AI Paper Atlas

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

Prototypes-oriented Transductive Few-shot Learning with Conditional Transport

Long Tian, Jingyi Feng, Xiaoqiang Chai, Wenchao Chen, Liming Wang, Xiyang Liu, Bo Chen

ICCV 2023 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Fine-tuning strategies for few-shot · 26 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 PUTM with PT-MAP uniform-prior transport under class imbalancetransductive few-shot · miniImageNet 1-shot imbalanced (WRN)accuracy (%): 70.9 -> 60.6Hurt
use PUTM with conditional transport instead of PT-MAP under class balancetransductive few-shot · miniImageNet 1-shot balanced (WRN)accuracy (%): 78.9 vs 78.4No clear effect
use PUTM instead of BAVAR in class-imbalanced 1-shottransductive few-shot · miniImageNet 1-shot imbalanced (WRN)accuracy (%): 74.1 -> 70.9Hurt
self-supervised WRN features instead of standard WRNPUTM · miniImageNet 1-shot imbalancedaccuracy (%): 70.9 -> 73.8Improved
calibrate prototypes with backward transport instead of forward transport (ablation)PUTM · miniImageNet 5-way 1-shot imbalancedaccuracy (%)Hurt
use PUTM instead of alpha-TIM for inference timetransductive few-shot · CUB 5-way 1-shot (RN18)end-to-end time (s): 5.6 -> 2.9Improved

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