# Sample-Specific Debiasing for Better Image-Text Models Source: [Sample-Specific Debiasing for Better Image-Text Models]() Collection index: [llms.txt]() Data updated: 2025-10-26T01:37:08.974Z Authors: Peiqi Wang, Yingcheng Liu, Ching-Yun Ko, William M. Wells, Seth Berkowitz, Steven Horng, Polina Golland Published: 2023-04-25T22:23:41.000Z ## Abstract 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. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. ## Original sources and implementation [Original paper]() [PDF]()