Papers › PhiNet v2: A Mask-Free Brain-Inspired Vision Foundation Model from Video

PhiNet v2: A Mask-Free Brain-Inspired Vision Foundation Model from Video

16 May 2025arXiv:2505.11129archive 2025-07-28

Makoto Yamada, Kian Ming A. Chai, Ayoub Rhim, Satoki Ishikawa, Mohammad Sabokrou, Yao-Hung Hubert Tsai

Recent advances in self-supervised learning (SSL) have revolutionized computer vision through innovative architectures and learning objectives, yet they have not fully leveraged insights from biological visual processing systems. Recently, a brain-inspired SSL model named PhiNet was proposed; it is based on a ResNet backbone and operates on static image inputs with strong augmentation. In this paper, we introduce PhiNet v2, a novel Transformer-based architecture that processes temporal visual input (that is, sequences of images) without relying on strong augmentation. Our model leverages variational inference to learn robust visual representations from continuous input streams, similar to human visual processing. Through extensive experimentation, we demonstrate that PhiNet v2 achieves competitive performance compared to state-of-the-art vision foundation models, while maintaining the ability to learn from sequential input without strong data augmentation. This work represents a significant step toward more biologically plausible computer vision systems that process visual information in a manner more closely aligned with human cognitive processes.

PaperPDFCode

Code

oist/phinetv2 officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Data AugmentationSelf-Supervised LearningVariational Inference

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Average PoolingConvolutionGlobal Average PoolingKaiming InitializationMax PoolingVariational Inference

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections