Summary of Multimodal Commonsense Knowledge Distillation For Visual Question Answering, by Shuo Yang et al.
Multimodal Commonsense Knowledge Distillation for Visual Question Answering
by Shuo Yang, Siwen Luo, Soyeon Caren Han
First submitted to arxiv on: 5 Nov 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI)
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 proposed graph-based multimodal commonsense knowledge distillation framework constructs a unified relational graph over commonsense knowledge, visual objects, and questions through a Graph Convolutional Network (GCN). This framework is flexible with any type of teacher and student models without further fine-tuning, achieving competitive performances on the ScienceQA dataset. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary A new way to help computers understand questions that require common sense has been developed. Currently, AI models struggle to answer these types of questions because they need a lot of training data and computing power. The proposed approach uses a special kind of graph to connect common sense knowledge with visual objects and questions, allowing it to be used with different AI models without needing more training. |
Keywords
» Artificial intelligence » Convolutional network » Fine tuning » Gcn » Knowledge distillation
