# The Pursuit of Knowledge: Discovering and Localizing Novel Categories using Dual Memory

Source: [The Pursuit of Knowledge: Discovering and Localizing Novel Categories using Dual Memory](<https://www.sota2.com/research/paper/68fa6ad31e209131cea2a931>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T23:34:16.637Z

Authors: Sai Saketh Rambhatla, Rama Chellappa, Abhinav Shrivastava

Published: 2021-05-04T17:55:59.000Z

## Abstract

We tackle object category discovery, which is the problem of discovering and localizing novel objects in a large unlabeled dataset. While existing methods show results on datasets with less cluttered scenes and fewer object instances per image, we present our results on the challenging COCO dataset. Moreover, we argue that, rather than discovering new categories from scratch, discovery algorithms can benefit from identifying what is already known and focusing their attention on the unknown. We propose a method that exploits prior knowledge about certain object types to discover new categories by leveraging two memory modules, namely Working and Semantic memory. We show the performance of our detector on the COCO minival dataset to demonstrate its in-the-wild capabilities.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2105.01652>)

[PDF](<https://arxiv.org/pdf/2105.01652.pdf>)