Related papers: Unsupervised Hyperbolic Representation Learning vi…
Recently, Hyperbolic Spaces in the context of Non-Euclidean Deep Learning have gained popularity because of their ability to represent hierarchical data. We propose that it is possible to take advantage of the hierarchical characteristic…
Unsupervised graph representation learning aims to distill various graph information into a downstream task-agnostic dense vector embedding. However, existing graph representation learning approaches are designed mainly under the node…
Image analysis in the euclidean space through linear hyperspaces is well studied. However, in the quest for more effective image representations, we turn to hyperbolic manifolds. They provide a compelling alternative to capture complex…
Scene graph representations enable structured visual understanding by modeling objects and their relationships, and have been widely used for multiview and 3D scene reasoning. Existing methods such as MSG learn scene graph embeddings in…
Hierarchical data arise in countless domains, from biological taxonomies and organizational charts to legal codes and knowledge graphs. Residual Quantization (RQ) is widely used to generate discrete, multitoken representations for such data…
In self-supervised learning, a system is tasked with achieving a surrogate objective by defining alternative targets on a set of unlabeled data. The aim is to build useful representations that can be used in downstream tasks, without costly…
We propose a meta-learning method for semi-supervised learning that learns from multiple tasks with heterogeneous attribute spaces. The existing semi-supervised meta-learning methods assume that all tasks share the same attribute space,…
In this paper, we introduce a unique variant of the denoising Auto-Encoder and combine it with the perceptual loss to classify images in an unsupervised manner. The proposed method, called Pseudo Labelling, consists of first applying a…
We introduce environment predictive coding, a self-supervised approach to learn environment-level representations for embodied agents. In contrast to prior work on self-supervised learning for images, we aim to jointly encode a series of…
Hyperspectral image (HSI) classification is gaining a lot of momentum in present time because of high inherent spectral information within the images. However, these images suffer from the problem of curse of dimensionality and usually…
Learning sensorimotor control policies from high-dimensional images crucially relies on the quality of the underlying visual representations. Prior works show that structured latent space such as visual keypoints often outperforms…
This paper proposes a novel unsupervised autoregressive neural model for learning generic speech representations. In contrast to other speech representation learning methods that aim to remove noise or speaker variabilities, ours is…
Brains learn to represent information from a large set of stimuli, typically by weak supervision. Unsupervised learning is therefore a natural approach for exploring the design of biological neural networks and their computations.…
Autoencoder-based learning has emerged as a staple for disciplining representations in unsupervised and semi-supervised settings. This paper analyzes a framework for improving generalization in a purely supervised setting, where the target…
Hyperbolic space can naturally embed hierarchies that often exist in real-world data and semantics. While high-dimensional hyperbolic embeddings lead to better representations, most hyperbolic models utilize low-dimensional embeddings, due…
Established methods for unsupervised representation learning such as variational autoencoders produce none or poorly calibrated uncertainty estimates making it difficult to evaluate if learned representations are stable and reliable. In…
Recent deep learning models can efficiently combine inputs from different modalities (e.g., images and text) and learn to align their latent representations, or to translate signals from one domain to another (as in image captioning, or…
A mainstream type of current self-supervised learning methods pursues a general-purpose representation that can be well transferred to downstream tasks, typically by optimizing on a given pretext task such as instance discrimination. In…
Self-Supervised learning from multimodal image and text data allows deep neural networks to learn powerful features with no need of human annotated data. Web and Social Media platforms provide a virtually unlimited amount of this multimodal…
User interaction with voice-powered agents generates large amounts of unlabeled utterances. In this paper, we explore techniques to efficiently transfer the knowledge from these unlabeled utterances to improve model performance on Spoken…