• Search Research Projects
  • Search Researchers
  • How to Use
  1. Back to project page

2021 Fiscal Year Annual Research Report

Zero-shot recognition of generic objects

Research Project

Project/Area Number 19K24344
Research InstitutionKobe University

Principal Investigator

HASCOET TRISTAN  神戸大学, 経営学研究科, 助教 (60848448)

Project Period (FY) 2019-08-30 – 2022-03-31
KeywordsZero-Shot Learning / Language Models / Visual Representation / Feature Extraction / Semantic representations / CNN / Object recognition / Computer vision
Outline of Annual Research Achievements

In this academic year, efforts have been focused on more core structural questions of Zero-Shot Learning: We focused our search on semantical representations and on re-thinking the methodology behind ZSL benchmarks.
Regarding semantical representations: The past year has seen a strong trend towards leveraging large language models to process visual captions on web-scale image collections, and successfully leverage these representations as a training signal to visual models. This line of work echoes some of our previous works leveraging image captioning dataset in order to achieve zero-shot classification, albeit in much better quantitative results. We have focused our efforts on estimating wether the strong classification abilities brought by these new models from Google and OpenAI are due to the new scale of data used in the training or the representation abilities of large language model.
Regarding the methodology behind ZSL benchmarks. We found two things: On the one hand the dimensioning of standard ZSL benchmark do not allow for the development of combinatorial generalization across classes due to the limited amount of visual classes defined. The methodology of web-scale supervision used in the previously mentioned work does remedy this shortcoming. On the other hand, web-scale supervision provides implicit information about the test classes used to evaluate zero-shot learning abilities. We found in a yet unpublished work different methodologies might allow measuring combinatorial generalization in a fair setting.

  • Research Products

    (1 results)

All 2022

All Journal Article (1 results) (of which Int'l Joint Research: 1 results,  Peer Reviewed: 1 results,  Open Access: 1 results)

  • [Journal Article] Reversible designs for extreme memory cost reduction of CNN training2022

    • Author(s)
      Tristan Hascoet , Quentin Febvre , Weihao Zhuang , Yasuo Ariki,Tetsuya Takiguchi
    • Journal Title

      EURASIP Journal on Image and Video Processing

      Volume: - Pages: -

    • Peer Reviewed / Open Access / Int'l Joint Research

URL: 

Published: 2022-12-28  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi