User-defined keyword spotting is a task to detect new spoken terms defined by users. This can be viewed as a few-shot learning problem since it is unreasonable for users to define their desired keywords by providing many examples. To solve this problem, previous works try to incorporate self-supervised learning models or apply meta-learning algorithms. But it is unclear whether self-supervised learning and meta-learning are complementary and which combination of the two types of approaches is most effective for few-shot keyword discovery. In this work, we systematically study these questions by utilizing various self-supervised learning models and combining them with a wide variety of meta-learning algorithms. Our result shows that HuBERT combined with Matching network achieves the best result and is robust to the changes of few-shot examples.

Incorporating external knowledge sources effectively in conversations is a longstanding problem in open-domain dialogue research. The existing literature on open-domain knowledge selection is limited and makes certain brittle assumptions on knowledge sources to simplify the overall task (Dinan et al., 2019), such as the existence of a single relevant knowledge sentence per context. In this work, we evaluate the existing state of open-domain conversation knowledge selection, showing where the existing methodologies regarding data and evaluation are flawed. We then improve on them by proposing a new framework for collecting relevant knowledge, and create an augmented dataset based on the Wizard of Wikipedia (WOW) corpus, which we call WOW++. WOW++ averages 8 relevant knowledge sentences per dialogue context, embracing the inherent ambiguity of open-domain dialogue knowledge selection. We then benchmark various knowledge ranking algorithms on this augmented dataset with both intrinsic evaluation and extrinsic measures of response quality, showing that neural rerankers that use WOW++ can outperform rankers trained on standard datasets.

We present SLOT-V, a novel supervised learning framework that learns observer models (human preferences) from robot motion trajectories in a legibility context. Legibility measures how easily a (human) observer can infer the robot's goal from a robot motion trajectory. When generating such trajectories, existing planners often rely on an observer model that estimates the quality of trajectory candidates. These observer models are frequently hand-crafted or, occasionally, learned from demonstrations. Here, we propose to learn them in a supervised manner using the same data format that is frequently used during the evaluation of aforementioned approaches. We then demonstrate the generality of SLOT-V using a Franka Emika in a simulated manipulation environment. For this, we show that it can learn to closely predict various hand-crafted observer models, i.e., that SLOT-V's hypothesis space encompasses existing handcrafted models. Next, we showcase SLOT-V's ability to generalize by showing that a trained model continues to perform well in environments with unseen goal configurations and/or goal counts. Finally, we benchmark SLOT-V's sample efficiency (and performance) against an existing IRL approach and show that SLOT-V learns better observer models with less data. Combined, these results suggest that SLOT-V can learn viable observer models. Better observer models imply more legible trajectories, which may - in turn - lead to better and more transparent human-robot interaction.

Detecting anomalies over real-world datasets remains a challenging task. Data annotation is an intensive human labor problem, particularly in sequential datasets, where the start and end time of anomalies are not known. As a result, data collected from sequential real-world processes can be largely unlabeled or contain inaccurate labels. These characteristics challenge the application of anomaly detection techniques based on supervised learning. In contrast, Multiple Instance Learning (MIL) has been shown effective on problems with incomplete knowledge of labels in the training dataset, mainly due to the notion of bags. While largely under-leveraged for anomaly detection, MIL provides an appealing formulation for anomaly detection over real-world datasets, and it is the primary contribution of this paper. In this paper, we propose an MIL-based formulation and various algorithmic instantiations of this framework based on different design decisions for key components of the framework. We evaluate the resulting algorithms over four datasets that capture different physical processes along different modalities. The experimental evaluation draws out several observations. The MIL-based formulation performs no worse than single instance learning on easy to moderate datasets and outperforms single-instance learning on more challenging datasets. Altogether, the results show that the framework generalizes well over diverse datasets resulting from different real-world application domains.

This article was published as a part of the Data Science Blogathon. Working on a task involving the interpretation of chest X-ray medical images and no labeled data at your disposal? Researchers from Harvard Medical School and Stanford University have devised an artificial intelligence diagnostic tool that can detect diseases from natural language descriptions of chest X-rays without needing the labeled data. This is a major step toward significant advancement in clinical AI design because most existing models require vast amounts of annotated data before that data can be fed into a model for training. This research paper will look at the proposed method in further detail.

Abstract: Self-supervised learning (SSL) has achieved remarkable performance on various medical imaging tasks by dint of priors from massive unlabeled data. However, for a specific downstream task, there is still a lack of an instruction book on how to select suitable pretext tasks and implementation details. Then, we conduct extensive experiments to explore four significant issues in SSL for medical imaging, including (1) the effect of self-supervised pretraining on imbalanced datasets, (2) network architectures, (3) the applicability of upstream tasks to downstream tasks and (4) the stacking effect of SSL and commonly used policies for deep learning, including data resampling and augmentation. Based on the experimental results, potential guidelines are presented for self-supervised pretraining in medical imaging. Abstract: Lyrics recognition is an important task in music processing.

Learning to produce contact-rich, dynamic behaviors from raw sensory data has been a longstanding challenge in robotics. Prominent approaches primarily focus on using visual or tactile sensing, where unfortunately one fails to capture high-frequency interaction, while the other can be too delicate for large-scale data collection. In this work, we propose a data-centric approach to dynamic manipulation that uses an often ignored source of information: sound. We first collect a dataset of 25k interaction-sound pairs across five dynamic tasks using commodity contact microphones. Then, given this data, we leverage self-supervised learning to accelerate behavior prediction from sound. Our experiments indicate that this self-supervised 'pretraining' is crucial to achieving high performance, with a 34.5% lower MSE than plain supervised learning and a 54.3% lower MSE over visual training. Importantly, we find that when asked to generate desired sound profiles, online rollouts of our models on a UR10 robot can produce dynamic behavior that achieves an average of 11.5% improvement over supervised learning on audio similarity metrics.

We present three large-scale experiments on binary text matching classification task both in Chinese and English to evaluate the effectiveness and generalizability of random text perturbations as a data augmentation approach for NLP. It is found that the augmentation can bring both negative and positive effects to the test set performance of three neural classification models, depending on whether the models train on enough original training examples. This remains true no matter whether five random text editing operations, used to augment text, are applied together or separately. Our study demonstrates with strong implication that the effectiveness of random text perturbations is task specific and not generally positive.

As humans, we perceive the three-dimensional structure of the world around us with apparent ease. Think of how vivid the three-dimensional percept is when you look at a vase of flowers sitting on the table next to you. You can tell the shape and translucency of each petal through the subtle patterns of light and shading that play across its surface and effortlessly segment each flower from the background of the scene (Figure 1.1). Looking at a framed group por- trait, you can easily count (and name) all of the people in the picture and even guess at their emotions from their facial appearance. Perceptual psychologists have spent decades trying to understand how the visual system works and, even though they can devise optical illusions1 to tease apart some of its principles (Figure 1.3), a complete solution to this puzzle remains elusive (Marr 1982; Palmer 1999; Livingstone 2008).

Semi-supervised learning has the potential to improve the data-efficiency of training data-hungry deep neural networks, which is especially important for medical image analysis tasks where labeled data is scarce. In this work, we present a simple semi-supervised learning method for lesion segmentation tasks based on the ideas of cut-paste augmentation and consistency regularization. By exploiting the mask information available in the labeled data, we synthesize partially labeled samples from the unlabeled images so that the usual supervised learning objective (e.g., binary cross entropy) can be applied. Additionally, we introduce a background consistency term to regularize the training on the unlabeled background regions of the synthetic images. We empirically verify the effectiveness of the proposed method on two public lesion segmentation datasets, including an eye fundus photograph dataset and a brain CT scan dataset. The experiment results indicate that our method achieves consistent and superior performance over other self-training and consistency-based methods without introducing sophisticated network components.