ULTra: Unveiling Latent Token Interpretability in Transformer-Based Understanding and Segmentation
Year: 2024
Type: preprint
Abstract: Transformers have revolutionized Computer Vision (CV) through self-attention mechanisms. However, their complexity makes latent token representations difficult to interpret. We introduce ULTra, a framework for interpreting Transformer embeddings and uncovering meaningful semantic patterns within them. ULTra enables unsupervised semantic segmentation using pre-trained models without requiring fine-tuning. Additionally, we propose a self-supervised training approach that refines segmentation performance by learning an external transformation matrix without modifying the underlying model. Our method achieves state-of-the-art performance in unsupervised semantic segmentation, outperforming existing segmentation methods. Furthermore, we validate ULTra for model interpretation on both synthetic and real-world scenarios, including Object Selection and interpretable text summarization using LLMs, demonstrating its broad applicability in explaining the semantic structure of latent token representations.
Source: arXiv (Cornell University)
Authors: Hosseini, Hesam, Mighan, Ghazal Hosseini, Afzali, Amirabbas, Amini, Sajjad, Houmansadr, Amir
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4404574365