduction layer (ablation)softmax features + L2 · CUB test (64-d)NMI: 59.1 -> 60.8Improved
add L2 normalization to FCR1 features (ablation)FCR 1 · CUB NMI (1024-d)NMI: 61.1 -> 62.0Improved
add L2 normalization to FCR2 features (ablation)FCR 2 · CAR NMI (1024-d)NMI: 58.7 -> 60.0Improved
use probability invariant shift distance instead of plain Euclidean (ablation)FCR 1 · CUB NMI (1024-d)NMI: 61.1 -> 59.3Hurt
use probability invariant shift distance (ablation)FCR 2 · CAR NMI (512-d)NMI: 61.4 -> 60.7Hurt
use L2 normalization instead of probability invariant shift (ablation)FCR 2 · CAR NMI (256-d)NMI: 61.3 -> 62.5Improved
increase training set size (samples per class) (ablation)softmax features vs DML · CUB and CAR (5% to 100% data)NMI and Recall@KImproved
increase feature dimensionality to 1024 (ablation)FCR2 and lifted struct · CAR NMINMIHurt

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