AI Paper Atlas

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

Semantic Diversity Learning for Zero-Shot Multi-Label Classification

Avi Ben-Cohen, Nadav Zamir, Emanuel Ben-Baruch, Itamar Friedman, Lihi Zelnik-Manor

ICCV 2021 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Generative feature synthesis for zero-shot · 42 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 SDW (semantic diversity weight) to the baseline (ablation)Fast0Tag-style baseline · NUS-WIDE ZSLmAP: 20.6 -> 22.7Improved
add SDW to the full method with M=7 and Reg 0.3 (ablation)Ours · NUS-WIDE ZSLmAP: 25.8 -> 25.9Improved
add SDW to the full method with M=7 and Reg 0.3 (ablation)Ours · NUS-WIDE GZSLmAP: 11.8 -> 12.1Mixed
add SDW to samples with more than 6 labels (ablation)Ours · NUS-WIDE ZSL, diverse imagesF1 (top-10): 42.4 -> 42.9Improved
use multiple principal directions with our loss instead of baseline (ablation)Baseline M=7 · NUS-WIDE ZSL, diverse imagesF1 (top-10): 37.1 -> 42.4Improved
add multiple principal directions naively (M=7, no reg) (ablation)Fast0Tag in our framework · NUS-WIDE ZSLmAP: 21.6 -> 20.6Hurt
add regularization (0.1) with M=2 (ablation)SDW M=2 · NUS-WIDE ZSLmAP: 22.2 -> 23.8Improved
increase principal directions from M=2 to M=7 (ablation)SDW + Reg 0.1 · NUS-WIDE ZSLmAP: 23.8 -> 25.1Improved
increase regularization from 0.1 to 0.3 at M=7 (no SDW) (ablation)Ours · NUS-WIDE ZSLmAP: 25.1 -> 25.8Improved
use ResNet50 instead of VGG19 backbone (ablation)Ours · NUS-WIDE ZSLmAP: 24.2 -> 24.4Improved
use TResNet-M instead of ResNet50 backbone (ablation)Ours · NUS-WIDE ZSLmAP: 24.4 -> 25.9Improved
use our loss instead of Fast0Tag loss with TResNet-M (ablation)TResNet-M · NUS-WIDE ZSLmAP: 21.6 -> 25.9Improved

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