Representation learning aims to discover individual salient features of a domain in a compact and descriptive form that strongly identifies the unique characteristics of a given sample respective to its domain. Existing works in visual style representation literature have tried to disentangle style from content during training explicitly. A complete separation between these has yet to be fully achieved. Our paper aims to learn a representation of visual artistic style more strongly disentangled from the semantic content depicted in an image. We use Neural Style Transfer (NST) to measure and drive the learning signal and achieve state-of-the-art representation learning on explicitly disentangled metrics. We show that strongly addressing the disentanglement of style and content leads to large gains in style-specific metrics, encoding far less semantic information and achieving state-of-the-art accuracy in downstream multimodal applications.
Sentence-level relation extraction aims to identify the relation between two entities for a given sentence. The existing works mostly focus on obtaining a better entity representation and adopting a multi-label classifier for relation extraction. A major limitation of these works is that they ignore background relational knowledge and the interrelation between entity types and candidate relations. In this work, we propose a new paradigm, Contrastive Learning with Descriptive Relation Prompts(CTL-DRP), to jointly consider entity information, relational knowledge and entity type restrictions. In particular, we introduce an improved entity marker and descriptive relation prompts when generating contextual embedding, and utilize contrastive learning to rank the restricted candidate relations. The CTL-DRP obtains a competitive F1-score of 76.7% on TACRED. Furthermore, the new presented paradigm achieves F1-scores of 85.8% and 91.6% on TACREV and Re-TACRED respectively, which are both the state-of-the-art performance.
There has been concern about ideological basis and possible discrimination in text generated by Large Language Models (LLMs). We test possible value biases in ChatGPT using a psychological value theory. We designed a simple experiment in which we used a number of different probes derived from the Schwartz basic value theory (items from the revised Portrait Value Questionnaire, the value type definitions, value names). We prompted ChatGPT via the OpenAI API repeatedly to generate text and then analyzed the generated corpus for value content with a theory-driven value dictionary using a bag of words approach. Overall, we found little evidence of explicit value bias. The results showed sufficient construct and discriminant validity for the generated text in line with the theoretical predictions of the psychological model, which suggests that the value content was carried through into the outputs with high fidelity. We saw some merging of socially oriented values, which may suggest that these values are less clearly differentiated at a linguistic level or alternatively, this mixing may reflect underlying universal human motivations. We outline some possible applications of our findings for both applications of ChatGPT for corporate usage and policy making as well as future research avenues. We also highlight possible implications of this relatively high-fidelity replication of motivational content using a linguistic model for the theorizing about human values.
Continuous convolution has recently gained prominence due to its ability to handle irregularly sampled data and model long-term dependency. Also, the promising experimental results of using large convolutional kernels have catalyzed the development of continuous convolution since they can construct large kernels very efficiently. Leveraging neural networks, more specifically multilayer perceptrons (MLPs), is by far the most prevalent approach to implementing continuous convolution. However, there are a few drawbacks, such as high computational costs, complex hyperparameter tuning, and limited descriptive power of filters. This paper suggests an alternative approach to building a continuous convolution without neural networks, resulting in more computationally efficient and improved performance. We present self-moving point representations where weight parameters freely move, and interpolation schemes are used to implement continuous functions. When applied to construct convolutional kernels, the experimental results have shown improved performance with drop-in replacement in the existing frameworks. Due to its lightweight structure, we are first to demonstrate the effectiveness of continuous convolution in a large-scale setting, e.g., ImageNet, presenting the improvements over the prior arts. Our code is available on https://github.com/sangnekim/SMPConv
Large scale vision and language models can achieve impressive zero-shot recognition performance by mapping class specific text queries to image content. Two distinct challenges that remain however, are high sensitivity to the choice of handcrafted class names that define queries, and the difficulty of adaptation to new, smaller datasets. Towards addressing these problems, we propose to leverage available data to learn, for each class, an optimal word embedding as a function of the visual content. By learning new word embeddings on an otherwise frozen model, we are able to retain zero-shot capabilities for new classes, easily adapt models to new datasets, and adjust potentially erroneous, non-descriptive or ambiguous class names. We show that our solution can easily be integrated in image classification and object detection pipelines, yields significant performance gains in multiple scenarios and provides insights into model biases and labelling errors.
Neural captioners are typically trained to mimic human-generated references without optimizing for any specific communication goal, leading to problems such as the generation of vague captions. In this paper, we show that fine-tuning an out-of-the-box neural captioner with a self-supervised discriminative communication objective helps to recover a plain, visually descriptive language that is more informative about image contents. Given a target image, the system must learn to produce a description that enables an out-of-the-box text-conditioned image retriever to identify such image among a set of candidates. We experiment with the popular ClipCap captioner, also replicating the main results with BLIP. In terms of similarity to ground-truth human descriptions, the captions emerging from discriminative finetuning lag slightly behind those generated by the non-finetuned model, when the latter is trained and tested on the same caption dataset. However, when the model is used without further tuning to generate captions for out-of-domain datasets, our discriminatively-finetuned captioner generates descriptions that resemble human references more than those produced by the same captioner without finetuning. We further show that, on the Conceptual Captions dataset, discriminatively finetuned captions are more helpful than either vanilla ClipCap captions or ground-truth captions for human annotators tasked with an image discrimination task.
Digital Twins bring several benefits for planning, operation, and maintenance of remote offshore assets. In this work, we explain the digital twin concept and the capability level scale in the context of wind energy. Furthermore, we demonstrate a standalone digital twin, a descriptive digital twin, and a prescriptive digital twin of an operational floating offshore wind turbine. The standalone digital twin consists of the virtual representation of the wind turbine and its operating environment. While at this level the digital twin does not evolve with the physical turbine, it can be used during the planning-, design-, and construction phases. At the next level, the descriptive digital twin is built upon the standalone digital twin by enhancing the latter with real data from the turbine. All the data is visualized in virtual reality for informed decision-making. Besides being used for data bundling and visualization, the descriptive digital twin forms the basis for diagnostic, predictive, prescriptive, and autonomous tools. A predictive digital twin is created through the use of weather forecasts, neural networks, and transfer learning. Finally, digital twin technology is discussed in a much wider context of ocean engineering.
In the context of Epidemic Intelligence, many Event-Based Surveillance (EBS) systems have been proposed in the literature to promote the early identification and characterization of potential health threats from online sources of any nature. Each EBS system has its own surveillance definitions and priorities, therefore this makes the task of selecting the most appropriate EBS system for a given situation a challenge for end-users. In this work, we propose a new evaluation framework to address this issue. It first transforms the raw input epidemiological event data into a set of normalized events with multi-granularity, then conducts a descriptive retrospective analysis based on four evaluation objectives: spatial, temporal, thematic and source analysis. We illustrate its relevance by applying it to an Avian Influenza dataset collected by a selection of EBS systems, and show how our framework allows identifying their strengths and drawbacks in terms of epidemic surveillance.
The study was designed to determine the entrepreneurial capability and engagement of persons with disabilities toward a framework for inclusive entrepreneurship. The researcher used descriptive and correlational approaches through purposive random sampling. The sample came from the City of General Trias and the Municipality of Rosario, registered under their respective Persons with Disabilities Affairs Offices (PDAO). The findings indicated that the respondents are from the working class, are primarily female, are mostly single, have college degrees, live in a medium-sized home, and earn the bare minimum. Furthermore, PWDs' perceived capability level in entrepreneurship was somehow capable, and the majority of engagement level responses were somehow engaged. Considerably, age and civil status have significant relationships with most of the variables under study. Finally, the perceived challenges of PWDs' respondents noted the following: lack of financial capacity, access to credit and other financial institutions, absence of business information, absence of access to data, lack of competent business skills, lack of family support, and lack of personal motivation. As a result, the author proposed a framework that emphasizes interaction and cooperation between national and local government units in the formulation of policies promoting inclusive entrepreneurship for people with disabilities.
We propose an approach for adapting the DeBERTa model for electronic health record (EHR) tasks using domain adaptation. We pretrain a small DeBERTa model on a dataset consisting of MIMIC-III discharge summaries, clinical notes, radiology reports, and PubMed abstracts. We compare this model's performance with a DeBERTa model pre-trained on clinical texts from our institutional EHR (MeDeBERTa) and an XGBoost model. We evaluate performance on three benchmark tasks for emergency department outcomes using the MIMIC-IV-ED dataset. We preprocess the data to convert it into text format and generate four versions of the original datasets to compare data processing and data inclusion. The results show that our proposed approach outperforms the alternative models on two of three tasks (p<0.001) and matches performance on the third task, with the use of descriptive columns improving performance over the original column names.
Automated diagnosis prediction from medical images is a valuable resource to support clinical decision-making. However, such systems usually need to be trained on large amounts of annotated data, which often is scarce in the medical domain. Zero-shot methods address this challenge by allowing a flexible adaption to new settings with different clinical findings without relying on labeled data. Further, to integrate automated diagnosis in the clinical workflow, methods should be transparent and explainable, increasing medical professionals' trust and facilitating correctness verification. In this work, we introduce Xplainer, a novel framework for explainable zero-shot diagnosis in the clinical setting. Xplainer adapts the classification-by-description approach of contrastive vision-language models to the multi-label medical diagnosis task. Specifically, instead of directly predicting a diagnosis, we prompt the model to classify the existence of descriptive observations, which a radiologist would look for on an X-Ray scan, and use the descriptor probabilities to estimate the likelihood of a diagnosis. Our model is explainable by design, as the final diagnosis prediction is directly based on the prediction of the underlying descriptors. We evaluate Xplainer on two chest X-ray datasets, CheXpert and ChestX-ray14, and demonstrate its effectiveness in improving the performance and explainability of zero-shot diagnosis. Our results suggest that Xplainer provides a more detailed understanding of the decision-making process and can be a valuable tool for clinical diagnosis.
Recent successes in image synthesis are powered by large-scale diffusion models. However, most methods are currently limited to either text- or image-conditioned generation for synthesizing an entire image, texture transfer or inserting objects into a user-specified region. In contrast, in this work we focus on synthesizing complex interactions (ie, an articulated hand) with a given object. Given an RGB image of an object, we aim to hallucinate plausible images of a human hand interacting with it. We propose a two-step generative approach: a LayoutNet that samples an articulation-agnostic hand-object-interaction layout, and a ContentNet that synthesizes images of a hand grasping the object given the predicted layout. Both are built on top of a large-scale pretrained diffusion model to make use of its latent representation. Compared to baselines, the proposed method is shown to generalize better to novel objects and perform surprisingly well on out-of-distribution in-the-wild scenes of portable-sized objects. The resulting system allows us to predict descriptive affordance information, such as hand articulation and approaching orientation. Project page: https://judyye.github.io/affordiffusion-www
Quantum Machine Learning has the potential to improve traditional machine learning methods and overcome some of the main limitations imposed by the classical computing paradigm. However, the practical advantages of using quantum resources to solve pattern recognition tasks are still to be demonstrated. This work proposes a universal, efficient framework that can reproduce the output of a plethora of classical supervised machine learning algorithms exploiting quantum computation's advantages. The proposed framework is named Multiple Aggregator Quantum Algorithm (MAQA) due to its capability to combine multiple and diverse functions to solve typical supervised learning problems. In its general formulation, MAQA can be potentially adopted as the quantum counterpart of all those models falling into the scheme of aggregation of multiple functions, such as ensemble algorithms and neural networks. From a computational point of view, the proposed framework allows generating an exponentially large number of different transformations of the input at the cost of increasing the depth of the corresponding quantum circuit linearly. Thus, MAQA produces a model with substantial descriptive power to broaden the horizon of possible applications of quantum machine learning with a computational advantage over classical methods. As a second meaningful addition, we discuss the adoption of the proposed framework as hybrid quantum-classical and fault-tolerant quantum algorithm.
In neural decoding research, one of the most intriguing topics is the reconstruction of perceived natural images based on fMRI signals. Previous studies have succeeded in re-creating different aspects of the visuals, such as low-level properties (shape, texture, layout) or high-level features (category of objects, descriptive semantics of scenes) but have typically failed to reconstruct these properties together for complex scene images. Generative AI has recently made a leap forward with latent diffusion models capable of generating high-complexity images. Here, we investigate how to take advantage of this innovative technology for brain decoding. We present a two-stage scene reconstruction framework called ``Brain-Diffuser''. In the first stage, starting from fMRI signals, we reconstruct images that capture low-level properties and overall layout using a VDVAE (Very Deep Variational Autoencoder) model. In the second stage, we use the image-to-image framework of a latent diffusion model (Versatile Diffusion) conditioned on predicted multimodal (text and visual) features, to generate final reconstructed images. On the publicly available Natural Scenes Dataset benchmark, our method outperforms previous models both qualitatively and quantitatively. When applied to synthetic fMRI patterns generated from individual ROI (region-of-interest) masks, our trained model creates compelling ``ROI-optimal'' scenes consistent with neuroscientific knowledge. Thus, the proposed methodology can have an impact on both applied (e.g. brain-computer interface) and fundamental neuroscience.
We analyse the power of graph neural networks (GNNs) in terms of Boolean circuit complexity and descriptive complexity. We prove that the graph queries that can be computed by a polynomial-size bounded-depth family of GNNs are exactly those definable in the guarded fragment GFO+C of first-order logic with counting and with built-in relations. This puts GNNs in the circuit complexity class (non-uniform) $\text{TC}^0$. Remarkably, the GNN families may use arbitrary real weights and a wide class of activation functions that includes the standard ReLU, logistic "sigmoid", and hyperbolic tangent functions. If the GNNs are allowed to use random initialisation and global readout (both standard features of GNNs widely used in practice), they can compute exactly the same queries as bounded depth Boolean circuits with threshold gates, that is, exactly the queries in $\text{TC}^0$. Moreover, we show that queries computable by a single GNN with piecewise linear activations and rational weights are definable in GFO+C without built-in relations. Therefore, they are contained in uniform $\text{TC}^0$.
Computational simulations are a popular method for testing hypotheses about the emergence of communication. This kind of research is performed in a variety of traditions including language evolution, developmental psychology, cognitive science, machine learning, robotics, etc. The motivations for the models are different, but the operationalizations and methods used are often similar. We identify the assumptions and explanatory targets of several most representative models and summarise the known results. We claim that some of the assumptions -- such as portraying meaning in terms of mapping, focusing on the descriptive function of communication, modelling signals with amodal tokens -- may hinder the success of modelling. Relaxing these assumptions and foregrounding the interactions of embodied and situated agents allows one to systematise the multiplicity of pressures under which symbolic systems evolve. In line with this perspective, we sketch the road towards modelling the emergence of meaningful symbolic communication, where symbols are simultaneously grounded in action and perception and form an abstract system.
Radiology narrative reports often describe characteristics of a patient's disease, including its location, size, and shape. Motivated by the recent success of multimodal learning, we hypothesized that this descriptive text could guide medical image analysis algorithms. We proposed a novel vision-language model, ConTEXTual Net, for the task of pneumothorax segmentation on chest radiographs. ConTEXTual Net utilizes language features extracted from corresponding free-form radiology reports using a pre-trained language model. Cross-attention modules are designed to combine the intermediate output of each vision encoder layer and the text embeddings generated by the language model. ConTEXTual Net was trained on the CANDID-PTX dataset consisting of 3,196 positive cases of pneumothorax with segmentation annotations from 6 different physicians as well as clinical radiology reports. Using cross-validation, ConTEXTual Net achieved a Dice score of 0.716$\pm$0.016, which was similar to the degree of inter-reader variability (0.712$\pm$0.044) computed on a subset of the data. It outperformed both vision-only models (ResNet50 U-Net: 0.677$\pm$0.015 and GLoRIA: 0.686$\pm$0.014) and a competing vision-language model (LAVT: 0.706$\pm$0.009). Ablation studies confirmed that it was the text information that led to the performance gains. Additionally, we show that certain augmentation methods degraded ConTEXTual Net's segmentation performance by breaking the image-text concordance. We also evaluated the effects of using different language models and activation functions in the cross-attention module, highlighting the efficacy of our chosen architectural design.
We propose a novel type of map for visual navigation, a renderable neural radiance map (RNR-Map), which is designed to contain the overall visual information of a 3D environment. The RNR-Map has a grid form and consists of latent codes at each pixel. These latent codes are embedded from image observations, and can be converted to the neural radiance field which enables image rendering given a camera pose. The recorded latent codes implicitly contain visual information about the environment, which makes the RNR-Map visually descriptive. This visual information in RNR-Map can be a useful guideline for visual localization and navigation. We develop localization and navigation frameworks that can effectively utilize the RNR-Map. We evaluate the proposed frameworks on camera tracking, visual localization, and image-goal navigation. Experimental results show that the RNR-Map-based localization framework can find the target location based on a single query image with fast speed and competitive accuracy compared to other baselines. Also, this localization framework is robust to environmental changes, and even finds the most visually similar places when a query image from a different environment is given. The proposed navigation framework outperforms the existing image-goal navigation methods in difficult scenarios, under odometry and actuation noises. The navigation framework shows 65.7% success rate in curved scenarios of the NRNS dataset, which is an improvement of 18.6% over the current state-of-the-art. Project page: https://rllab-snu.github.io/projects/RNR-Map/
Preparing exact and comprehensive word meaning explanations is one of the key steps in the process of monolingual dictionary writing. In standard methodology, the explanations need an expert lexicographer who spends a substantial amount of time checking the consistency between the descriptive text and corpus evidence. In the following text, we present a new tool that derives explanations automatically based on collective information from very large corpora, particularly on word sketches. We also propose a quantitative evaluation of the constructed explanations, concentrating on explanations of nouns. The methodology is to a certain extent language independent; however, the presented verification is limited to Czech and English. We show that the presented approach allows to create explanations that contain data useful for understanding the word meaning in approximately 90% of cases. However, in many cases, the result requires post-editing to remove redundant information.
We address the issue of detecting changes of models that lie behind a data stream. The model refers to an integer-valued structural information such as the number of free parameters in a parametric model. Specifically we are concerned with the problem of how we can detect signs of model changes earlier than they are actualized. To this end, we employ {\em continuous model selection} on the basis of the notion of {\em descriptive dimensionality}~(Ddim). It is a real-valued model dimensionality, which is designed for quantifying the model dimensionality in the model transition period. Continuous model selection is to determine the real-valued model dimensionality in terms of Ddim from a given data. We propose a novel methodology for detecting signs of model changes by tracking the rise-up of Ddim in a data stream. We apply this methodology to detecting signs of changes of the number of clusters in a Gaussian mixture model and those of the order in an auto regression model. With synthetic and real data sets, we empirically demonstrate its effectiveness by showing that it is able to visualize well how rapidly model dimensionality moves in the transition period and to raise early warning signals of model changes earlier than they are detected with existing methods.