Finding Distributed Object-Centric Properties in Self-Supervised Transformers

1. 1Analyzing the limitations of using [CLS] token attention maps for object detection
2. 2Investigating alternative approaches to focus on object-centric information
3. 3Evaluating the effectiveness of self-supervised Vision Transformers in discovering distributed object-centric properties

Computer vision engineers and researchers working on self-supervised learning and Vision Transformers can benefit from this study to improve object detection and localization in images

💡 Self-supervised Vision Transformers can learn to focus on objects without relying on image-level objectives, improving object detection and localization

🔍 Discovering object-centric properties in self-supervised Vision Transformers without image-level objectives