AI Paper Atlas

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

Field-Guide-Inspired Zero-Shot Learning

Utkarsh Mall, Bharath Hariharan, Kavita Bala

ICCV 2021 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Generative feature synthesis for zero-shot · 12 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
replace expert-annotated similar class with a random class (ablation)ZSL-Interactive · CUBaccuracy: <20%Hurt
use Sibling-variance instead of random attribute acquisition (ablation)ZSL-Interactive · CUBaccuracyImproved
use Sibling-variance instead of Representation-change (ablation)ZSL-Interactive · CUBaccuracyImproved
use Representation-change instead of Sibling-variance in later stages (ablation)ZSL-Interactive · AWA2accuracyMixed
use taxonomy siblings to compute variance instead of variance over all classes (ablation)Sibling-variance · CUBaccuracyImproved
let learner pick attributes instead of expert picking 10 attributes (ablation)ZSL-Interactive · CUB (20 novel classes)accuracyImproved
add one image of the novel class (Image-based query) (ablation)ZSL-Interactive · AWA2accuracyImproved
add one image of the novel class (Image-based query) (ablation)ZSL-Interactive · CUB, SUNaccuracyNo clear effect
use sibling of expert class as the similar class (ablation)Sibling-variance · CUBaccuracyHurt
use random similar class instead of sibling (ablation)Sibling-variance · CUBaccuracyHurt
add 10% noise to novel attributes (partial, 5 per class)ZSL-Interactive · partial attributesaccuracy: ~1% drop vs ~5% for traditional ZSLHurt
use interactive field-guide annotation instead of reduced random vocabulary (ablation)ZSL-Interactive · CUB, SUNaccuracyImproved

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