Related papers: Contrastive Meta-Learning for Partially Observable…

Asymmetric appearance between positive pair effectively reduces the risk of representation degradation in contrastive learning. However, there are still a mass of appearance similarities between positive pair constructed by the existing…

We propose a method to facilitate exploration and analysis of new large data sets. In particular, we give an unsupervised deep learning approach to learning a latent representation that captures semantic similarity in the data set. The core…

Since the meaning representations are detailed and accurate annotations which express fine-grained sequence-level semtantics, it is usually hard to train discriminative semantic parsers via Maximum Likelihood Estimation (MLE) in an…

Contrastive learning have been widely used as pretext tasks for self-supervised pre-trained molecular representation learning models in AI-aided drug design and discovery. However, exiting methods that generate molecular views by…

In the early observation period of a time series, there might be only a few historic observations available to learn a model. However, in cases where an existing prior set of datasets is available, Meta learning methods can be applicable.…

Music retrieval and recommendation applications often rely on content features encoded as embeddings, which provide vector representations of items in a music dataset. Numerous complementary embeddings can be derived from processing items…

Contrastive learning (CL) has emerged as a powerful technique for representation learning, with or without label supervision. However, supervised CL is prone to collapsing representations of subclasses within a class by not capturing all…

A large-scale vision and language model that has been pretrained on massive data encodes visual and linguistic prior, which makes it easier to generate images and language that are more natural and realistic. Despite this, there is still a…

In neutrino physics, analyses often depend on large simulated datasets, making it essential for models to generalise effectively to real-world detector data. Contrastive learning, a well-established technique in deep learning, offers a…

This paper presents a self-supervised feature learning method for hyperspectral image classification. Our method tries to construct two different views of the raw hyperspectral image through a cross-representation learning method. And then…

Meta-learning has been the most common framework for few-shot learning in recent years. It learns the model from collections of few-shot classification tasks, which is believed to have a key advantage of making the training objective…

Despite the success of a number of recent techniques for visual self-supervised deep learning, there has been limited investigation into the representations that are ultimately learned. By leveraging recent advances in the comparison of…

In many machine learning problems, labeled training data is limited but unlabeled data is ample. Some of these problems have instances that can be factored into multiple views, each of which is nearly sufficent in determining the correct…

Visual recognition tasks are often limited to dealing with a small subset of classes simply because the labels for the remaining classes are unavailable. We are interested in identifying novel concepts in a dataset through representation…

Machine learning can greatly benefit from providing learning algorithms with pairs of contrastive training examples -- typically pairs of instances that differ only slightly, yet have different class labels. Intuitively, the difference in…

Predicting a landslide susceptibility map (LSM) is essential for risk recognition and disaster prevention. Despite the successful application of data-driven approaches for LSM prediction, most methods generally apply a single global model…

Learning good representations involves capturing the diverse ways in which data samples relate. Contrastive loss - an objective matching related samples - underlies methods from self-supervised to multimodal learning. Contrastive losses,…

Several automatic approaches for objective music performance assessment (MPA) have been proposed in the past, however, existing systems are not yet capable of reliably predicting ratings with the same accuracy as professional judges. This…

Learning with few samples is a major challenge for parameter-rich models like deep networks. In contrast, people learn complex new concepts even from very few examples, suggesting that the sample complexity of learning can often be reduced.…

A lot of recent advances in unsupervised feature learning are based on designing features which are invariant under semantic data augmentations. A common way to do this is contrastive learning, which uses positive and negative samples. Some…