AI Paper Atlas

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

Joint Intermodal and Intramodal Label Transfers for Extremely Rare or Unseen Classes

Guo-Jun Qi, Wei Liu, Charų C. Aggarwal, Thomas S. Huang

TPAMI 2016 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Fine-grained and cross-domain few-shot baselines · 58 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
share the label transfer matrix across seen and unseen classes (ablation)I2LT · CUB200 zero-shotaverage AUC: 0.64 -> 0.67Improved
share the label transfer matrix across seen and unseen classes (ablation)I2LT · Flowers102 zero-shotaverage AUC: 0.70 -> 0.73Improved
replace BOVW features with CNN featuresI2LT · NUS-WIDE I2I searchPrecision@20: 56.34 -> 68.72Improved
replace BOVW features with CNN featuresI2LT · NUS-WIDE T2I searchPrecision@20: 56.85 -> 69.20Improved
add joint intermodal and intramodal transfer (I2LT) over TTITTI · NUS-WIDE (81 concepts)MAP: 0.3418 -> 0.4042Improved
increase the number of training images from two to tenI2LT · Flickr-Wiki birdserror rate: 0.2523 -> 0.2314Improved
increase number of training images to a large levellabel transfer vs baselines · Flickr-Wikierror rateHurt
increase number of text-image co-occurrence pairsI2LT · Flickr-Wikierror rateImproved
use I2LT over SVM with two training imagesSVM · Flickr-Wiki birds (2 images)error rate: 0.3293 -> 0.2523Improved
add the trace norm regularizer for concise transfer modelI2LT · zero-shot CUB200 and Flowers102average AUCImproved

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