Summary of Scaling Up Deep Clustering Methods Beyond Imagenet-1k, by Nikolas Adaloglou and Felix Michels and Kaspar Senft and Diana Petrusheva and Markus Kollmann
Scaling Up Deep Clustering Methods Beyond ImageNet-1K
by Nikolas Adaloglou, Felix Michels, Kaspar Senft, Diana Petrusheva, Markus Kollmann
First submitted to arxiv on: 3 Jun 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Artificial Intelligence (cs.AI); 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 Deep image clustering methods are typically evaluated on small-scale balanced classification datasets while feature-based k-means has been applied on proprietary billion-scale datasets. The paper explores the performance of feature-based deep clustering approaches on large-scale benchmarks, disentangling the impact of class imbalance, granularity, easily recognizable classes, and capturing multiple classes. New ImageNet21K-based benchmarks are developed to evaluate the methods’ performance. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Imagine you have a huge collection of images, and you want to group them into similar categories. This paper studies how well different computer algorithms do this job on really large datasets. It shows that some algorithms work better than others when dealing with unbalanced datasets or easy-to-classify images. The study also finds that non-main category predictions can be useful in discovering new subcategories. |
Keywords
» Artificial intelligence » Classification » Clustering » K means
