Related papers: Nearly Zero-Shot Learning for Semantic Decoding in…
Zero-Shot Learning (ZSL) aims at classifying unlabeled objects by leveraging auxiliary knowledge, such as semantic representations. A limitation of previous approaches is that only intrinsic properties of objects, e.g. their visual…
Zero-shot learning methods rely on fixed visual and semantic embeddings, extracted from independent vision and language models, both pre-trained for other large-scale tasks. This is a weakness of current zero-shot learning frameworks as…
Background and objective: Employing deep learning models in critical domains such as medical imaging poses challenges associated with the limited availability of training data. We present a strategy for improving the performance and…
Few-Shot Classification(FSC) aims to generalize from base classes to novel classes given very limited labeled samples, which is an important step on the path toward human-like machine learning. State-of-the-art solutions involve learning to…
We propose a model to tackle classification tasks in the presence of very little training data. To this aim, we approximate the notion of exact match with a theoretically sound mechanism that computes a probability of matching in the input…
Traditionally, training neural networks to perform semantic segmentation required expensive human-made annotations. But more recently, advances in the field of unsupervised learning have made significant progress on this issue and towards…
The field of machine learning has recently made significant progress in reducing the requirements for labelled training data when building new models. These `cheaper' learning techniques hold significant potential for the social sciences,…
We present an end-to-end deep learning approach to denoising speech signals by processing the raw waveform directly. Given input audio containing speech corrupted by an additive background signal, the system aims to produce a processed…
State-of-the-art audio classification often employs a zero-shot approach, which involves comparing audio embeddings with embeddings from text describing the respective audio class. These embeddings are usually generated by neural networks…
Zero-shot learning (ZSL) aims to classify objects that are not observed or seen during training. It relies on class semantic description to transfer knowledge from the seen classes to the unseen classes. Existing methods of obtaining class…
Multilingual neural machine translation systems learn to map sentences of different languages into a common representation space. Intuitively, with a growing number of seen languages the encoder sentence representation grows more flexible…
Thanks to the impressive progress of large-scale vision-language pretraining, recent recognition models can classify arbitrary objects in a zero-shot and open-set manner, with a surprisingly high accuracy. However, translating this success…
This paper tackles the problem of zero-shot sign language recognition (ZSSLR), where the goal is to leverage models learned over the seen sign classes to recognize the instances of unseen sign classes. In this context, readily available…
We study few-shot learning in natural language domains. Compared to many existing works that apply either metric-based or optimization-based meta-learning to image domain with low inter-task variance, we consider a more realistic setting,…
With the advent of strong pre-trained natural language processing models like BERT, DeBERTa, MiniLM, T5, the data requirement for industries to fine-tune these models to their niche use cases has drastically reduced (typically to a few…
Fine-grained few-shot recognition often suffers from the problem of training data scarcity for novel categories.The network tends to overfit and does not generalize well to unseen classes due to insufficient training data. Many methods have…
When pre-trained on large unsupervised textual corpora, language models are able to store and retrieve factual knowledge to some extent, making it possible to use them directly for zero-shot cloze-style question answering. However, storing…
Few-shot learning is a challenging problem since only a few examples are provided to recognize a new class. Several recent studies exploit additional semantic information, e.g. text embeddings of class names, to address the issue of rare…
Conventional approaches to text classification typically assume the existence of a fixed set of predefined labels to which a given text can be classified. However, in real-world applications, there exists an infinite label space for…
Zero-shot learning (ZSL) models rely on learning a joint embedding space where both textual/semantic description of object classes and visual representation of object images can be projected to for nearest neighbour search. Despite the…