Yair Smadar

Roi Peleg, Yair Smadar, Teddy Lazebnik et al.

The performance of deep learning models is critically dependent on sophisticated optimization strategies. While existing optimizers have shown promising results, many rely on first-order Exponential Moving Average (EMA) techniques, which often limit their ability to track complex gradient trends accurately. This fact can lead to a significant lag in trend identification and suboptimal optimization, particularly in highly dynamic gradient behavior. To address this fundamental limitation, we introduce Fast Adaptive Moment Estimation (FAME), a novel optimization technique that leverages the power of Triple Exponential Moving Average. By incorporating an advanced tracking mechanism, FAME enhances responsiveness to data dynamics, mitigates trend identification lag, and optimizes learning efficiency. Our comprehensive evaluation encompasses different computer vision tasks including image classification, object detection, and semantic segmentation, integrating FAME into 30 distinct architectures ranging from lightweight CNNs to Vision Transformers. Through rigorous benchmarking against state-of-the-art optimizers, FAME demonstrates superior accuracy and robustness. Notably, it offers high scalability, delivering substantial improvements across diverse model complexities, architectures, tasks, and benchmarks.

Dmitri, Lvov, Yair Smadar et al.

In this paper, we explore the application of Recurrent Neural Network (RNN) for still images. Typically, Convolutional Neural Networks (CNNs) are the prevalent method applied for this type of data, and more recently, transformers have gained popularity, although they often require large models. Unlike these methods, RNNs are generally associated with processing sequences over time rather than single images. We argue that RNNs can effectively handle still images by interpreting the pixels as a sequence. This approach could be particularly advantageous for compact models designed for embedded systems, where resources are limited. Additionally, we introduce a novel RNN design tailored for two-dimensional inputs, such as images, and a custom version of BiDirectional RNN (BiRNN) that is more memory-efficient than traditional implementations. In our research, we have tested these layers in Convolutional Recurrent Neural Networks (CRNNs), predominantly composed of Conv2D layers, with RNN layers at or close to the end. Experiments on the COCO and CIFAR100 datasets show better results, particularly for small networks.