AI Paper Atlas

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

Adaptive Margin Diversity Regularizer for handling Data Imbalance in Zero-Shot SBIR

Titir Dutta, Anurag Singh, Soma Biswas

ECCV 2020 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Transductive and semantic-dictionary zero-shot · 22 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 AMDRegSEM-PCYC · TU-Berlin Ext. ZS-SBIRMAP@all: 0.297 -> 0.330Improved
add AMDRegSEM-PCYC · Sketchy Ext. ZS-SBIRMAP@all: 0.349 -> 0.397Improved
add AMDRegStyle-guide · TU-Berlin Ext. ZS-SBIRMAP@all: 0.254 -> 0.291Improved
add AMDRegStyle-guide · Sketchy Ext. ZS-SBIRMAP@all: 0.375 -> 0.410Improved
add AMDRegSAKE · TU-Berlin Ext. ZS-SBIRMAP@all: 0.428 -> 0.447Improved
add AMDRegSAKE · Sketchy Ext. ZS-SBIRMAP@all: 0.547 -> 0.551No clear effect
add AMDRegSEM-PCYC · TU-Berlin Ext. generalized ZS-SBIRMAP@all: 0.192 -> 0.245Improved
add AMDRegSEM-PCYC · Sketchy Ext. generalized ZS-SBIRMAP@all: 0.307 -> 0.320Improved
introduce step imbalance p=100 into training dataBaseline Model [7] · mini-Sketchy ZS-SBIRMAP@200: 0.395 -> 0.156Hurt
add AMDReg to baseline under step imbalance p=100Baseline Model [7] · mini-Sketchy ZS-SBIRMAP@200: 0.156 -> 0.218Improved
add adaptive imbalance margin to the diversity regularizer (AMDReg vs Diversity-Regularizer) (ablation)Baseline Model [7] · mini-Sketchy ZS-SBIR long-tailed p=10MAP@200: 0.296 -> 0.332Improved
use AMDReg instead of LDAM-CE loss (ablation)Baseline Model [7] · mini-Sketchy ZS-SBIR long-tailed p=100MAP@200: 0.234 -> 0.240No clear effect

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