Summary of Data-driven Hierarchical Open Set Recognition, by Andrew Hannum et al.
Data-Driven Hierarchical Open Set Recognition
by Andrew Hannum, Max Conway, Mario Lopez, André Harrison
First submitted to arxiv on: 4 Nov 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Machine Learning (cs.LG)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper proposes a novel approach to open set recognition (OSR), a hierarchical method that automatically builds a hierarchy of known classes in embedding space without requiring manual relational information. The authors utilize constrained agglomerative clustering and demonstrate their method on the Animals with Attributes 2 (AwA2) dataset, achieving an AUC ROC score of 0.82 and utility score of 0.85. The approach introduces two classification methods (score-based and traversal-based) and a new Concentration Centrality (CC) metric for measuring hierarchical classification consistency. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper helps robots and computers see better by creating a special way to recognize unknown things. It’s called open set recognition, or OSR. Normally, we need to teach machines what something is before they can recognize it. But this new method doesn’t require that. Instead, it uses clustering to group similar things together in a hierarchy. This helps robots and computers understand what they don’t know. The paper tests its method on some animals pictures and gets good results. |
Keywords
» Artificial intelligence » Auc » Classification » Clustering » Embedding space
