Related papers: The Omniglot challenge: a 3-year progress report
Multimodal meta-learning is a recent problem that extends conventional few-shot meta-learning by generalizing its setup to diverse multimodal task distributions. This setup makes a step towards mimicking how humans make use of a diverse set…
Most recent progress in natural language understanding (NLU) has been driven, in part, by benchmarks such as GLUE, SuperGLUE, SQuAD, etc. In fact, many NLU models have now matched or exceeded "human-level" performance on many tasks in these…
Natural language processing (NLP) tasks (e.g. question-answering in English) benefit from knowledge of other tasks (e.g. named entity recognition in English) and knowledge of other languages (e.g. question-answering in Spanish). Such shared…
The iterated learning model simulates the transmission of language from generation to generation in order to explore how the constraints imposed by language transmission facilitate the emergence of language structure. Despite each modelled…
Cloze-style reading comprehension has been a popular task for measuring the progress of natural language understanding in recent years. In this paper, we design a novel multi-perspective framework, which can be seen as the joint training of…
The vast proliferation of sensor devices and Internet of Things enables the applications of sensor-based activity recognition. However, there exist substantial challenges that could influence the performance of the recognition system in…
Recent developments in pre-trained neural language modeling have led to leaps in accuracy on commonsense question-answering benchmarks. However, there is increasing concern that models overfit to specific tasks, without learning to utilize…
Analyzing instructional interactions between an instructor and a learner who are co-present in the same physical space is a critical problem for educational support and skill transfer. Yet such face-to-face instructional scenes have not…
The ability to quickly learn a new task with minimal instruction - known as few-shot learning - is a central aspect of intelligent agents. Classical few-shot benchmarks make use of few-shot samples from a single modality, but such samples…
Multi-task learning (MTL) has received considerable attention, and numerous deep learning applications benefit from MTL with multiple objectives. However, constructing multiple related tasks is difficult, and sometimes only a single task is…
Despite extensive research spanning several decades, class imbalance is still considered a profound difficulty for both machine learning and deep learning models. While data oversampling is the foremost technique to address this issue,…
One-shot face recognition measures the ability to identify persons with only seeing them at one glance, and is a hallmark of human visual intelligence. It is challenging for conventional machine learning approaches to mimic this way, since…
The ability to quickly recognize and learn new visual concepts from limited samples enables humans to swiftly adapt to new environments. This ability is enabled by semantic associations of novel concepts with those that have already been…
Language-based object detection is a promising direction towards building a natural interface to describe objects in images that goes far beyond plain category names. While recent methods show great progress in that direction, proper…
We introduce one-shot texture segmentation: the task of segmenting an input image containing multiple textures given a patch of a reference texture. This task is designed to turn the problem of texture-based perceptual grouping into an…
Despite recent advances, the remaining bottlenecks in deep generative models are necessity of extensive training and difficulties with generalization from small number of training examples. We develop a new generative model called…
Few-shot Learning aims to learn and distinguish new categories with a very limited number of available images, presenting a significant challenge in the realm of deep learning. Recent researchers have sought to leverage the additional…
Large-scale datasets are foundational for research and development in natural language processing. However, current approaches face three key challenges: (1) reliance on ambiguously licensed sources restricting use, sharing, and derivative…
The HuggingFace Datasets Hub hosts thousands of datasets, offering exciting opportunities for language model training and evaluation. However, datasets for a specific task type often have different schemas, making harmonization challenging.…
In 2022, with the release of ChatGPT, large-scale language models gained widespread attention. ChatGPT not only surpassed previous models in terms of parameters and the scale of its pretraining corpus but also achieved revolutionary…