相关论文: Train and You'll Miss It: Interactive Model Iterat…

Weak supervision (WS) is an alternative to the traditional supervised learning to address the need for ground truth. Data programming is a practical WS approach that allows programmatic labeling data samples using labeling functions (LFs)…

Weak supervision (WS) frameworks are a popular way to bypass hand-labeling large datasets for training data-hungry models. These approaches synthesize multiple noisy but cheaply-acquired estimates of labels into a set of high-quality…

In this paper, we present a statistical-mechanical analysis of deep learning. We elucidate some of the essential components of deep learning---pre-training by unsupervised learning and fine tuning by supervised learning. We formulate the…

Recent progress in speech recognition has relied on models trained on vast amounts of labeled data. However, classroom Automatic Speech Recognition (ASR) faces the real-world challenge of abundant weak transcripts paired with only a small…

Training deep networks with noisy labels leads to poor generalization and degraded accuracy due to overfitting to label noise. Existing approaches for learning with noisy labels often rely on the availability of a clean subset of data. By…

Instruction tuning of language models has demonstrated the ability to enhance model generalization to unseen tasks via in-context learning using a few examples. However, typical supervised learning still requires a plethora of downstream…

Currently, machine learning techniques have seen significant success across various applications. Most of these techniques rely on supervision from human-generated labels or a mixture of noisy and imprecise labels from multiple sources.…

Labeling training data is a key bottleneck in the modern machine learning pipeline. Recent weak supervision approaches combine labels from multiple noisy sources by estimating their accuracies without access to ground truth labels; however,…

Deep learning usually achieves the best results with complete supervision. In the case of semantic segmentation, this means that large amounts of pixelwise annotations are required to learn accurate models. In this paper, we show that we…

One paradigm for learning from few labeled examples while making best use of a large amount of unlabeled data is unsupervised pretraining followed by supervised fine-tuning. Although this paradigm uses unlabeled data in a task-agnostic way,…

In many real-world scenarios, labeled data for a specific machine learning task is costly to obtain. Semi-supervised training methods make use of abundantly available unlabeled data and a smaller number of labeled examples. We propose a new…

Labeling training data has become one of the major roadblocks to using machine learning. Among various weak supervision paradigms, programmatic weak supervision (PWS) has achieved remarkable success in easing the manual labeling bottleneck…

A recent trend in deep learning algorithms has been towards training large scale models, having high parameter count and trained on big dataset. However, robustness of such large scale models towards real-world settings is still a…

We present a technique to improve the transferability of deep representations learned on small labeled datasets by introducing self-supervised tasks as auxiliary loss functions. While recent approaches for self-supervised learning have…

Large amounts of labeled training data are one of the main contributors to the great success that deep models have achieved in the past. Label acquisition for tasks other than benchmarks can pose a challenge due to requirements of both…

Within medical imaging, manual curation of sufficient well-labeled samples is cost, time and scale-prohibitive. To improve the representativeness of the training dataset, for the first time, we present an approach to utilize large amounts…

Semi-Supervised Learning (SSL) has been proved to be an effective way to leverage both labeled and unlabeled data at the same time. Recent semi-supervised approaches focus on deep neural networks and have achieved promising results on…

We propose a method, called Label Embedding Network, which can learn label representation (label embedding) during the training process of deep networks. With the proposed method, the label embedding is adaptively and automatically learned…

The success of deep learning has been due, in no small part, to the availability of large annotated datasets. Thus, a major bottleneck in current learning pipelines is the time-consuming human annotation of data. In scenarios where such…

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…