Related papers: Learning Aligned Cross-Modal Representation for Ge…
Zero-shot cross-domain sequential recommendation (ZCDSR) enables predictions in unseen domains without additional training or fine-tuning, addressing the limitations of traditional models in sparse data environments. Recent advancements in…
Zero-shot learning (ZSL) enables the recognition of novel classes by leveraging semantic knowledge transfer from known to unknown categories. This knowledge, typically encapsulated in attribute descriptions, aids in identifying…
Understanding how different AI models encode the same high-level concepts, such as objects or attributes, remains challenging because each model typically produces its own isolated representation. Existing interpretability methods like…
We present a deep generative model for learning to predict classes not seen at training time. Unlike most existing methods for this problem, that represent each class as a point (via a semantic embedding), we represent each seen/unseen…
Overfitting in RL has become one of the main obstacles to applications in reinforcement learning(RL). Existing methods do not provide explicit semantic constrain for the feature extractor, hindering the agent from learning a unified…
General-purpose AI models, particularly those designed for text and vision, demonstrate impressive versatility across a wide range of deep-learning tasks. However, they often underperform in specialised domains like medical imaging, where…
Unlike conventional zero-shot classification, zero-shot semantic segmentation predicts a class label at the pixel level instead of the image level. When solving zero-shot semantic segmentation problems, the need for pixel-level prediction…
Generalized zero-shot learning (GZSL) is a challenging class of vision and knowledge transfer problems in which both seen and unseen classes appear during testing. Existing GZSL approaches either suffer from semantic loss and discard…
Deep learning has shown significant potential in diagnosing neurodegenerative diseases from MRI data. However, most existing methods rely heavily on large volumes of labeled data and often yield representations that lack interpretability.…
The advances in attention-based encoder-decoder (AED) networks have brought great progress to end-to-end (E2E) automatic speech recognition (ASR). One way to further improve the performance of AED-based E2E ASR is to introduce an extra text…
3D medical images such as computed tomography are widely used in clinical practice, offering a great potential for automatic diagnosis. Supervised learning-based approaches have achieved significant progress but rely heavily on extensive…
This paper presents a cross-modal learning framework that exploits complementary information from depth and grayscale images for robust navigation. We introduce a Cross-Modal Wasserstein Autoencoder that learns shared latent representations…
Zero-Shot Learning (ZSL) is a classification task where we do not have even a single training labeled example from a set of unseen classes. Instead, we only have prior information (or description) about seen and unseen classes, often in the…
Gleason grading from histopathology images is essential for accurate prostate cancer (PCa) diagnosis. Since such images are obtained after invasive tissue resection quick diagnosis is challenging under the existing paradigm. We propose a…
The Linear Representation Hypothesis asserts that the embeddings learned by neural networks can be understood as linear combinations of features corresponding to high-level concepts. Based on this ansatz, sparse autoencoders (SAEs) have…
In Computer Vision, Zero-Shot Learning (ZSL) aims at classifying unseen classes -- classes for which no matching training image exists. Most of ZSL works learn a cross-modal mapping between images and class labels for seen classes. However,…
Remarkable progress in zero-shot learning (ZSL) has been achieved using generative models. However, existing generative ZSL methods merely generate (imagine) the visual features from scratch guided by the strong class semantic vectors…
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…
Generalized zero-shot learning (GZSL) is the problem of learning a classifier where some classes have samples and others are learned from side information, like semantic attributes or text description, in a zero-shot learning fashion (ZSL).…
One of the recent developments in deep learning is generalized zero-shot learning (GZSL), which aims to recognize objects from both seen and unseen classes, when only the labeled examples from seen classes are provided. Over the past couple…