SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2203.16517 · CVPR · 2022

Unseen Classes at a Later Time? No Problem

Vineeth Balasubramanian, Hari Chandana Kuchibhotla, Shivam Chandhok, Sumitra Malagi

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Recent progress towards learning from limited supervision has encouraged efforts towards designing models that can recognize novel classes at test time (generalized zeroshot learning or GZSL). GZSL approaches assume knowledge of all classes, with or without labeled data, beforehand. However, practical scenarios demand models that are adaptable and can handle dynamic addition of new seen and unseen classes on the fly (i.e continual generalized zero-shot learning or CGZSL). One solution is to sequentially retrain and reuse conventional GZSL methods, however, such an approach suffers from catastrophic forgetting leading to suboptimal generalization performance. A few recent efforts towards tackling CGZSL have been limited by difference in settings, practicality, data splits and protocols followed -inhibiting fair comparison and a clear direction forward. Motivated from these observations, in this work, we firstly consolidate the different CGZSL setting variants and propose a new Online-CGZSL setting which is more practical and flexible. Secondly, we introduce a unified feature-generative framework for CGZSL that leverages bi-directional incremental alignment to dynamically adapt to addition of new classes, with or without labeled data, that arrive over time in any of these CGZSL settings. Our comprehensive experiments and analysis on five benchmark datasets and comparison with baselines show that our approach consistently outperforms existing methods, especially on the more practical Online setting.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2203.16517")
get_code_for_paper("2203.16517")
have("2203.16517")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2203.16517.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2203.16517.svg)](https://syntology.ai/paper/2203.16517)

Connect an agent — have() is free.