SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2203.15266 · CVPR · 2022

Interactive Multi-Class Tiny-Object Detection

Seonwook Park, Chunggi Lee, Sanghoon Kim, Heon Song, Donggeun Yoo, Sérgio Pereira, Jeongun Ryu, Haejoon Kim

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. If it links a repository, it is listed below.

Abstract

An annotator clicks on some instances and classes C3Det detects many objects from different classes, even for classes not specified by the annotator The annotator clicks on a few objects that were omitted in the previous step few more clicks More objects are detected Eventually, all objects are detected Figure 1. C3Det is a deep learning framework for interactive tiny-object detection that relates multiple annotator clicks to multiple instances and multiple classes of objects (each object class is depicted with a different color), in order to reduce overall annotation cost.

For agents

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

get_harvested_code_for_paper("2203.15266")
get_code_for_paper("2203.15266")
have("2203.15266")

Connect an agent — have() is free.