Huyen Le

Fabian Gröger, Shuo Wen, Huyen Le et al.

Multimodal models have demonstrated powerful capabilities in complex tasks requiring multimodal alignment, including zero-shot classification and cross-modal retrieval. However, existing models typically rely on millions of paired multimodal samples, which are prohibitively expensive or infeasible to obtain in many domains. In this work, we explore the feasibility of building multimodal models with limited amount of paired data by aligning pretrained unimodal foundation models. We show that high-quality alignment is possible with as few as tens of thousands of paired samples$\unicode{x2013}$less than $1\%$ of the data typically used in the field. To achieve this, we introduce STRUCTURE, an effective regularization technique that preserves the neighborhood geometry of the latent space of unimodal encoders. Additionally, we show that aligning last layers is often suboptimal and demonstrate the benefits of aligning the layers with the highest representational similarity across modalities. These two components can be readily incorporated into existing alignment methods, yielding substantial gains across 24 zero-shot image classification and retrieval benchmarks, with average relative improvement of $51.6\%$ in classification and $91.8\%$ in retrieval tasks. Our results highlight the effectiveness and broad applicability of our framework for limited-sample multimodal learning and offer a promising path forward for resource-constrained domains.

Huyen Le, Khiet Dang, Nhung Nguyen et al.

Human-induced pluripotent stem cell-derived cardiomyocytes (hiPSC-CMs) are a powerful tool in advancing cardiovascular research and clinical applications. The maturation of sarcomere organization in hiPSC-CMs is crucial, as it supports the contractile function and structural integrity of these cells. Traditional methods for assessing this maturation like manual annotation and feature extraction are labor-intensive, time-consuming, and unsuitable for high-throughput analysis. To address this, we propose D-SarcNet, a dual-stream deep learning framework that takes fluorescent hiPSC-CM single-cell images as input and outputs the stage of the sarcomere structural organization on a scale from 1.0 to 5.0. The framework also integrates Fast Fourier Transform (FFT), deep learning-generated local patterns, and gradient magnitude to capture detailed structural information at both global and local levels. Experiments on a publicly available dataset from the Allen Institute for Cell Science show that the proposed approach not only achieves a Spearman correlation of 0.868 marking a 3.7% improvement over the previous state-of-the-art but also significantly enhances other key performance metrics, including MSE, MAE, and R2 score. Beyond establishing a new state-of-the-art in sarcomere structure assessment from hiPSC-CM images, our ablation studies highlight the significance of integrating global and local information to enhance deep learning networks ability to discern and learn vital visual features of sarcomere structure.