AI Paper Atlas

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

Interpretable Compositional Representations for Robust Few-Shot Generalization

Samarth Mishra, Pengkai Zhu, Venkatesh Saligrama

TPAMI 2022 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Transductive and semantic-dictionary zero-shot · 11 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 pseudo-labeled target images (joint pi) to RPC trainingRPC (source pi) · SVHN->MNIST DAaccuracy: 82.4 -> 95.2Improved
add pseudo-labeled target images (joint pi) to RPC trainingRPC (source pi) · MNIST->USPS DAaccuracy: 94.8 -> 98.8Improved
add pseudo-labeled target images (joint pi) to RPC trainingRPC (source pi) · USPS->MNIST DAaccuracy: 96.1 -> 96.8Improved
use RPC encoding with source-only training instead of a standard DCNSource Only · SVHN->MNIST DAaccuracy: 60.1 -> 82.4Improved
add compactness loss L_com (ablation)RPC · CUB 5-way 1-shotaccuracy: 73.01 -> 75.01Improved
add diversity loss L_div (ablation)RPC · CUB 5-way 1-shotaccuracy: 74.72 -> 75.01Improved
add autoencoder loss L_ae (ablation)RPC · CUB 5-way 1-shotaccuracy: 71.84 -> 75.01Improved
add autoencoder loss L_ae (ablation)RPC · CUB 5-way 5-shotaccuracy: 85.63 -> 89.61Improved
add compactness loss L_com (ablation)RPC · GZSL CUBharmonic mean: 39.6 -> 48.4Improved
add diversity loss L_div (ablation)RPC · GZSL CUBharmonic mean: 43.7 -> 48.4Improved
add autoencoder loss L_ae (ablation)RPC · GZSL CUBharmonic mean: 48.1 -> 48.4No clear effect
add autoencoder loss L_ae (ablation)RPC · SVHN->MNIST DAaccuracy: 94.4 -> 95.2Improved

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