In this study, we introduce a new synthetic data generation procedure for augmentation of histopathology image data. This is an extension to our previous research in which we proved the possibility ...to apply deep learning models for morphological analysis of tumor cells, trained on synthetic data only. The medical problem considered is related to the Ki-67 protein proliferation index calculation. We focused on the problem of cell counting in cell conglomerates, which are considered as structures composed of overlapping tumor cells. The lack of large and standardized data sets is a critical problem in medical image classification. Classical augmentation procedures are not sufficient. Therefore, in this research, we expanded our previous augmentation approach for histopathology images and we proved the possibility to apply it for a cell-counting problem.
Multiple studies presented satisfactory performances for the treatment of various ocular diseases. To date, there has been no study that describes a multiclass model, medically accurate, and trained ...on large diverse dataset. No study has addressed a class imbalance problem in one giant dataset originating from multiple large diverse eye fundus image collections. To ensure a real-life clinical environment and mitigate the problem of biased medical image data, 22 publicly available datasets were merged. To secure medical validity only Diabetic Retinopathy (DR), Age-Related Macular Degeneration (AMD) and Glaucoma (GL) were included. The state-of-the-art models ConvNext, RegNet and ResNet were utilized. In the resulting dataset, there were 86,415 normal, 3787 GL, 632 AMD and 34,379 DR fundus images. ConvNextTiny achieved the best results in terms of recognizing most of the examined eye diseases with the most metrics. The overall accuracy was 80.46 ± 1.48. Specific accuracy values were: 80.01 ± 1.10 for normal eye fundus, 97.20 ± 0.66 for GL, 98.14 ± 0.31 for AMD, 80.66 ± 1.27 for DR. A suitable screening model for the most prevalent retinal diseases in ageing societies was designed. The model was developed on a diverse, combined large dataset which made the obtained results less biased and more generalizable.
Contemporary deep neural networks offer state-of-the-art results when applied to visual reasoning, e.g., in the context of 3D point cloud data. Point clouds are an important data type for the precise ...modeling of three-dimensional environments, but effective processing of this type of data proves to be challenging. In the world of large, heavily-parameterized network architectures and continuously-streamed data, there is an increasing need for machine learning models that can be trained on additional data. Unfortunately, currently available models cannot fully leverage training on additional data without losing their past knowledge. Combating this phenomenon, called catastrophic forgetting, is one of the main objectives of continual learning. Continual learning for deep neural networks has been an active field of research, primarily in 2D computer vision, natural language processing, reinforcement learning, and robotics. However, in 3D computer vision, there are hardly any continual learning solutions specifically designed to take advantage of point cloud structure. This work proposes a novel neural network architecture capable of continual learning on 3D point cloud data. We utilize point cloud structure properties for preserving a heavily compressed set of past data. By using rehearsal and reconstruction as regularization methods of the learning process, our approach achieves a significant decrease of catastrophic forgetting compared to the existing solutions on several most popular point cloud datasets considering two continual learning settings: when a task is known beforehand, and in the challenging scenario of when task information is unknown to the model.
•We introduce a new continual learning model designed for 2D & 3D point cloud data.•For rehearsal purposes, we utilize only a tiny portion of the original data.•We can significantly mitigate the catastrophic forgetting for up to 20 tasks.•The experiments show superb results on the most popular benchmark datasets.
Some tasks in content processing, e.g., natural language processing (NLP), like hate or offensive speech and emotional or funny text detection, are subjective by nature. Each human may perceive some ...content individually. The existing reasoning methods commonly rely on agreed output values, the same for all recipients. We propose fundamentally different — personalized solutions applicable to any subjective NLP task. Our five new deep learning models take into account not only the textual content but also the opinions and beliefs of a given person. They differ in their approaches to learning Human Bias (HuBi) and fusion with content (text) representation. The experiments were carried out on 14 tasks related to offensive, emotional, and humorous texts. Our personalized HuBi methods radically outperformed the generalized ones for all NLP problems. Personalization also has a greater impact on reasoning quality than commonly explored pre-trained and fine-tuned language models. We discovered a high correlation between human bias calculated using our dedicated formula and that learned by the model. Multi-task solutions achieved better outcomes than single-task architectures. Human and word embeddings also provided additional insights.
•Human-centered neural architectures suitable for subjective NLP problems are introduced.•Personalized NLP requires dedicated validation procedures.•Personalized methods revealed their superiority over generalized approaches for 14 tasks related to hate speech, emotions and humor.•Language models, multi-tasking and fine-tuning have less impact than personalization.•There is correlation between formula-based human bias and bias learned by the neural model.
HyperShot: Few-Shot Learning by Kernel HyperNetworks Sendera, Marcin; Przewiezlikowski, Marcin; Karanowski, Konrad ...
2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV),
2023-Jan.
Conference Proceeding
Few-shot models aim at making predictions using a minimal number of labeled examples from a given task. The main challenge in this area is the one-shot setting where only one element represents each ...class. We propose HyperShot - the fusion of kernels and hypernetwork paradigm. Compared to reference approaches that apply a gradientbased adjustment of the parameters, our model aims to switch the classification module parameters depending on the task's embedding. In practice, we utilize a hypernetwork, which takes the aggregated information from support data and returns the classifier's parameters handcrafted for the considered problem. Moreover, we introduce the kernel-based representation of the support examples delivered to hypernetwork to create the parameters of the classification module. Consequently, we rely on relations between embeddings of the support examples instead of direct feature values provided by the backbone models. Thanks to this approach, our model can adapt to highly different tasks. *
Few-shot models aim at making predictions using a minimal number of labeled examples from a given task. The main challenge in this area is the
one-shot
setting, where only one element represents each ...class. We propose the general framework for few-shot learning via kernel HyperNetworks—the fusion of kernels and hypernetwork paradigm. Firstly, we introduce the classical realization of this framework, dubbed HyperShot. Compared to reference approaches that apply a gradient-based adjustment of the parameters, our models aim to switch the classification module parameters depending on the task’s embedding. In practice, we utilize a hypernetwork, which takes the aggregated information from support data and returns the classifier’s parameters handcrafted for the considered problem. Moreover, we introduce the kernel-based representation of the support examples delivered to hypernetwork to create the parameters of the classification module. Consequently, we rely on relations between the support examples’ embeddings instead of the backbone models’ direct feature values. Thanks to this approach, our model can adapt to highly different tasks. While such a method obtains very good results, it is limited by typical problems such as poorly quantified uncertainty due to limited data size. We further show that incorporating Bayesian neural networks into our general framework, an approach we call BayesHyperShot, solves this issue.
Contemporary deep neural networks offer state-of-the-art results when applied to visual reasoning, e.g., in the context of 3D point cloud data. Point clouds are important datatype for precise ...modeling of three-dimensional environments, but effective processing of this type of data proves to be challenging. In the world of large, heavily-parameterized network architectures and continuously-streamed data, there is an increasing need for machine learning models that can be trained on additional data. Unfortunately, currently available models cannot fully leverage training on additional data without losing their past knowledge. Combating this phenomenon, called catastrophic forgetting, is one of the main objectives of continual learning. Continual learning for deep neural networks has been an active field of research, primarily in 2D computer vision, natural language processing, reinforcement learning, and robotics. However, in 3D computer vision, there are hardly any continual learning solutions specifically designed to take advantage of point cloud structure. This work proposes a novel neural network architecture capable of continual learning on 3D point cloud data. We utilize point cloud structure properties for preserving a heavily compressed set of past data. By using rehearsal and reconstruction as regularization methods of the learning process, our approach achieves a significant decrease of catastrophic forgetting compared to the existing solutions on several most popular point cloud datasets considering two continual learning settings: when a task is known beforehand, and in the challenging scenario of when task information is unknown to the model.
Designing predictive models for subjective problems in natural language processing (NLP) remains challenging. This is mainly due to its non-deterministic nature and different perceptions of the ...content by different humans. It may be solved by Personalized Natural Language Processing (PNLP), where the model exploits additional information about the reader to make more accurate predictions. However, current approaches require complete information about the recipients to be straight embedded. Besides, the recent methods focus on deterministic inference or simple frequency-based estimations of the probabilities. In this work, we overcome this limitation by proposing a novel approach to capture the uncertainty of the forecast using conditional Normalizing Flows. This allows us to model complex multimodal distributions and to compare various models using negative log-likelihood (NLL). In addition, the new solution allows for various interpretations of possible reader perception thanks to the available sampling function. We validated our method on three challenging, subjective NLP tasks, including emotion recognition and hate speech. The comparative analysis of generalized and personalized approaches revealed that our personalized solutions significantly outperform the baseline and provide more precise uncertainty estimates. The impact on the text interpretability and uncertainty studies are presented as well. The information brought by the developed methods makes it possible to build hybrid models whose effectiveness surpasses classic solutions. In addition, an analysis and visualization of the probabilities of the given decisions for texts with high entropy of annotations and annotators with mixed views were carried out.
Designing predictive models for subjective problems in natural language processing (NLP) remains challenging. This is mainly due to its non-deterministic nature and different perceptions of the ...content by different humans. It may be solved by Personalized Natural Language Processing (PNLP), where the model exploits additional information about the reader to make more accurate predictions. However, current approaches require complete information about the recipients to be straight embedded. Besides, the recent methods focus on deterministic inference or simple frequency-based estimations of the probabilities. In this work, we overcome this limitation by proposing a novel approach to capture the uncertainty of the forecast using conditional Normalizing Flows. This allows us to model complex multimodal distributions and to compare various models using negative log-likelihood (NLL). In addition, the new solution allows for various interpretations of possible reader perception thanks to the available sampling function. We validated our method on three challenging, subjective NLP tasks, including emotion recognition and hate speech. The comparative analysis of generalized and personalized approaches revealed that our personalized solutions significantly outperform the baseline and provide more precise uncertainty estimates. The impact on the text interpretability and uncertainty studies are presented as well. The information brought by the developed methods makes it possible to build hybrid models whose effectiveness surpasses classic solutions. In addition, an analysis and visualization of the probabilities of the given decisions for texts with high entropy of annotations and annotators with mixed views were carried out.
As humans, we experience a wide range of feelings and reactions. One of these is laughter, often related to a personal sense of humor and the perception of funny content. Due to its subjective ...nature, recognizing humor in NLP is a very challenging task. Here, we present a new approach to the task of predicting humor in the text by applying the idea of a personalized approach. It takes into account both the text and the context of the content receiver. For that purpose, we proposed four Deep-SHEEP learning models that take advantage of user preference information differently. The experiments were conducted on four datasets: Cockamamie, HUMOR, Jester, and Humicroedit. The results have shown that the application of an innovative personalized approach and user-centric perspective significantly improves performance compared to generalized methods. Moreover, even for random text embeddings, our personalized methods outperform the generalized ones in the subjective humor modeling task. We also argue that the user-related data reflecting an individual sense of humor has similar importance as the evaluated text itself. Different types of humor were investigated as well.