Sample-Specific Debiasing for Better Image-Text Models
This work addresses a specific bottleneck in medical AI applications like image classification and cross-modal retrieval, offering an incremental improvement over existing debiased contrastive learning techniques.
The paper tackled the problem of false negatives in contrastive learning for image-text models, particularly in healthcare data with nonuniform class distributions, by developing a sample-specific debiasing method that improved representation quality, as demonstrated through experiments on image and image-text datasets.
Self-supervised representation learning on image-text data facilitates crucial medical applications, such as image classification, visual grounding, and cross-modal retrieval. One common approach involves contrasting semantically similar (positive) and dissimilar (negative) pairs of data points. Drawing negative samples uniformly from the training data set introduces false negatives, i.e., samples that are treated as dissimilar but belong to the same class. In healthcare data, the underlying class distribution is nonuniform, implying that false negatives occur at a highly variable rate. To improve the quality of learned representations, we develop a novel approach that corrects for false negatives. Our method can be viewed as a variant of debiased contrastive learning that uses estimated sample-specific class probabilities. We provide theoretical analysis of the objective function and demonstrate the proposed approach on both image and paired image-text data sets. Our experiments illustrate empirical advantages of sample-specific debiasing.