Related papers: Masked Modeling Duo: Learning Representations by E…

Neural models have become ubiquitous in automatic speech recognition systems. While neural networks are typically used as acoustic models in more complex systems, recent studies have explored end-to-end speech recognition systems based on…

How to learn discriminative video representation from unlabeled videos is challenging but crucial for video analysis. The latest attempts seek to learn a representation model by predicting the appearance contents in the masked regions.…

We introduce a novel learning-based method for encoding and manipulating 3D surface meshes. Our method is specifically designed to create an interpretable embedding space for deformable shape collections. Unlike previous 3D mesh…

In many machine learning tasks, learning a good representation of the data can be the key to building a well-performant solution. This is because most learning algorithms operate with the features in order to find models for the data. For…

Training visual embeddings with labeled data supervision has been the de facto setup for representation learning in computer vision. Inspired by recent success of adopting masked image modeling (MIM) in self-supervised representation…

Unified multimodal models typically rely on pretrained vision encoders and use separate visual representations for understanding and generation, creating misalignment between the two tasks and preventing fully end-to-end optimization from…

Representation learning seeks to expose certain aspects of observed data in a learned representation that's amenable to downstream tasks like classification. For instance, a good representation for 2D images might be one that describes only…

Representation learning has overcome the often arduous and manual featurization of networks through (unsupervised) feature learning as it results in embeddings that can apply to a variety of downstream learning tasks. The focus of…

Deep learning Networks play a crucial role in the evolution of a vast number of current machine learning models for solving a variety of real world non-trivial tasks. Such networks use big data which is generally unlabeled unsupervised and…

When capturing and storing images, devices inevitably introduce noise. Reducing this noise is a critical task called image denoising. Deep learning has become the de facto method for image denoising, especially with the emergence of…

Learning a better representation with neural networks is a challenging problem, which was tackled extensively from different prospectives in the past few years. In this work, we focus on learning a representation that could be used for a…

We introduce DenoMAE2.0, an enhanced denoising masked autoencoder that integrates a local patch classification objective alongside traditional reconstruction loss to improve representation learning and robustness. Unlike conventional Masked…

We present a representation learning method that learns features at multiple different levels of scale. Working within the unsupervised framework of denoising autoencoders, we observe that when the input is heavily corrupted during…

Communication is essential in coordinating the behaviors of multiple agents. However, existing methods primarily emphasize content, timing, and partners for information sharing, often neglecting the critical aspect of integrating shared…

2D top-down maps are commonly used for the navigation and exploration of mobile robots through unknown areas. Typically, the robot builds the navigation maps incrementally from local observations using onboard sensors. Recent works have…

This paper shows that Masking the Deep hierarchical features is an efficient self-supervised method, denoted as MaskDeep. MaskDeep treats each patch in the representation space as an independent instance. We mask part of patches in the…

Most existing text recognition methods are trained on large-scale synthetic datasets due to the scarcity of labeled real-world datasets. Synthetic images, however, cannot faithfully reproduce real-world scenarios, such as uneven…

Anomaly detection on attributed networks aims at finding nodes whose patterns deviate significantly from the majority of reference nodes, which is pervasive in many applications such as network intrusion detection and social spammer…

In this paper, we study learning generalized driving style representations from automobile GPS trip data. We propose a novel Autoencoder Regularized deep neural Network (ARNet) and a trip encoding framework trip2vec to learn drivers'…

Molecular representation learning has attracted much attention recently. A molecule can be viewed as a 2D graph with nodes/atoms connected by edges/bonds, and can also be represented by a 3D conformation with 3-dimensional coordinates of…