6 papers
Geometry-Aware Hyperbolic Residual-Quantized Variational Autoencoders
Alessio Colombo, Melika Ayoughi
Residual Vector Quantization turns continuous representations into discrete, multi-level token sequences. Yet most methods operate in Euclidean space, despite the coarse-to-fine st…
Minimizing Hyperbolic Embedding Distortion with LLM-Guided Hierarchy Restructuring
Melika Ayoughi, Pascal Mettes, Paul Groth
Hyperbolic geometry is an effective geometry for embedding hierarchical data structures. Hyperbolic learning has therefore become increasingly prominent in machine learning applica…
Learning the relative composition of EEG signals using pairwise relative shift pretraining
Christopher Sandino, Sayeri Lala, Geeling Chau +6
Self-supervised learning (SSL) offers a promising approach for learning electroencephalography (EEG) representations from unlabeled data, reducing the need for expensive annotation…
Continual Hyperbolic Learning of Instances and Classes
Melika Ayoughi, Mina Ghadimi Atigh, Mohammad Mahdi Derakhshani +3
Continual learning has traditionally focused on classifying either instances or classes, but real-world applications, such as robotics and self-driving cars, require models to hand…
How PARTs assemble into wholes: Learning the relative composition of images
Melika Ayoughi, Samira Abnar, Chen Huang +10
The composition of objects and their parts, along with object-object positional relationships, provides a rich source of information for representation learning. Hence, spatial-awa…
Self-Contained Entity Discovery from Captioned Videos
Melika Ayoughi, Pascal Mettes, Paul Groth
This paper introduces the task of visual named entity discovery in videos without the need for task-specific supervision or task-specific external knowledge sources. Assigning spec…