Summary of Similarity-dissimilarity Loss with Supervised Contrastive Learning For Multi-label Classification, by Guangming Huang et al.
Similarity-Dissimilarity Loss with Supervised Contrastive Learning for Multi-label Classification
by Guangming Huang, Yunfei Long, Cunjin Luo, Sheng Liu
First submitted to arxiv on: 17 Oct 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Computation and Language (cs.CL); Computer Vision and Pattern Recognition (cs.CV)
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 The paper proposes a novel approach to multi-label classification using supervised contrastive learning, specifically addressing the challenge of identifying positive samples in this scenario. The authors introduce five distinct relations between samples and propose a Similarity-Dissimilarity Loss with contrastive learning for multi-label classification. This loss function re-weights the loss based on the similarity and dissimilarity between positive samples and an anchor, taking into account various relationships between anchors and samples. The approach is evaluated on MIMIC datasets for multi-label text classification and further extended to MS-COCO. Experimental results demonstrate the effectiveness and robustness of the proposed loss under the supervised contrastive learning paradigm. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper tries to solve a big problem in making computers good at understanding lots of things at once. When we have many labels (or categories) for something, like text or images, it’s hard for machines to figure out which ones are most important. The authors come up with a new way to make this process better by looking at different relationships between these labels and the data itself. They test their idea on some medical records and image datasets and show that it works really well. |
Keywords
» Artificial intelligence » Classification » Loss function » Supervised » Text classification
