Image captioning systems have recently improved dramatically, but they still tend to produce captions that are insensitive to the communicative goals that captions should meet. To address this, we propose Issue-Sensitive Image Captioning (ISIC). In ISIC, a captioning system is given a target image and an issue, which is a set of images partitioned in a way that specifies what information is relevant. The goal of the captioner is to produce a caption that resolves this issue. To model this task, we use an extension of the Rational Speech Acts model of pragmatic language use. Our extension is built on top of state-of-the-art pretrained neural image captioners and explicitly reasons about issues in our sense. We establish experimentally that these models generate captions that are both highly descriptive and issue-sensitive, and we show how ISIC can complement and enrich the related task of Visual Question Answering.
In this paper, we propose a linguistically-motivated query expansion framework that recognizes and en-codes significant query constituents that characterize query intent in order to improve retrieval performance. Concepts-of-Interest are recognized as the core concepts that represent the gist of the search goal whilst the remaining query constituents which serve to specify the search goal and complete the query structure are classified as descriptive, relational or structural. Acknowledging the need to form semantically-associated base pairs for the purpose of extracting related potential expansion concepts, an algorithm which capitalizes on syntactical dependencies to capture relationships between adjacent and non-adjacent query concepts is proposed. Lastly, a robust weighting scheme that duly emphasizes the importance of query constituents based on their linguistic role within the expanded query is presented. We demonstrate improvements in retrieval effectiveness in terms of increased mean average precision (MAP) garnered by the proposed linguistic-based query expansion framework through experimentation on the TREC ad hoc test collections.
Chest X-Ray (CXR) images are commonly used for clinical screening and diagnosis. Automatically writing reports for these images can considerably lighten the workload of radiologists for summarizing descriptive findings and conclusive impressions. The complex structures between and within sections of the reports pose a great challenge to the automatic report generation. Specifically, the section Impression is a diagnostic summarization over the section Findings; and the appearance of normality dominates each section over that of abnormality. Existing studies rarely explore and consider this fundamental structure information. In this work, we propose a novel framework that exploits the structure information between and within report sections for generating CXR imaging reports. First, we propose a two-stage strategy that explicitly models the relationship between Findings and Impression. Second, we design a novel cooperative multi-agent system that implicitly captures the imbalanced distribution between abnormality and normality. Experiments on two CXR report datasets show that our method achieves state-of-the-art performance in terms of various evaluation metrics. Our results expose that the proposed approach is able to generate high-quality medical reports through integrating the structure information.
We achieved a new milestone in the difficult task of enabling agents to learn about their environment autonomously. Our neuro-symbolic architecture is trained end-to-end to produce a succinct and effective discrete state transition model from images alone. Our target representation (the Planning Domain Definition Language) is already in a form that off-the-shelf solvers can consume, and opens the door to the rich array of modern heuristic search capabilities. We demonstrate how the sophisticated innate prior we place on the learning process significantly reduces the complexity of the learned representation, and reveals a connection to the graph-theoretic notion of "cube-like graphs", thus opening the door to a deeper understanding of the ideal properties for learned symbolic representations. We show that the powerful domain-independent heuristics allow our system to solve visual 15-Puzzle instances which are beyond the reach of blind search, without resorting to the Reinforcement Learning approach that requires a huge amount of training on the domain-dependent reward information.
We develop a new method to find the number of volatility regimes in a nonstationary financial time series by applying unsupervised learning to its volatility structure. We use change point detection to partition a time series into locally stationary segments and then compute a distance matrix between segment distributions. The segments are clustered into a learned number of discrete volatility regimes via an optimization routine. Using this framework, we determine a volatility clustering structure for financial indices, large-cap equities, exchange-traded funds and currency pairs. Our method overcomes the rigid assumptions necessary to implement many parametric regime-switching models, while effectively distilling a time series into several characteristic behaviours. Our results provide significant simplification of these time series and a strong descriptive analysis of prior behaviours of volatility. Finally, we create and validate a dynamic trading strategy that learns the optimal match between the current distribution of a time series and its past regimes, thereby making online risk-avoidance decisions in the present.
Question Generation (QG) is fundamentally a simple syntactic transformation; however, many aspects of semantics influence what questions are good to form. We implement this observation by developing SynQG, a set of transparent syntactic rules leveraging universal dependencies, shallow semantic parsing, lexical resources, and custom rules which transform declarative sentences into question-answer pairs. We utilize PropBank argument descriptions and VerbNet state predicates to incorporate shallow semantic content, which helps generate questions of a descriptive nature and produce inferential and semantically richer questions than existing systems. In order to improve syntactic fluency and eliminate grammatically incorrect questions, we employ back-translation over the output of these syntactic rules. A set of crowd-sourced evaluations shows that our system can generate a larger number of highly grammatical and relevant questions than previous QG systems and that back-translation drastically improves grammaticality at a slight cost of generating irrelevant questions.
Radiographic images offer an alternative method for the rapid screening and monitoring of Coronavirus Disease 2019 (COVID-19) patients. This approach is limited by the shortage of radiology experts who can provide a timely interpretation of these images. Motivated by this challenge, our paper proposes a novel learning architecture, called Detail-Oriented Capsule Networks (DECAPS), for the automatic diagnosis of COVID-19 from Computed Tomography (CT) scans. Our network combines the strength of Capsule Networks with several architecture improvements meant to boost classification accuracies. First, DECAPS uses an Inverted Dynamic Routing mechanism which increases model stability by preventing the passage of information from non-descriptive regions. Second, DECAPS employs a Peekaboo training procedure which uses a two-stage patch crop and drop strategy to encourage the network to generate activation maps for every target concept. The network then uses the activation maps to focus on regions of interest and combines both coarse and fine-grained representations of the data. Finally, we use a data augmentation method based on conditional generative adversarial networks to deal with the issue of data scarcity. Our model achieves 84.3% precision, 91.5% recall, and 96.1% area under the ROC curve, significantly outperforming state-of-the-art methods. We compare the performance of the DECAPS model with three experienced, well-trained thoracic radiologists and show that the architecture significantly outperforms them. While further studies on larger datasets are required to confirm this finding, our results imply that architectures like DECAPS can be used to assist radiologists in the CT scan mediated diagnosis of COVID-19.
Despite recent breakthroughs in reinforcement learning (RL) and imitation learning (IL), existing algorithms fail to generalize beyond the training environments. In reality, humans can adapt to new tasks quickly by leveraging prior knowledge about the world such as language descriptions. To facilitate the research on language-guided agents with domain adaption, we propose a novel zero-shot compositional policy learning task, where the environments are characterized as a composition of different attributes. Since there are no public environments supporting this study, we introduce a new research platform BabyAI++ in which the dynamics of environments are disentangled from visual appearance. At each episode, BabyAI++ provides varied vision-dynamics combinations along with corresponding descriptive texts. To evaluate the adaption capability of learned agents, a set of vision-dynamics pairings are held-out for testing on BabyAI++. Unsurprisingly, we find that current language-guided RL/IL techniques overfit to the training environments and suffer from a huge performance drop when facing unseen combinations. In response, we propose a multi-modal fusion method with an attention mechanism to perform visual language-grounding. Extensive experiments show strong evidence that language grounding is able to improve the generalization of agents across environments with varied dynamics.
Image inpainting task requires filling the corrupted image with contents coherent with the context. This research field has achieved promising progress by using neural image inpainting methods. Nevertheless, there is still a critical challenge in guessing the missed content with only the context pixels. The goal of this paper is to fill the semantic information in corrupted images according to the provided descriptive text. Unique from existing text-guided image generation works, the inpainting models are required to compare the semantic content of the given text and the remaining part of the image, then find out the semantic content that should be filled for missing part. To fulfill such a task, we propose a novel inpainting model named Text-Guided Dual Attention Inpainting Network (TDANet). Firstly, a dual multimodal attention mechanism is designed to extract the explicit semantic information about the corrupted regions, which is done by comparing the descriptive text and complementary image areas through reciprocal attention. Secondly, an image-text matching loss is applied to maximize the semantic similarity of the generated image and the text. Experiments are conducted on two open datasets. Results show that the proposed TDANet model reaches new state-of-the-art on both quantitative and qualitative measures. Result analysis suggests that the generated images are consistent with the guidance text, enabling the generation of various results by providing different descriptions. Codes are available at https://github.com/idealwhite/TDANet
Image search can be tackled using deep features from pre-trained Convolutional Neural Networks (CNN). The feature map from the last convolutional layer of a CNN encodes descriptive information from which a discriminative global descriptor can be obtained. We propose a new representation of co-occurrences from deep convolutional features to extract additional relevant information from this last convolutional layer. Combining this co-occurrence map with the feature map, we achieve an improved image representation. We present two different methods to get the co-occurrence representation, the first one based on direct aggregation of activations, and the second one, based on a trainable co-occurrence representation. The image descriptors derived from our methodology improve the performance in very well-known image retrieval datasets as we prove in the experiments.
Convolutional neural networks (CNN) are capable of learning robust representation with different regularization methods and activations as convolutional layers are spatially correlated. Based on this property, a large variety of regional dropout strategies have been proposed, such as Cutout, DropBlock, CutMix, etc. These methods aim to promote the network to generalize better by partially occluding the discriminative parts of objects. However, all of them perform this operation randomly, without capturing the most important region(s) within an object. In this paper, we propose Attentive CutMix, a naturally enhanced augmentation strategy based on CutMix. In each training iteration, we choose the most descriptive regions based on the intermediate attention maps from a feature extractor, which enables searching for the most discriminative parts in an image. Our proposed method is simple yet effective, easy to implement and can boost the baseline significantly. Extensive experiments on CIFAR-10/100, ImageNet datasets with various CNN architectures (in a unified setting) demonstrate the effectiveness of our proposed method, which consistently outperforms the baseline CutMix and other methods by a significant margin.
In multicriteria decision aiding (MCDA), the Choquet integral has been used as an aggregation operator to deal with the case of interacting decision criteria. While the application of the Choquet integral for ranking problems have been receiving most of the attention, this paper rather focuses on multicriteria sorting problems (MCSP). In the Choquet integral context, a practical problem that arises is related to the elicitation of parameters known as the Choquet capacities. We address the problem of Choquet capacity identification for MCSP by applying the Stochastic Acceptability Multicriteri Analysis (SMAA), proposing the SMAA-S-Choquet method. The proposed method is also able to model uncertain data that may be present in both decision matrix and limiting profiles, the latter a parameter associated with the sorting problematic. We also introduce two new descriptive measures in order to conduct reverse analysis regarding the capacities: the Scenario Acceptability Index and the Scenario Central Capacity vector.
Autonomous vehicles (AVs) must share space with pedestrians, both in carriageway cases such as cars at pedestrian crossings and off-carriageway cases such as delivery vehicles navigating through crowds on pedestrianized high-streets. Unlike static obstacles, pedestrians are active agents with complex, interactive motions. Planning AV actions in the presence of pedestrians thus requires modelling of their probable future behaviour as well as detecting and tracking them. This narrative review article is Part II of a pair, together surveying the current technology stack involved in this process, organising recent research into a hierarchical taxonomy ranging from low-level image detection to high-level psychological models, from the perspective of an AV designer. This self-contained Part II covers the higher levels of this stack, consisting of models of pedestrian behaviour, from prediction of individual pedestrians' likely destinations and paths, to game-theoretic models of interactions between pedestrians and autonomous vehicles. This survey clearly shows that, although there are good models for optimal walking behaviour, high-level psychological and social modelling of pedestrian behaviour still remains an open research question that requires many conceptual issues to be clarified. Early work has been done on descriptive and qualitative models of behaviour, but much work is still needed to translate them into quantitative algorithms for practical AV control.
Situation AWareness (SAW) is essential for many mission critical applications. However, SAW is very challenging when trying to immediately identify objects of interest or zoom in on suspicious activities from thousands of video frames. This work aims at developing a queryable system to instantly select interesting content. While face recognition technology is mature, in many scenarios like public safety monitoring, the features of objects of interest may be much more complicated than face features. In addition, human operators may not be always able to provide a descriptive, simple, and accurate query. Actually, it is more often that there are only rough, general descriptions of certain suspicious objects or accidents. This paper proposes an Interactive Video Surveillance as an Edge service (I-ViSE) based on unsupervised feature queries. Adopting unsupervised methods that do not reveal any private information, the I-ViSE scheme utilizes general features of a human body and color of clothes. An I-ViSE prototype is built following the edge-fog computing paradigm and the experimental results verified the I-ViSE scheme meets the design goal of scene recognition in less than two seconds.
Summarizing data samples by quantitative measures has a long history, with descriptive statistics being a case in point. However, as natural language processing methods flourish, there are still insufficient characteristic metrics to describe a collection of texts in terms of the words, sentences, or paragraphs they comprise. In this work, we propose metrics of diversity, density, and homogeneity that quantitatively measure the dispersion, sparsity, and uniformity of a text collection. We conduct a series of simulations to verify that each metric holds desired properties and resonates with human intuitions. Experiments on real-world datasets demonstrate that the proposed characteristic metrics are highly correlated with text classification performance of a renowned model, BERT, which could inspire future applications.
With the recent booming of open-source packages for scientific computing, power system simulation is being revisited to reduce the programming efforts for modeling and analysis. Existing open-source tools require manual efforts to develop code for numerical equations and sparse Jacobians. Such work would become repeated, tedious and error-prone when a researcher needs to implement complex models with a large number of equations. This paper proposes a two-layer hybrid library consisted of a symbolic layer for descriptive modeling and a numeric layer for vector-based numerical computation. The open-source library allows to implement differential-algebraic equation (DAE)-based models with descriptive equation strings, which will be transparently generated into robust and fast numerical simulation code and high-quality documentation. Thus, complex models and systems can be easily prototyped and simulated. These two layers are decoupled so that the symbolic layer is case-independent, and existing numerical programs can be reused. Implementation details in indexing, equation evaluation, and Jacobian evaluation are discussed. Case studies present a) implementation of turbine governor model TGOV1, b) the power flow calculation for MATPOWER test systems, c) the validation against commercial software using Kundur's two-area system with GENROU, EXDC2 and TGOV1 models, and d) the full eigenvalue analysis for Kundur's system.
This paper further extends RIn-Close_CVC, a biclustering algorithm capable of performing an efficient, complete, correct and non-redundant enumeration of maximal biclusters with constant values on columns in numerical datasets. By avoiding a priori partitioning and itemization of the dataset, RIn-Close_CVC implements an online partitioning, which is demonstrated here to guide to more informative biclustering results. The improved algorithm is called RIn-Close_CVC3, keeps those attractive properties of RIn-Close_CVC, as formally proved here, and is characterized by: a drastic reduction in memory usage; a consistent gain in runtime; additional ability to handle datasets with missing values; and additional ability to operate with attributes characterized by distinct distributions or even mixed data types. The experimental results include synthetic and real-world datasets used to perform scalability and sensitivity analyses. As a practical case study, a parsimonious set of relevant and interpretable mixed-attribute-type rules is obtained in the context of supervised descriptive pattern mining.
Interactive search sessions often contain multiple queries, where the user submits a reformulated version of the previous query in response to the original results. We aim to enhance the query recommendation experience for a commercial image search engine. Our proposed methodology incorporates current state-of-the-art practices from relevant literature -- the use of generation-based sequence-to-sequence models that capture session context, and a multitask architecture that simultaneously optimizes the ranking of results. We extend this setup by driving the learning of such a model with captions of clicked images as the target, instead of using the subsequent query within the session. Since these captions tend to be linguistically richer, the reformulation mechanism can be seen as assistance to construct more descriptive queries. In addition, via the use of a pairwise loss for the secondary ranking task, we show that the generated reformulations are more diverse.
In this paper, we propose a generalizable method that systematically combines data driven MCMC samplingand inference using rule-based context knowledge for data abstraction. In particular, we demonstrate the usefulness of our method in the scenario of building abstract semantic maps for indoor environments. The product of our system is a parametric abstract model of the perceived environment that not only accurately represents the geometry of the environment but also provides valuable abstract information which benefits high-level robotic applications. Based on predefined abstract terms,such as type and relation, we define task-specific context knowledge as descriptive rules in Markov Logic Networks. The corresponding inference results are used to construct a priordistribution that aims to add reasonable constraints to the solution space of semantic maps. In addition, by applying a semantically annotated sensor model, we explicitly use context information to interpret the sensor data. Experiments on real world data show promising results and thus confirm the usefulness of our system.
An open question in the Deep Learning community is why neural networks trained with Gradient Descent generalize well on real datasets even though they are capable of fitting random data. We propose an approach to answering this question based on a hypothesis about the dynamics of gradient descent that we call Coherent Gradients: Gradients from similar examples are similar and so the overall gradient is stronger in certain directions where these reinforce each other. Thus changes to the network parameters during training are biased towards those that (locally) simultaneously benefit many examples when such similarity exists. We support this hypothesis with heuristic arguments and perturbative experiments and outline how this can explain several common empirical observations about Deep Learning. Furthermore, our analysis is not just descriptive, but prescriptive. It suggests a natural modification to gradient descent that can greatly reduce overfitting.