18336423. VISUAL GROUNDING OF SELF-SUPERVISED REPRESENTATIONS FOR MACHINE LEARNING MODELS UTILIZING DIFFERENCE ATTENTION (Adobe Inc.)
Contents
VISUAL GROUNDING OF SELF-SUPERVISED REPRESENTATIONS FOR MACHINE LEARNING MODELS UTILIZING DIFFERENCE ATTENTION
Organization Name
Inventor(s)
Aishwarya Agarwal of Bengaluru (IN)
Srikrishna Karanam of Bangalore (IN)
Balaji Vasan Srinivasan of Bangalore (IN)
VISUAL GROUNDING OF SELF-SUPERVISED REPRESENTATIONS FOR MACHINE LEARNING MODELS UTILIZING DIFFERENCE ATTENTION
This abstract first appeared for US patent application 18336423 titled 'VISUAL GROUNDING OF SELF-SUPERVISED REPRESENTATIONS FOR MACHINE LEARNING MODELS UTILIZING DIFFERENCE ATTENTION
Original Abstract Submitted
The present disclosure relates to systems, non-transitory computer-readable media, and methods for utilizing difference attention to evaluate and/or train machine learning models. In particular, in some embodiments, the disclosed systems generate, utilizing a machine learning model, a first feature vector from a digital image. In one or more implementations, the disclosed systems generate a masked digital image by masking a region from the digital image. Additionally, in some embodiments, the disclosed systems generate, utilizing the machine learning model, a second feature vector from the masked digital image. Moreover, in some implementations, the disclosed systems determine a difference feature vector between the first feature vector and the second feature vector. Furthermore, in some embodiments, the disclosed systems generate, from the difference feature vector, a difference attention map reflecting a visual grounding of the machine learning model relative to the region.
