Deciphering the Role of Representation Disentanglement: Investigating Compositional Generalization in CLIP Models
- 24 November 2024
- book chapter
- Published by Springer Nature
- p. 35-50
Abstract
No abstract availableKeywords
All Related Versions
This publication has 7 references indexed in Scilit:
- CounterCurate: Enhancing Physical and Semantic Visio-Linguistic Compositional Reasoning via Counterfactual Examples2024
- Disentangled Representation Learning for Multimedia2023
- On Evaluating Multilingual Compositional Generalization with Translated Datasets2023
- Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality2022
- Improving Compositional Generalization with Self-Training for Data-to-Text Generation2022
- Learning to Predict Visual Attributes in the Wild2021
- Compositional Generalization and Natural Language Variation: Can a Semantic Parsing Approach Handle Both?2021