Brain-Inspired Stochastic Joint Embedding Representation Learning
For computer vision researchers, this work offers a biologically plausible SSL approach that reduces reliance on data augmentation, though performance gains are not demonstrated.
PhiNet v2 learns robust visual representations from sequential image input without strong data augmentation, achieving competitive performance with state-of-the-art models like RSP and CropMAE.
Representation learning is one of the key research topics in machine learning, and the framework of self-supervised learning (SSL) has revolutionized computer vision. However, these approaches have not yet fully leveraged insights from biological visual processing systems. In this paper, we introduce PhiNet v2, a novel architecture that processes temporal visual input (i.e., sequences of images) without relying on strong data augmentation, enabling it to learn robust visual representations in a manner similar to human visual processing. Our learning objective is derived from variational inference. Through extensive experiments, we demonstrate that PhiNet v2 achieves competitive performance compared to state-of-the-art vision representation models, including RSP and CropMAE, while retaining the ability to learn effectively from sequential input without strong data augmentation. This work represents a step toward more biologically plausible computer vision systems that process visual information in a manner more aligned with human cognitive processes.