PyTorchKR Papers

최신 논문

총 399편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2110.09599공식 코드 · Papers with Code

Label-Descriptive Patterns and Their Application to Characterizing Classification Errors

State-of-the-art deep learning methods achieve human-like performance on many tasks, but make errors nevertheless. Characterizing these errors in easily interpretable terms gives insight into whether a classifier is prone to making systematic errors, but also gives a way to act and improve the classifier. We propose to discover those feature-value combinations (i.e., patterns) that strongly correlate with correct resp. erroneous predictions to obtain a global and interpretable description for arbitrary classifiers. We show this is an instance of the more general label description problem, which we formulate in terms of the Minimum Description Length principle. To discover a good pattern set, we develop the efficient Premise algorithm. Through an extensive set of experiments we show it performs very well in practice on both synthetic and real-world data. Unlike existing solutions, it ably recovers ground truth patterns, even on highly imbalanced data over many features. Through two case studies on Visual Question Answering and Named Entity Recognition, we confirm that Premise gives clear and actionable insight into the systematic errors made by modern NLP classifiers.

arXiv:2110.08059공식 코드 · Papers with Code

FlexConv: Continuous Kernel Convolutions with Differentiable Kernel Sizes

When designing Convolutional Neural Networks (CNNs), one must select the size\break of the convolutional kernels before training. Recent works show CNNs benefit from different kernel sizes at different layers, but exploring all possible combinations is unfeasible in practice. A more efficient approach is to learn the kernel size during training. However, existing works that learn the kernel size have a limited bandwidth. These approaches scale kernels by dilation, and thus the detail they can describe is limited. In this work, we propose FlexConv, a novel convolutional operation with which high bandwidth convolutional kernels of learnable kernel size can be learned at a fixed parameter cost. FlexNets model long-term dependencies without the use of pooling, achieve state-of-the-art performance on several sequential datasets, outperform recent works with learned kernel sizes, and are competitive with much deeper ResNets on image benchmark datasets. Additionally, FlexNets can be deployed at higher resolutions than those seen during training. To avoid aliasing, we propose a novel kernel parameterization with which the frequency of the kernels can be analytically controlled. Our novel kernel parameterization shows higher descriptive power and faster convergence speed than existing parameterizations. This leads to important improvements in classification accuracy.

arXiv:2110.04875공식 코드 · Papers with Code

Scope2Screen: Focus+Context Techniques for Pathology Tumor Assessment in Multivariate Image Data

Inspection of tissues using a light microscope is the primary method of diagnosing many diseases, notably cancer. Highly multiplexed tissue imaging builds on this foundation, enabling the collection of up to 60 channels of molecular information plus cell and tissue morphology using antibody staining. This provides unique insight into disease biology and promises to help with the design of patient-specific therapies. However, a substantial gap remains with respect to visualizing the resulting multivariate image data and effectively supporting pathology workflows in digital environments on screen. We, therefore, developed Scope2Screen, a scalable software system for focus+context exploration and annotation of whole-slide, high-plex, tissue images. Our approach scales to analyzing 100GB images of 10^9 or more pixels per channel, containing millions of cells. A multidisciplinary team of visualization experts, microscopists, and pathologists identified key image exploration and annotation tasks involving finding, magnifying, quantifying, and organizing ROIs in an intuitive and cohesive manner. Building on a scope2screen metaphor, we present interactive lensing techniques that operate at single-cell and tissue levels. Lenses are equipped with task-specific functionality and descriptive statistics, making it possible to analyze image features, cell types, and spatial arrangements (neighborhoods) across image channels and scales. A fast sliding-window search guides users to regions similar to those under the lens; these regions can be analyzed and considered either separately or as part of a larger image collection. A novel snapshot method enables linked lens configurations and image statistics to be saved, restored, and shared. We validate our designs with domain experts and apply Scope2Screen in two case studies involving lung and colorectal cancers to discover cancer-relevant image features.

arXiv:2109.13701공식 코드 · Papers with Code

CIDEr-R: Robust Consensus-based Image Description Evaluation

This paper shows that CIDEr-D, a traditional evaluation metric for image description, does not work properly on datasets where the number of words in the sentence is significantly greater than those in the MS COCO Captions dataset. We also show that CIDEr-D has performance hampered by the lack of multiple reference sentences and high variance of sentence length. To bypass this problem, we introduce CIDEr-R, which improves CIDEr-D, making it more flexible in dealing with datasets with high sentence length variance. We demonstrate that CIDEr-R is more accurate and closer to human judgment than CIDEr-D; CIDEr-R is more robust regarding the number of available references. Our results reveal that using Self-Critical Sequence Training to optimize CIDEr-R generates descriptive captions. In contrast, when CIDEr-D is optimized, the generated captions' length tends to be similar to the reference length. However, the models also repeat several times the same word to increase the sentence length.

arXiv:2109.13137공식 코드 · Papers with Code

Mitigating Racial Biases in Toxic Language Detection with an Equity-Based Ensemble Framework

Recent research has demonstrated how racial biases against users who write African American English exists in popular toxic language datasets. While previous work has focused on a single fairness criteria, we propose to use additional descriptive fairness metrics to better understand the source of these biases. We demonstrate that different benchmark classifiers, as well as two in-process bias-remediation techniques, propagate racial biases even in a larger corpus. We then propose a novel ensemble-framework that uses a specialized classifier that is fine-tuned to the African American English dialect. We show that our proposed framework substantially reduces the racial biases that the model learns from these datasets. We demonstrate how the ensemble framework improves fairness metrics across all sample datasets with minimal impact on the classification performance, and provide empirical evidence in its ability to unlearn the annotation biases towards authors who use African American English. ** Please note that this work may contain examples of offensive words and phrases.

arXiv:2109.02865공식 코드 · Papers with Code

Journalistic Guidelines Aware News Image Captioning

The task of news article image captioning aims to generate descriptive and informative captions for news article images. Unlike conventional image captions that simply describe the content of the image in general terms, news image captions follow journalistic guidelines and rely heavily on named entities to describe the image content, often drawing context from the whole article they are associated with. In this work, we propose a new approach to this task, motivated by caption guidelines that journalists follow. Our approach, Journalistic Guidelines Aware News Image Captioning (JoGANIC), leverages the structure of captions to improve the generation quality and guide our representation design. Experimental results, including detailed ablation studies, on two large-scale publicly available datasets show that JoGANIC substantially outperforms state-of-the-art methods both on caption generation and named entity related metrics.

arXiv:2109.02610공식 코드 · Papers with Code

EsmamDS: A more diverse exceptional survival model mining approach

A variety of works in the literature strive to uncover the factors associated with survival behaviour. However, the computational tools to provide such information are global models designed to predict if or when a (survival) event will occur. When approaching the problem of explaining differences in survival behaviour, those approaches rely on (assumptions of) predictive features followed by risk stratification. In other words, they lack the ability to discover new information on factors related to survival. In contrast, we approach such a problem from the perspective of descriptive supervised pattern mining to discover local patterns associated with different survival behaviours. Hence, we introduce the EsmamDS algorithm: an Exceptional Model Mining framework to provide straightforward characterisations of subgroups presenting unusual survival models -- given by the Kaplan-Meier estimates. This work builds on the Esmam algorithm to address the problem of pattern redundancy and provide a more informative and diverse characterisation of survival behaviour.

arXiv:2109.02244공식 코드 · Papers with Code

Self-supervised Product Quantization for Deep Unsupervised Image Retrieval

Supervised deep learning-based hash and vector quantization are enabling fast and large-scale image retrieval systems. By fully exploiting label annotations, they are achieving outstanding retrieval performances compared to the conventional methods. However, it is painstaking to assign labels precisely for a vast amount of training data, and also, the annotation process is error-prone. To tackle these issues, we propose the first deep unsupervised image retrieval method dubbed Self-supervised Product Quantization (SPQ) network, which is label-free and trained in a self-supervised manner. We design a Cross Quantized Contrastive learning strategy that jointly learns codewords and deep visual descriptors by comparing individually transformed images (views). Our method analyzes the image contents to extract descriptive features, allowing us to understand image representations for accurate retrieval. By conducting extensive experiments on benchmarks, we demonstrate that the proposed method yields state-of-the-art results even without supervised pretraining.

arXiv:2108.12211공식 코드 · Papers with Code

Enel: Context-Aware Dynamic Scaling of Distributed Dataflow Jobs using Graph Propagation

Distributed dataflow systems like Spark and Flink enable the use of clusters for scalable data analytics. While runtime prediction models can be used to initially select appropriate cluster resources given target runtimes, the actual runtime performance of dataflow jobs depends on several factors and varies over time. Yet, in many situations, dynamic scaling can be used to meet formulated runtime targets despite significant performance variance. This paper presents Enel, a novel dynamic scaling approach that uses message propagation on an attributed graph to model dataflow jobs and, thus, allows for deriving effective rescaling decisions. For this, Enel incorporates descriptive properties that capture the respective execution context, considers statistics from individual dataflow tasks, and propagates predictions through the job graph to eventually find an optimized new scale-out. Our evaluation of Enel with four iterative Spark jobs shows that our approach is able to identify effective rescaling actions, reacting for instance to node failures, and can be reused across different execution contexts.

arXiv:2108.06712공식 코드 · Papers with Code

HiTab: A Hierarchical Table Dataset for Question Answering and Natural Language Generation

Tables are often created with hierarchies, but existing works on table reasoning mainly focus on flat tables and neglect hierarchical tables. Hierarchical tables challenge existing methods by hierarchical indexing, as well as implicit relationships of calculation and semantics. This work presents HiTab, a free and open dataset to study question answering (QA) and natural language generation (NLG) over hierarchical tables. HiTab is a cross-domain dataset constructed from a wealth of statistical reports (analyses) and Wikipedia pages, and has unique characteristics: (1) nearly all tables are hierarchical, and (2) both target sentences for NLG and questions for QA are revised from original, meaningful, and diverse descriptive sentences authored by analysts and professions of reports. (3) to reveal complex numerical reasoning in statistical analyses, we provide fine-grained annotations of entity and quantity alignment. HiTab provides 10,686 QA pairs and descriptive sentences with well-annotated quantity and entity alignment on 3,597 tables with broad coverage of table hierarchies and numerical reasoning types. Targeting hierarchical structure, we devise a novel hierarchy-aware logical form for symbolic reasoning over tables, which shows high effectiveness. Targeting complex numerical reasoning, we propose partially supervised training given annotations of entity and quantity alignment, which helps models to largely reduce spurious predictions in the QA task. In the NLG task, we find that entity and quantity alignment also helps NLG models to generate better results in a conditional generation setting. Experiment results of state-of-the-art baselines suggest that this dataset presents a strong challenge and a valuable benchmark for future research.

arXiv:2108.05863공식 코드 · Papers with Code

Towers of Babel: Combining Images, Language, and 3D Geometry for Learning Multimodal Vision

The abundance and richness of Internet photos of landmarks and cities has led to significant progress in 3D vision over the past two decades, including automated 3D reconstructions of the world's landmarks from tourist photos. However, a major source of information available for these 3D-augmented collections---namely language, e.g., from image captions---has been virtually untapped. In this work, we present WikiScenes, a new, large-scale dataset of landmark photo collections that contains descriptive text in the form of captions and hierarchical category names. WikiScenes forms a new testbed for multimodal reasoning involving images, text, and 3D geometry. We demonstrate the utility of WikiScenes for learning semantic concepts over images and 3D models. Our weakly-supervised framework connects images, 3D structure, and semantics---utilizing the strong constraints provided by 3D geometry---to associate semantic concepts to image pixels and 3D points.

arXiv:2108.02807공식 코드 · Papers with Code

Neural Twins Talk & Alternative Calculations

Inspired by how the human brain employs a higher number of neural pathways when describing a highly focused subject, we show that deep attentive models used for the main vision-language task of image captioning, could be extended to achieve better performance. Image captioning bridges a gap between computer vision and natural language processing. Automated image captioning is used as a tool to eliminate the need for human agent for creating descriptive captions for unseen images.Automated image captioning is challenging and yet interesting. One reason is that AI based systems capable of generating sentences that describe an input image could be used in a wide variety of tasks beyond generating captions for unseen images found on web or uploaded to social media. For example, in biology and medical sciences, these systems could provide researchers and physicians with a brief linguistic description of relevant images, potentially expediting their work.

arXiv:2108.01383공식 코드 · Papers with Code

On the descriptive power of LiDAR intensity images for segment-based loop closing in 3-D SLAM

We propose an extension to the segment-based global localization method for LiDAR SLAM using descriptors learned considering the visual context of the segments. A new architecture of the deep neural network is presented that learns the visual context acquired from synthetic LiDAR intensity images. This approach allows a single multi-beam LiDAR to produce rich and highly descriptive location signatures. The method is tested on two public datasets, demonstrating an improved descriptiveness of the new descriptors, and more reliable loop closure detection in SLAM. Attention analysis of the network is used to show the importance of focusing on the broader context rather than only on the 3-D segment.

arXiv:2107.13921공식 코드 · Papers with Code

Bellamy: Reusing Performance Models for Distributed Dataflow Jobs Across Contexts

Distributed dataflow systems enable the use of clusters for scalable data analytics. However, selecting appropriate cluster resources for a processing job is often not straightforward. Performance models trained on historical executions of a concrete job are helpful in such situations, yet they are usually bound to a specific job execution context (e.g. node type, software versions, job parameters) due to the few considered input parameters. Even in case of slight context changes, such supportive models need to be retrained and cannot benefit from historical execution data from related contexts. This paper presents Bellamy, a novel modeling approach that combines scale-outs, dataset sizes, and runtimes with additional descriptive properties of a dataflow job. It is thereby able to capture the context of a job execution. Moreover, Bellamy is realizing a two-step modeling approach. First, a general model is trained on all the available data for a specific scalable analytics algorithm, hereby incorporating data from different contexts. Subsequently, the general model is optimized for the specific situation at hand, based on the available data for the concrete context. We evaluate our approach on two publicly available datasets consisting of execution data from various dataflow jobs carried out in different environments, showing that Bellamy outperforms state-of-the-art methods.

arXiv:2107.11170공식 코드 · Papers with Code

Bias Loss for Mobile Neural Networks

Compact convolutional neural networks (CNNs) have witnessed exceptional improvements in performance in recent years. However, they still fail to provide the same predictive power as CNNs with a large number of parameters. The diverse and even abundant features captured by the layers is an important characteristic of these successful CNNs. However, differences in this characteristic between large CNNs and their compact counterparts have rarely been investigated. In compact CNNs, due to the limited number of parameters, abundant features are unlikely to be obtained, and feature diversity becomes an essential characteristic. Diverse features present in the activation maps derived from a data point during model inference may indicate the presence of a set of unique descriptors necessary to distinguish between objects of different classes. In contrast, data points with low feature diversity may not provide a sufficient amount of unique descriptors to make a valid prediction; we refer to them as random predictions. Random predictions can negatively impact the optimization process and harm the final performance. This paper proposes addressing the problem raised by random predictions by reshaping the standard cross-entropy to make it biased toward data points with a limited number of unique descriptive features. Our novel Bias Loss focuses the training on a set of valuable data points and prevents the vast number of samples with poor learning features from misleading the optimization process. Furthermore, to show the importance of diversity, we present a family of SkipNet models whose architectures are brought to boost the number of unique descriptors in the last layers. Our Skipnet-M can achieve 1% higher classification accuracy than MobileNetV3 Large.

arXiv:2107.07791공식 코드 · Papers with Code

Graph Representation Learning for Road Type Classification

We present a novel learning-based approach to graph representations of road networks employing state-of-the-art graph convolutional neural networks. Our approach is applied to realistic road networks of 17 cities from Open Street Map. While edge features are crucial to generate descriptive graph representations of road networks, graph convolutional networks usually rely on node features only. We show that the highly representative edge features can still be integrated into such networks by applying a line graph transformation. We also propose a method for neighborhood sampling based on a topological neighborhood composed of both local and global neighbors. We compare the performance of learning representations using different types of neighborhood aggregation functions in transductive and inductive tasks and in supervised and unsupervised learning. Furthermore, we propose a novel aggregation approach, Graph Attention Isomorphism Network, GAIN. Our results show that GAIN outperforms state-of-the-art methods on the road type classification problem.

arXiv:2106.15550공식 코드 · Papers with Code

Unified Questioner Transformer for Descriptive Question Generation in Goal-Oriented Visual Dialogue

Building an interactive artificial intelligence that can ask questions about the real world is one of the biggest challenges for vision and language problems. In particular, goal-oriented visual dialogue, where the aim of the agent is to seek information by asking questions during a turn-taking dialogue, has been gaining scholarly attention recently. While several existing models based on the GuessWhat?! dataset have been proposed, the Questioner typically asks simple category-based questions or absolute spatial questions. This might be problematic for complex scenes where the objects share attributes or in cases where descriptive questions are required to distinguish objects. In this paper, we propose a novel Questioner architecture, called Unified Questioner Transformer (UniQer), for descriptive question generation with referring expressions. In addition, we build a goal-oriented visual dialogue task called CLEVR Ask. It synthesizes complex scenes that require the Questioner to generate descriptive questions. We train our model with two variants of CLEVR Ask datasets. The results of the quantitative and qualitative evaluations show that UniQer outperforms the baseline.

arXiv:2106.08285공식 코드 · Papers with Code

Multi-StyleGAN: Towards Image-Based Simulation of Time-Lapse Live-Cell Microscopy

Time-lapse fluorescent microscopy (TLFM) combined with predictive mathematical modelling is a powerful tool to study the inherently dynamic processes of life on the single-cell level. Such experiments are costly, complex and labour intensive. A complimentary approach and a step towards in silico experimentation, is to synthesise the imagery itself. Here, we propose Multi-StyleGAN as a descriptive approach to simulate time-lapse fluorescence microscopy imagery of living cells, based on a past experiment. This novel generative adversarial network synthesises a multi-domain sequence of consecutive timesteps. We showcase Multi-StyleGAN on imagery of multiple live yeast cells in microstructured environments and train on a dataset recorded in our laboratory. The simulation captures underlying biophysical factors and time dependencies, such as cell morphology, growth, physical interactions, as well as the intensity of a fluorescent reporter protein. An immediate application is to generate additional training and validation data for feature extraction algorithms or to aid and expedite development of advanced experimental techniques such as online monitoring or control of cells. Code and dataset is available at https://git.rwth-aachen.de/bcs/projects/tp/multi-stylegan.

arXiv:2105.14477공식 코드 · Papers with Code

Towards Diverse Paragraph Captioning for Untrimmed Videos

Video paragraph captioning aims to describe multiple events in untrimmed videos with descriptive paragraphs. Existing approaches mainly solve the problem in two steps: event detection and then event captioning. Such two-step manner makes the quality of generated paragraphs highly dependent on the accuracy of event proposal detection which is already a challenging task. In this paper, we propose a paragraph captioning model which eschews the problematic event detection stage and directly generates paragraphs for untrimmed videos. To describe coherent and diverse events, we propose to enhance the conventional temporal attention with dynamic video memories, which progressively exposes new video features and suppresses over-accessed video contents to control visual focuses of the model. In addition, a diversity-driven training strategy is proposed to improve diversity of paragraph on the language perspective. Considering that untrimmed videos generally contain massive but redundant frames, we further augment the video encoder with keyframe awareness to improve efficiency. Experimental results on the ActivityNet and Charades datasets show that our proposed model significantly outperforms the state-of-the-art performance on both accuracy and diversity metrics without using any event boundary annotations. Code will be released at https://github.com/syuqings/video-paragraph.

arXiv:2105.06811공식 코드 · Papers with Code

Quantified Sleep: Machine learning techniques for observational n-of-1 studies

This paper applies statistical learning techniques to an observational Quantified-Self (QS) study to build a descriptive model of sleep quality. A total of 472 days of my sleep data was collected with an Oura ring and combined with lifestyle, environmental, and psychological data. Such n-of-1 QS projects pose a number of challenges: heterogeneous data sources; missing values; high dimensionality; dynamic feedback loops; human biases. This paper directly addresses these challenges with an end-to-end QS pipeline that produces robust descriptive models. Sleep quality is one of the most difficult modelling targets in QS research, due to high noise and a large number of weakly-contributing factors. Sleep quality was selected so that approaches from this paper would generalise to most other n-of-1 QS projects. Techniques are presented for combining and engineering features for the different classes of data types, sample frequencies, and schema - including event logs, weather, and geo-spatial data. Statistical analyses for outliers, normality, (auto)correlation, stationarity, and missing data are detailed, along with a proposed method for hierarchical clustering to identify correlated groups of features. The missing data was overcome using a combination of knowledge-based and statistical techniques, including several multivariate imputation algorithms. "Markov unfolding" is presented for collapsing the time series into a collection of independent observations, whilst incorporating historical information. The final model was interpreted in two ways: by inspecting the internal $\beta$-parameters, and using the SHAP framework. These two interpretation techniques were combined to produce a list of the 16 most-predictive features, demonstrating that an observational study can greatly narrow down the number of features that need to be considered when designing interventional QS studies.