mlsanityData to 14 Oct 2026

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

arXiv 2105.01652 ↗First posted 4 May 2021cs.CV cs.AIcited by 13

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 13 papers in the map (data through 14 Oct 2026). Builds on 33 of its 74 references that are in the map. First posted on arXiv 4 May 2021.

Builds on

33 of 74 references.

References · 33

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  3. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
  4. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  5. 2017Mask R-CNNcited by 7,277
  6. 2015Fast R-CNNcited by 2,933
  7. 2016iCaRL: Incremental Classifier and Representation Learningcited by 2,333
  8. 2013Rich feature hierarchies for accurate object detection and semantic segmentationcited by 2,162
  9. 2019LVIS: A Dataset for Large Vocabulary Instance Segmentationcited by 1,217
  10. 2018End-to-End Incremental Learningcited by 597
  11. 2016Training Region-based Object Detectors with Online Hard Example Miningcited by 579
  12. 2014Semi-Supervised Learning with Deep Generative Modelscited by 496
21 more
  1. 2018Learning without Memorizingcited by 250
  2. 2014Towards Open World Recognitioncited by 226
  3. 2019Learning to Discover Novel Visual Categories via Deep Transfer Clusteringcited by 225
  4. 2017Incremental Learning of Object Detectors without Catastrophic Forgettingcited by 208
  5. 2018Zero-shot Recognition via Semantic Embeddings and Knowledge Graphscited by 155
  6. 2020Automatically Discovering and Learning New Visual Categories with Ranking Statisticscited by 143
  7. 2017Learning to cluster in order to transfer across domains and taskscited by 128
  8. 2017Data Distillation: Towards Omni-Supervised Learningcited by 126
  9. 2019Multi-class Classification without Multi-class Labelscited by 100
  10. 2019Efficient Parameter-free Clustering Using First Neighbor Relationscited by 97
  11. 2015Unsupervised Object Discovery and Localization in the Wild: Part-based Matching with Bottom-up Region Proposalscited by 69
  12. 2020Toward unsupervised, multi-object discovery in large-scale image collectionscited by 65
  13. 2016The More You Know: Using Knowledge Graphs for Image Classificationcited by 63
  14. 2018FineGAN: Unsupervised Hierarchical Disentanglement for Fine-Grained Object Generation and Discoverycited by 58
  15. 2019Unsupervised Image Matching and Object Discovery as Optimizationcited by 42
  16. 2018Object Discovery in Videos as Foreground Motion Clusteringcited by 32
  17. 2019Object Discovery with a Copy-Pasting GANcited by 29
  18. 2015Unsupervised Object Discovery and Tracking in Video Collectionscited by 17
  19. 2015Watch and Learn: Semi-Supervised Learning of Object Detectors from Videoscited by 17
  20. 2019Large-Scale Object Mining for Object Discovery from Unlabeled Videocited by 11
  21. 2016Deep Image Category Discovery using a Transferred Similarity Functioncited by 5

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 5; 2023: 2; 2024: 5.

13 papers.

Sort:

  1. 2022Towards Open-Set Object Detection and Discoverycited by 44
  2. 2024LiFT: A Surprisingly Simple Lightweight Feature Transform for Dense ViT Descriptorscited by 27
  3. 2022MOVE: Unsupervised Movable Object Segmentation and Detectioncited by 20
  4. 2023MOST: Multiple Object localization with Self-supervised Transformers for object discoverycited by 17
  5. 2022SparseDet: Improving Sparsely Annotated Object Detection with Pseudo-positive Miningcited by 14
  6. 2024Cross-domain Open-world Discoverycited by 6
  7. 2022NovelCraft: A Dataset for Novelty Detection and Discovery in Open Worldscited by 4
  8. 2022Learning Commonsense-aware Moment-Text Alignment for Fast Video Temporal Groundingcited by 3
  9. 2021PatchNet: Unsupervised Object Discovery based on Patch Embeddingcited by 2
  10. 2024PANDAS: Prototype-based Novel Class Discovery and Detectioncited by 2
  11. 2024Debiased Novel Category Discovering and Localizationcited by 2
  12. 2023A Unified Evaluation Framework for Novelty Detection and Accommodation in NLP with an Instantiation in Authorship Attributioncited by 1
1 more
  1. 2024OW-Rep: Open World Object Detection with Instance Representation Learningcited by 0