Related papers: Selecting which Dense Retriever to use for Zero-Sh…
Modern computing and communication technologies can make data collection procedures very efficient. However, our ability to analyze large data sets and/or to extract information out from them is hard-pressed to keep up with our capacities…
Feature selection, an effective technique for dimensionality reduction, plays an important role in many machine learning systems. Supervised knowledge can significantly improve the performance. However, faced with the rapid growth of newly…
How can we reuse existing knowledge, in the form of available datasets, when solving a new and apparently unrelated target task from a set of unlabeled data? In this work we make a first contribution to answer this question in the context…
In open-domain question answering, a model receives a text question as input and searches for the correct answer using a large evidence corpus. The retrieval step is especially difficult as typical evidence corpora have \textit{millions} of…
Deep learning has significantly improved the precision of instance segmentation with abundant labeled data. However, in many areas like medical and manufacturing, collecting sufficient data is extremely hard and labeling this data requires…
Large-scale datasets are essential for the success of deep learning in image retrieval. However, manual assessment errors and semi-supervised annotation techniques can lead to label noise even in popular datasets. As previous works…
Large pre-trained models can dramatically reduce the amount of task-specific data required to solve a problem, but they often fail to capture domain-specific nuances out of the box. The Web likely contains the information necessary to excel…
This work stems from an observed limitation of text encoders: embeddings may not be able to recognize fine-grained entities or events within encoded semantics, resulting in failed retrieval even in simple cases. To examine such behaviors,…
With the explosive 3D data growth, the urgency of utilizing zero-shot learning to facilitate data labeling becomes evident. Recently, methods transferring language or language-image pre-training models like Contrastive Language-Image…
Over the last few years, contextualized pre-trained transformer models such as BERT have provided substantial improvements on information retrieval tasks. Recent approaches based on pre-trained transformer models such as BERT, fine-tune…
Few-shot dense retrieval (DR) aims to effectively generalize to novel search scenarios by learning a few samples. Despite its importance, there is little study on specialized datasets and standardized evaluation protocols. As a result,…
In Information Retrieval, and more generally in Natural Language Processing, adapting models to specific domains is conducted through fine-tuning. Despite the successes achieved by this method and its versatility, the need for human-curated…
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…
One of important areas of machine learning research is zero-shot learning. It is applied when properly labeled training data set is not available. A number of zero-shot algorithms have been proposed and experimented with. However, none of…
Dense retrievers play a vital role in accessing external and specialized knowledge to augment language models (LMs). Training dense retrievers typically requires annotated query-document pairs, which are costly to create and scarce in…
In the field of visual scene understanding, deep neural networks have made impressive advancements in various core tasks like segmentation, tracking, and detection. However, most approaches operate on the close-set assumption, meaning that…
The development of advanced 3D sensors has enabled many objects to be captured in the wild at a large scale, and a 3D object recognition system may therefore encounter many objects for which the system has received no training. Zero-Shot…
In recent years, deep discriminative models have achieved extraordinary performance on supervised learning tasks, significantly outperforming their generative counterparts. However, their success relies on the presence of a large amount of…
Deep learning has gained broad interest in remote sensing image scene classification thanks to the effectiveness of deep neural networks in extracting the semantics from complex data. However, deep networks require large amounts of training…
This paper presents a method of zero-shot learning (ZSL) which poses ZSL as the missing data problem, rather than the missing label problem. Specifically, most existing ZSL methods focus on learning mapping functions from the image feature…