The Visual Question Answering (VQA) task utilizes both visual image and language analysis to answer a textual question with respect to an image. It has been a popular research topic with an increasing number of real-world applications in the last decade. This paper describes our recent research of AliceMind-MMU (ALIbaba's Collection of Encoder-decoders from Machine IntelligeNce lab of Damo academy - MultiMedia Understanding) that obtains similar or even slightly better results than human being does on VQA. This is achieved by systematically improving the VQA pipeline including: (1) pre-training with comprehensive visual and textual feature representation; (2) effective cross-modal interaction with learning to attend; and (3) A novel knowledge mining framework with specialized expert modules for the complex VQA task. Treating different types of visual questions with corresponding expertise needed plays an important role in boosting the performance of our VQA architecture up to the human level. An extensive set of experiments and analysis are conducted to demonstrate the effectiveness of the new research work.
A drastic rise in potentially life-threatening misinformation has been a by-product of the COVID-19 pandemic. Computational support to identify false information within the massive body of data on the topic is crucial to prevent harm. Researchers proposed many methods for flagging online misinformation related to COVID-19. However, these methods predominantly target specific content types (e.g., news) or platforms (e.g., Twitter). The methods' capabilities to generalize were largely unclear so far. We evaluate fifteen Transformer-based models on five COVID-19 misinformation datasets that include social media posts, news articles, and scientific papers to fill this gap. We show tokenizers and models tailored to COVID-19 data do not provide a significant advantage over general-purpose ones. Our study provides a realistic assessment of models for detecting COVID-19 misinformation. We expect that evaluating a broad spectrum of datasets and models will benefit future research in developing misinformation detection systems.
The problem of rapid and automated detection of distinct market regimes is a topic of great interest to financial mathematicians and practitioners alike. In this paper, we outline an unsupervised learning algorithm for clustering financial time-series into a suitable number of temporal segments (market regimes). As a special case of the above, we develop a robust algorithm that automates the process of classifying market regimes. The method is robust in the sense that it does not depend on modelling assumptions of the underlying time series as our experiments with real datasets show. This method -- dubbed the Wasserstein $k$-means algorithm -- frames such a problem as one on the space of probability measures with finite $p^\text{th}$ moment, in terms of the $p$-Wasserstein distance between (empirical) distributions. We compare our WK-means approach with a more traditional clustering algorithms by studying the so-called maximum mean discrepancy scores between, and within clusters. In both cases it is shown that the WK-means algorithm vastly outperforms all considered competitor approaches. We demonstrate the performance of all approaches both in a controlled environment on synthetic data, and on real data.
Robust localization in dense urban scenarios using a low-cost sensor setup and sparse HD maps is highly relevant for the current advances in autonomous driving, but remains a challenging topic in research. We present a novel monocular localization approach based on a sliding-window pose graph that leverages predicted uncertainties for increased precision and robustness against challenging scenarios and per frame failures. To this end, we propose an efficient multi-task uncertainty-aware perception module, which covers semantic segmentation, as well as bounding box detection, to enable the localization of vehicles in sparse maps, containing only lane borders and traffic lights. Further, we design differentiable cost maps that are directly generated from the estimated uncertainties. This opens up the possibility to minimize the reprojection loss of amorphous map elements in an association free and uncertainty-aware manner. Extensive evaluation on the Lyft 5 dataset shows that, despite the sparsity of the map, our approach enables robust and accurate 6D localization in challenging urban scenarios
A crucial difference between single- and multi-document summarization is how salient content manifests itself in the document(s). While such content may appear at the beginning of a single document, essential information is frequently reiterated in a set of documents related to a particular topic, resulting in an endorsement effect that increases information salience. In this paper, we model the cross-document endorsement effect and its utilization in multiple document summarization. Our method generates a synopsis from each document, which serves as an endorser to identify salient content from other documents. Strongly endorsed text segments are used to enrich a neural encoder-decoder model to consolidate them into an abstractive summary. The method has a great potential to learn from fewer examples to identify salient content, which alleviates the need for costly retraining when the set of documents is dynamically adjusted. Through extensive experiments on benchmark multi-document summarization datasets, we demonstrate the effectiveness of our proposed method over strong published baselines. Finally, we shed light on future research directions and discuss broader challenges of this task using a case study.
Expert systems have been used to enable computers to make recommendations and decisions. This paper presents the use of a machine learning trained expert system (MLES) for phishing site detection and fake news detection. Both topics share a similar goal: to design a rule-fact network that allows a computer to make explainable decisions like domain experts in each respective area. The phishing website detection study uses a MLES to detect potential phishing websites by analyzing site properties (like URL length and expiration time). The fake news detection study uses a MLES rule-fact network to gauge news story truthfulness based on factors such as emotion, the speaker's political affiliation status, and job. The two studies use different MLES network implementations, which are presented and compared herein. The fake news study utilized a more linear design while the phishing project utilized a more complex connection structure. Both networks' inputs are based on commonly available data sets.
Behaviour selection has been an active research topic for robotics, in particular in the field of human-robot interaction. For a robot to interact effectively and autonomously with humans, the coupling between techniques for human activity recognition, based on sensing information, and robot behaviour selection, based on decision-making mechanisms, is of paramount importance. However, most approaches to date consist of deterministic associations between the recognised activities and the robot behaviours, neglecting the uncertainty inherent to sequential predictions in real-time applications. In this paper, we address this gap by presenting a neurorobotics approach based on computational models that resemble neurophysiological aspects of living beings. This neurorobotics approach was compared to a non-bioinspired, heuristics-based approach. To evaluate both approaches, a robot simulation is developed, in which a mobile robot has to accomplish tasks according to the activity being performed by the inhabitant of an intelligent home. The outcomes of each approach were evaluated according to the number of correct outcomes provided by the robot. Results revealed that the neurorobotics approach is advantageous, especially considering the computational models based on more complex animals.
Sound event localization and detection (SELD) is an emerging research topic that aims to unify the tasks of sound event detection and direction-of-arrival estimation. As a result, SELD inherits the challenges of both tasks, such as noise, reverberation, interference, polyphony, and non-stationarity of sound sources. Furthermore, SELD often faces an additional challenge of assigning correct correspondences between the detected sound classes and directions of arrival to multiple overlapping sound events. Previous studies have shown that unknown interferences in reverberant environments often cause major degradation in the performance of SELD systems. To further understand the challenges of the SELD task, we performed a detailed error analysis on two of our SELD systems, which both ranked second in the team category of DCASE SELD Challenge, one in 2020 and one in 2021. Experimental results indicate polyphony as the main challenge in SELD, due to the difficulty in detecting all sound events of interest. In addition, the SELD systems tend to make fewer errors for the polyphonic scenario that is dominant in the training set.
The use of deep neural networks (DNNs) in safety-critical applications like mobile health and autonomous driving is challenging due to numerous model-inherent shortcomings. These shortcomings are diverse and range from a lack of generalization over insufficient interpretability to problems with malicious inputs. Cyber-physical systems employing DNNs are therefore likely to suffer from safety concerns. In recent years, a zoo of state-of-the-art techniques aiming to address these safety concerns has emerged. This work provides a structured and broad overview of them. We first identify categories of insufficiencies to then describe research activities aiming at their detection, quantification, or mitigation. Our paper addresses both machine learning experts and safety engineers: The former ones might profit from the broad range of machine learning topics covered and discussions on limitations of recent methods. The latter ones might gain insights into the specifics of modern ML methods. We moreover hope that our contribution fuels discussions on desiderata for ML systems and strategies on how to propel existing approaches accordingly.
Machine translation (MT) models used in industries with constantly changing topics, such as translation or news agencies, need to adapt to new data to maintain their performance over time. Our aim is to teach a pre-trained MT model to translate previously unseen words accurately, based on very few examples. We propose (i) an experimental setup allowing us to simulate novel vocabulary appearing in human-submitted translations, and (ii) corresponding evaluation metrics to compare our approaches. We extend a data augmentation approach using a pre-trained language model to create training examples with similar contexts for novel words. We compare different fine-tuning and data augmentation approaches and show that adaptation on the scale of one to five examples is possible. Combining data augmentation with randomly selected training sentences leads to the highest BLEU score and accuracy improvements. Impressively, with only 1 to 5 examples, our model reports better accuracy scores than a reference system trained with on average 313 parallel examples.
Add to Chrome
Add to Firefox