Related papers: A Co-training Approach for Noisy Time Series Learn…

Contrastive learning has recently established itself as a powerful self-supervised learning framework for extracting rich and versatile data representations. Broadly speaking, contrastive learning relies on a data augmentation scheme to…

In the near future, more and more machines will perform tasks in the vicinity of human spaces or support them directly in their spatially bound activities. In order to simplify the verbal communication and the interaction between robotic…

We tackle the problem of learning concept classifiers from videos on the web without using manually labeled data. Although metadata attached to videos (e.g., video titles, descriptions) can be of help collecting training data for the target…

Existing speculative decoding methods typically require additional model structure and training processes to assist the model for draft token generation. This makes the migration of acceleration methods to the new model more costly and more…

Consistency training regularizes a model by enforcing predictions of original and perturbed inputs to be similar. Previous studies have proposed various augmentation methods for the perturbation but are limited in that they are agnostic to…

Modern self-supervised learning algorithms typically enforce persistency of instance representations across views. While being very effective on learning holistic image and video representations, such an objective becomes sub-optimal for…

This paper proposes a self-supervised learning approach for video features that results in significantly improved performance on downstream tasks (such as video classification, captioning and segmentation) compared to existing methods. Our…

Noise is usually regarded as adversarial to extract the effective dynamics from time series, such that the conventional data-driven approaches usually aim at learning the dynamics by mitigating the noisy effect. However, noise can have a…

Generating factual-consistent summaries is a challenging task for abstractive summarization. Previous works mainly encode factual information or perform post-correct/rank after decoding. In this paper, we provide a factual-consistent…

In this paper we introduce a method for significantly improving the signal to noise ratio in financial data. The approach relies on combining a target variable with different context variables and use auto-encoders (AEs) to learn…

Self-supervised contrastive learning offers a means of learning informative features from a pool of unlabeled data. In this paper, we delve into another useful approach -- providing a way of selecting a core-set that is entirely unlabeled.…

Recently, the cross-modal pre-training task has been a hotspot because of its wide application in various down-streaming researches including retrieval, captioning, question answering and so on. However, exiting methods adopt a one-stream…

Tensor train (TT) decomposition, a powerful tool for analyzing multidimensional data, exhibits superior performance in many machine learning tasks. However, existing methods for TT decomposition either suffer from noise overfitting, or…

Learning robust representations of polyp tracklets is key to enabling multiple AI-assisted colonoscopy applications, from polyp characterization to automated reporting and retrieval. Supervised contrastive learning is an effective approach…

Carrying conversations in multi-sound environments is one of the more challenging tasks, since the sounds overlap across time and frequency making it difficult to understand a single sound source. One proposed approach to help isolate an…

In this paper, we propose test-time training with the quantum auto-encoder (QTTT). QTTT adapts to (1) data distribution shifts between training and testing data and (2) quantum circuit error by minimizing the self-supervised loss of the…

The standard approach to contrastive learning is to maximize the agreement between different views of the data. The views are ordered in pairs, such that they are either positive, encoding different views of the same object, or negative,…

Audiovisual representation learning typically relies on the correspondence between sight and sound. However, there are often multiple audio tracks that can correspond with a visual scene. Consider, for example, different conversations on…

Correlated time series analysis plays an important role in many real-world industries. Learning an efficient representation of this large-scale data for further downstream tasks is necessary but challenging. In this paper, we propose a…

This thesis focuses on representation learning for sequence data over time or space, aiming to improve downstream sequence prediction tasks by using the learned representations. Supervised learning has been the most dominant approach for…