Related papers: Active Dictionary Learning in Sparse Representatio…

In recent years, speech-based self-supervised learning (SSL) has made significant progress in various tasks, including automatic speech recognition (ASR). An ASR model with decent performance can be realized by fine-tuning an SSL model with…

Dictionary learning is the task of determining a data-dependent transform that yields a sparse representation of some observed data. The dictionary learning problem is non-convex, and usually solved via computationally complex iterative…

Active learning (AL) is a training paradigm for selecting unlabeled samples for annotation to improve model performance on a test set, which is useful when only a limited number of samples can be annotated. These algorithms often work by…

Recent works using artificial neural networks based on word distributed representation greatly boost the performance of various natural language learning tasks, especially question answering. Though, they also carry along with some…

Dictionary learning for sparse representations has been successful in many reconstruction tasks. Simplicial learning is an adaptation of dictionary learning, where subspaces become clipped and acquire arbitrary offsets, taking the form of…

We introduce supervised contrastive active learning (SCAL) and propose efficient query strategies in active learning based on the feature similarity (featuresim) and principal component analysis based feature-reconstruction error (fre) to…

Large pre-trained transformers have revolutionized artificial intelligence across various domains, and fine-tuning remains the dominant approach for adapting these models to downstream tasks due to the cost of training from scratch.…

Term-based sparse representations dominate the first-stage text retrieval in industrial applications, due to its advantage in efficiency, interpretability, and exact term matching. In this paper, we study the problem of transferring the…

In this paper, we suggest a novel data-driven approach to active learning (AL). The key idea is to train a regressor that predicts the expected error reduction for a candidate sample in a particular learning state. By formulating the query…

We propose a novel structured discriminative block-diagonal dictionary learning method, referred to as scalable Locality-Constrained Projective Dictionary Learning (LC-PDL), for efficient representation and classification. To improve the…

In the realm of deep learning-based recommendation systems, the increasing computational demands, driven by the growing number of users and items, pose a significant challenge to practical deployment. This challenge is primarily twofold:…

Active learning (AL) attempts to maximize the performance gain of the model by marking the fewest samples. Deep learning (DL) is greedy for data and requires a large amount of data supply to optimize massive parameters, so that the model…

In training speech recognition systems, labeling audio clips can be expensive, and not all data is equally valuable. Active learning aims to label only the most informative samples to reduce cost. For speech recognition, confidence scores…

In this paper, it is proved that dictionary learning and sparse representation is invariant to a linear transformation. It subsumes the special case of transforming/projecting the data into a discriminative space. This is important because…

Active learning is a machine learning paradigm that aims to improve the performance of a model by strategically selecting and querying unlabeled data. One effective selection strategy is to base it on the model's predictive uncertainty,…

In recent years, deep dictionary learning (DDL)has attracted a great amount of attention due to its effectiveness for representation learning and visual recognition.~However, most existing methods focus on unsupervised deep dictionary…

Active learning aims to address the paucity of labeled data by finding the most informative samples. However, when applying to semantic segmentation, existing methods ignore the segmentation difficulty of different semantic areas, which…

Ordering the selection of training data using active learning can lead to improvements in learning efficiently from smaller corpora. We present an exploration of active learning approaches applied to three grounded language problems of…

Active learning aims to obtain a classifier of high accuracy by using fewer label requests in comparison to passive learning by selecting effective queries. Many active learning methods have been developed in the past two decades, which…

Neural sequence-to-sequence automatic speech recognition (ASR) systems are in principle open vocabulary systems, when using appropriate modeling units. In practice, however, they often fail to recognize words not seen during training, e.g.,…