Topic: contrastive learning

Munawar Hayat discusses visual grounding and object hallucination in vision-language models. Topics include attention-guided alignment, contrastive learning for combined image-and-text retrieval, and evaluating images containing multiple people. The conversation connects identity leakage and attribute blending with the constraints of efficient on-device deployment.

Children learn to build a visual representation of the world from unsupervised exploration and we hypothesize that a key part of this learning ability is the use of self-generated navigational information as a similarity label to drive a learning objective for self-supervised learning. The goal of this work is to exploit navigational information in a visual environment to provide performance in training that exceeds the state-of-the-art self-supervised training. Here, we show that using spatial and temporal information in the pretraining stage of contrastive learning can improve the performan

Human olfactory perception is understudied in the whole spectrum of neuroscience, from computational to system neuroscience. In this study, we explore the hierarchy underlying human olfactory perception by embedding perceptual data in the hyperbolic space. Previous research emphasizes the significance of hyperbolic geometry in gaining insights into the neural encoding of natural odorants. This is due to the exponential growth of the hyperbolic space, that makes it appropriate to encode hierarchical data. We employ a contrastive learning approach over the Poincare ball in order to embed olfacto