AI Paper Atlas

Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning

Zero-Shot Attribute Attacks on Fine-Grained Recognition Models

Nasim Shafiee, Ehsan Elhamifar

ECCV 2022 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Generative feature synthesis for zero-shot · 4 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
add regularization loss Lreg to the ranking loss (ablation)CAUP on DAZLE · CUB (l2-norm 6)seen/unseen fooling fraction: 0.24/0.18 -> 0.53/0.40Improved
add utility loss Lutil to the ranking loss (ablation)CAUP on DAZLE · CUB (l2-norm 6)seen/unseen fooling fraction: 0.24/0.18 -> 0.90/0.82Improved
add both Lreg and Lutil to the ranking loss (ablation)CAUP on DAZLE · CUB (l2-norm 6)seen/unseen fooling fraction: 0.24/0.18 -> 0.96/0.89Improved
add both Lreg and Lutil to the ranking loss (ablation)CAUP on DAZLE · AWA2 (l2-norm 6)seen/unseen fooling fraction: 0.05/0.11 -> 0.76/0.73Improved
add both Lreg and Lutil to the ranking loss (ablation)CAUP on DAZLE · SUN (l2-norm 6)seen/unseen fooling fraction: 0.38/0.22 -> 0.75/0.55Improved
add Lutil to the ranking loss (ablation)CAUP on DAZLE · SUN (l2-norm 6)seen/unseen fooling fraction: 0.38/0.22 -> 0.30/0.26Mixed
compose AUPs with class-attribute weights instead of uniform weights (ablation)CAUP on DAZLE · CUB, AWA2, SUNfooling percentage vs l2-normImproved
use compositional attribute-based perturbations instead of single universal perturbation (UAP, GAP)CAUP on DAZLE · CUB (l2-norm 6)seen fooling percentage: 35 -> 96Improved
use compositional attribute-based perturbations instead of UAP, GAPCAUP on DAZLE · AWA2 (l2-norm 6)seen fooling percentage: 11 -> 89Improved
use CAUP instead of UAP on a robust modelCAUP on DCN · AWA2 (l2-norm 6)seen fooling percentage: 02 -> 08Improved
use CAUP instead of UAPCAUP on CNZSL · SUN (l2-norm 6)seen fooling percentage: 29 -> 22Hurt
use CAUP under l-infinity norm 0.06 instead of GAPCAUP · 12 model-dataset-pair casesfooling percentageMixed

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