Related papers: (Un)likelihood Training for Interpretable Embeddin…

Unsupervised meta-learning aims to learn feature representations from unsupervised datasets that can transfer to downstream tasks with limited labeled data. In this paper, we propose a novel approach to unsupervised meta-learning that…

Zero Shot Learning (ZSL) enables a learning model to classify instances of an unseen class during training. While most research in ZSL focuses on single-label classification, few studies have been done in multi-label ZSL, where an instance…

Vision-language pre-training has recently gained popularity as it allows learning rich feature representations using large-scale data sources. This paradigm has quickly made its way into the medical image analysis community. In particular,…

Deep neural networks often struggle to learn robust representations in the presence of dataset biases, leading to suboptimal generalization on unbiased datasets. This limitation arises because the models heavily depend on peripheral and…

Cross-modal data matching refers to retrieval of data from one modality, when given a query from another modality. In general, supervised algorithms achieve better retrieval performance compared to their unsupervised counterpart, as they…

To overcome the imbalanced multimodal learning problem, where models prefer the training of specific modalities, existing methods propose to control the training of uni-modal encoders from different perspectives, taking the inter-modal…

Training deep feature hierarchies to solve supervised learning tasks has achieved state of the art performance on many problems in computer vision. However, a principled way in which to train such hierarchies in the unsupervised setting has…

Variational Autoencoders for multimodal data hold promise for many tasks in data analysis, such as representation learning, conditional generation, and imputation. Current architectures either share the encoder output, decoder input, or…

Multimodal learning assumes all modality combinations of interest are available during training to learn cross-modal correspondences. In this paper, we challenge this modality-complete assumption for multimodal learning and instead strive…

Video Anomaly Detection (VAD) has been extensively studied under the settings of One-Class Classification (OCC) and Weakly-Supervised learning (WS), which however both require laborious human-annotated normal/abnormal labels. In this paper,…

Universal lesion detection has great value for clinical practice as it aims to detect various types of lesions in multiple organs on medical images. Deep learning methods have shown promising results, but demanding large volumes of…

Recent advancements in language representation learning primarily emphasize language modeling for deriving meaningful representations, often neglecting style-specific considerations. This study addresses this gap by creating generic,…

Mimicry is a fundamental learning mechanism in humans, enabling individuals to learn new tasks by observing and imitating experts. However, applying this ability to robots presents significant challenges due to the inherent differences…

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…

Multimodal learning from document data has achieved great success lately as it allows to pre-train semantically meaningful features as a prior into a learnable downstream task. In this paper, we approach the document classification problem…

We present a method to learn a joint multimodal representation space that enables recognition of unseen activities in videos. We first compare the effect of placing various constraints on the embedding space using paired text and video…

Labeling and maintaining a commercial sound effects library is a time-consuming task exacerbated by databases that continually grow in size and undergo taxonomy updates. Moreover, sound search and taxonomy creation are complicated by…

Meta-learning, or learning-to-learn, seeks to design algorithms that can utilize previous experience to rapidly learn new skills or adapt to new environments. Representation learning -- a key tool for performing meta-learning -- learns a…

Pretrained encoders for mathematical texts have achieved significant improvements on various tasks such as formula classification and information retrieval. Yet they remain limited in representing and capturing student strategies for entire…

Implicit neural networks are a general class of learning models that replace the layers in traditional feedforward models with implicit algebraic equations. Compared to traditional learning models, implicit networks offer competitive…