AI Paper Atlas

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

Exchangeable Deep Neural Networks for Set-to-Set Matching and Learning

Yuki Saito, Takuma Nakamura, Hirotaka Hachiya, Kenji Fukumizu

ECCV 2020 · 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
use K-pair-set loss instead of triplet loss (ablation)Cross Affinity · Market-1501 Group averageaccuracy (%): 45.5 -> 87.0Improved
add cross-set feature transformation (CSeFT) (ablation)Cross Affinity · Market-1501 Group averageaccuracy (%): 82.8 -> 87.0Improved
use two CSeFT layers instead of one (ablation)Cross Affinity · Market-1501 Group averageaccuracy (%): 86.0 -> 87.0Improved
use eight heads instead of one (ablation)Cross Affinity · Market-1501 Group averageaccuracy (%): 85.9 -> 87.0Improved
add encoder (self-attention block) (ablation)Cross Affinity · Market-1501 Group averageaccuracy (%): 85.7 -> 87.0Improved
use multiple cross-similarity functions instead of single CS (ablation)Cross Affinity · Market-1501 Group averageaccuracy (%): 86.0 -> 87.0Improved
add ReLU in cross-similarity (ablation)Cross Affinity · Market-1501 Group averageaccuracy (%): 85.0 -> 87.0Improved
use mCS instead of max pooling (ablation)Cross Affinity · Market-1501 Group averageaccuracy (%): 86.1 -> 87.0Improved
use mCS instead of cosine similarity metric (ablation)Cross Affinity · Market-1501 Group averageaccuracy (%): 53.1 -> 87.0Improved
add set-aug data augmentation (ablation)Cross Affinity · Road Group CMC-1CMC-1 (%): 45.2 -> 84.0Improved
add image augmentation (img-aug) (ablation)Cross Affinity · Road Group CMC-1CMC-1 (%): 45.2 -> 47.7No clear effect
add img-aug on top of set-aug (ablation)Cross Affinity · Road Group CMC-1CMC-1 (%): 84.0 -> 81.7Hurt

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