4 papers
Simulation-to-real transfer learning for infrared spectroscopic chemical sensing and analysis from molecules to complex samples
Yusen Tan, Yixuan Chen, Zheng Fang +8
Infrared (IR) spectroscopy is widely used for chemical sensing, but extracting reliable chemical information from spectra remains challenging. Conventional interpretation is labor-…
When Slots Compete: Slot Merging in Object-Centric Learning
Christos Chatzisavvas, Panagiotis Rigas, George Ioannakis +2
Slot-based object-centric learning represents an image as a set of latent slots with a decoder that combines them into an image or features. The decoder specifies how slots are com…
Interpretable Vision Transformers in Monocular Depth Estimation via SVDA
Vasileios Arampatzakis, George Pavlidis, Nikolaos Mitianoudis +1
Monocular depth estimation is a central problem in computer vision with applications in robotics, AR, and autonomous driving, yet the self-attention mechanisms that drive modern Tr…
Interpretable Vision Transformers in Image Classification via SVDA
Vasileios Arampatzakis, George Pavlidis, Nikolaos Mitianoudis +1
Vision Transformers (ViTs) have achieved state-of-the-art performance in image classification, yet their attention mechanisms often remain opaque and exhibit dense, non-structured…