LowDINO -- A Low Parameter Self Supervised Learning Model
This work addresses the need for efficient self-supervised learning models for resource-constrained applications, but it is incremental as it builds on existing SSL methods and architectures.
The paper tackles the problem of designing small neural networks for self-supervised learning by proposing LowDINO, a model with under 5 million parameters that uses MobileViT blocks and self-distillation to achieve performance comparable to large models on tasks like image classification and segmentation.
This research aims to explore the possibility of designing a neural network architecture that allows for small networks to adopt the properties of huge networks, which have shown success in self-supervised learning (SSL), for all the downstream tasks like image classification, segmentation, etc. Previous studies have shown that using convolutional neural networks (ConvNets) can provide inherent inductive bias, which is crucial for learning representations in deep learning models. To reduce the number of parameters, attention mechanisms are utilized through the usage of MobileViT blocks, resulting in a model with less than 5 million parameters. The model is trained using self-distillation with momentum encoder and a student-teacher architecture is also employed, where the teacher weights use vision transformers (ViTs) from recent SOTA SSL models. The model is trained on the ImageNet1k dataset. This research provides an approach for designing smaller, more efficient neural network architectures that can perform SSL tasks comparable to heavy models