Related papers: ADROIT: A Self-Supervised Framework for Learning R…

Semi-supervised learning (SSL) is an efficient framework that can train models with both labeled and unlabeled data, but may generate ambiguous and non-distinguishable representations when lacking adequate labeled samples. With…

Active learning emerged as an alternative to alleviate the effort to label huge amount of data for data hungry applications (such as image/video indexing and retrieval, autonomous driving, etc.). The goal of active learning is to…

Learning compact and interpretable representations of data is a critical challenge in scientific image analysis. Here, we introduce Affinity-VAE, a generative model that enables us to impose our scientific intuition about the similarity of…

Masked autoencoders have become popular training paradigms for self-supervised visual representation learning. These models randomly mask a portion of the input and reconstruct the masked portion according to the target representations. In…

Despite the significant improvements that representation learning via self-supervision has led to when learning from unlabeled data, no methods exist that explain what influences the learned representation. We address this need through our…

We introduce an unsupervised domain adaption (UDA) strategy that combines multiple image translations, ensemble learning and self-supervised learning in one coherent approach. We focus on one of the standard tasks of UDA in which a semantic…

We present a discriminative clustering approach in which the feature representation can be learned from data and moreover leverage labeled data. Representation learning can give a similarity-based clustering method the ability to…

Research in auditory, visual, and audiovisual speech recognition (ASR, VSR, and AVSR, respectively) has traditionally been conducted independently. Even recent self-supervised studies addressing two or all three tasks simultaneously tend to…

Sketch recognition allows natural and efficient interaction in pen-based interfaces. A key obstacle to building accurate sketch recognizers has been the difficulty of creating large amounts of annotated training data. Several authors have…

Natural Language Understanding (NLU) models are typically trained in a supervised learning framework. In the case of intent classification, the predicted labels are predefined and based on the designed annotation schema while the labelling…

Document intelligence automates the extraction of information from documents and supports many business applications. Recent self-supervised learning methods on large-scale unlabeled document datasets have opened up promising directions…

Conventional multimedia annotation/retrieval systems such as Normalized Continuous Relevance Model (NormCRM) [16] require a fully labeled training data for a good performance. Active Learning, by determining an order for labeling the…

Deep neural network models trained on large labeled datasets are the state-of-the-art in a large variety of computer vision tasks. In many applications, however, labeled data is expensive to obtain or requires a time consuming manual…

Representation-based retrieval models, so-called bi-encoders, estimate the relevance of a document to a query by calculating the similarity of their respective embeddings. Current state-of-the-art bi-encoders are trained using an expensive…

Active learning (AL) aims to enable training high performance classifiers with low annotation cost by predicting which subset of unlabelled instances would be most beneficial to label. The importance of AL has motivated extensive research,…

Learning interpretable and disentangled representations is a crucial yet challenging task in representation learning. In this work, we focus on semi-supervised disentanglement learning and extend work by Locatello et al. (2019) by…

Speaker representation learning is crucial for voice recognition systems, with recent advances in self-supervised approaches reducing dependency on labeled data. Current two-stage iterative frameworks, while effective, suffer from…

Recent works in self-supervised learning have shown impressive results on single-object images, but they struggle to perform well on complex multi-object images as evidenced by their poor visual grounding. To demonstrate this concretely, we…

Using deep learning, we now have the ability to create exceptionally good semantic segmentation systems; however, collecting the prerequisite pixel-wise annotations for training images remains expensive and time-consuming. Therefore, it…

The i.i.d. assumption is a useful idealization that underpins many successful approaches to supervised machine learning. However, its violation can lead to models that learn to exploit spurious correlations in the training data, rendering…