| 1. |
- Berg, Axel, et al.
(författare)
-
Points to patches: Enabling the use of self-attention for 3D shape recognition
- 2022
-
Ingår i: 2022 26th International Conference on Pattern Recognition (ICPR). - 2831-7475 .- 1051-4651. - 9781665490627 - 9781665490627 ; , s. 528-534
-
Konferensbidrag (refereegranskat)abstract
- While the Transformer architecture has become ubiquitous in the machine learning field, its adaptation to 3D shape recognition is non-trivial. Due to its quadratic computational complexity, the self-attention operator quickly becomes inefficient as the set of input points grows larger. Furthermore, we find that the attention mechanism struggles to find useful connections between individual points on a global scale. In order to alleviate these problems, we propose a two-stage Point Transformer-in-Transformer (Point-TnT) approach which combines local and global attention mechanisms, enabling both individual points and patches of points to attend to each other effectively. Experiments on shape classification show that such an approach provides more useful features for downstream tasks than the baseline Transformer, while also being more computationally efficient. In addition, we also extend our method to feature matching for scene reconstruction, showing that it can be used in conjunction with existing scene reconstruction pipelines.
|
|
| 2. |
- Hsu, Pohao, et al.
(författare)
-
Extremely Low-light Image Enhancement with Scene Text Restoration
- 2022
-
Ingår i: Proceedings - International Conference on Pattern Recognition. - 1051-4651. - 9781665490627 ; 2022-August, s. 317-323
-
Konferensbidrag (refereegranskat)abstract
- Deep learning based methods have made impressive progress in enhancing extremely low-light images - the image quality of the reconstructed images has generally improved. However, we found out that most of these methods could not sufficiently recover the image details, for instance the texts in the scene. In this paper, a novel image enhancement framework is proposed to specifically restore the scene texts, as well as the overall quality of the image simultaneously under extremely low-light images conditions. Particularly, we employed a selfregularised attention map, an edge map, and a novel text detection loss. The quantitative and qualitative experimental results have shown that the proposed model outperforms stateof-the-art methods in terms of image restoration, text detection, and text spotting on See In the Dark and ICDAR15 datasets.
|
|
| 3. |
- Liu, Xixi, 1995, et al.
(författare)
-
Effortless Training of Joint Energy-Based Models with Sliced Score Matching
- 2022
-
Ingår i: Proceedings - International Conference on Pattern Recognition. - 1051-4651. - 9781665490627 ; 2022-August, s. 2643-2649
-
Konferensbidrag (refereegranskat)abstract
- Standard discriminative classifiers can be upgraded to joint energy-based models (JEMs) by combining the classification loss with a log-evidence loss. Hence, such models intrinsically allow detection of out-of-distribution (OOD) samples, and empirically also provide better-calibrated posteriors, i.e., prediction uncertainties. However, the training procedure suggested for JEMs (using stochastic gradient Langevin dynamics---or SGLD---to maximize the evidence) is reported to be brittle. In this work, we propose to utilize score matching---in particular sliced score matching---to obtain a stable training method for JEMs. We observe empirically that the combination of score matching with the standard classification loss leads to improved OOD detection and better-calibrated classifiers for otherwise identical DNN architectures. Additionally, we also analyze the impact of replacing the regular soft-max layer for classification with a gated soft-max one in order to improve the intrinsic transformation invariance and generalization ability.
|
|
| 4. |
- Liu, Xixi, 1995, et al.
(författare)
-
Joint Energy-based Model for Deep Probabilistic Regression
- 2022
-
Ingår i: Proceedings - International Conference on Pattern Recognition. - 1051-4651. - 9781665490627 ; 2022-August, s. 2693-2699
-
Konferensbidrag (refereegranskat)abstract
- It is desirable that a deep neural network trained on a regression task does not only achieve high prediction accuracy, but its prediction posteriors are also well-calibrated, especially in safety-critical settings. Recently, energy-based models specifically to enrich regression posteriors have been proposed and achieve state-of-art results in object detection tasks. However, applying these models at prediction time is not straightforward as the resulting inference methods require to minimize an underlying energy function. Furthermore, these methods empirically do not provide accurate prediction uncertainties. Inspired by recent joint energy-based models for classification, in this work we propose to utilize a joint energy model for regression tasks and describe architectural differences needed in this setting. Within this frame-work, we apply our methods to three computer vision regression tasks. We demonstrate that joint energy-based models for deep probabilistic regression improve the calibration property, do not require expensive inference, and yield competitive accuracy in terms of the mean absolute error (MAE).
|
|
| 5. |
|
|
| 6. |
- Alvén, Jennifer, 1989, et al.
(författare)
-
Shape-aware multi-atlas segmentation
- 2016
-
Ingår i: Proceedings - International Conference on Pattern Recognition. - 1051-4651. ; 0, s. 1101-1106
-
Konferensbidrag (refereegranskat)abstract
- Despite of having no explicit shape model, multi-atlas approaches to image segmentation have proved to be a top-performer for several diverse datasets and imaging modalities. In this paper, we show how one can directly incorporate shape regularization into the multi-atlas framework. Unlike traditional methods, our proposed approach does not rely on label fusion on the voxel level. Instead, each registered atlas is viewed as an estimate of the position of a shape model. We evaluate and compare our method on two public benchmarks: (i) the VISCERAL Grand Challenge on multi-organ segmentation of whole-body CT images and (ii) the Hammers brain atlas of MR images for segmenting the hippocampus and the amygdala. For this wide spectrum of both easy and hard segmentation tasks, our experimental quantitative results are on par or better than state-of-the-art. More importantly, we obtain qualitatively better segmentation boundaries, for instance, preserving fine structures.
|
|
| 7. |
- Arvidsson, Ida, et al.
(författare)
-
Prediction of Obstructive Coronary Artery Disease from Myocardial Perfusion Scintigraphy using Deep Neural Networks
- 2021
-
Ingår i: 2020 25TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR). - : IEEE COMPUTER SOC. - 1051-4651. - 9781728188089 ; , s. 4442-4449
-
Konferensbidrag (refereegranskat)abstract
- For diagnosis and risk assessment in patients with stable ischemic heart disease, myocardial perfusion scintigraphy is one of the most common cardiological examinations performed today. There are however many motivations for why an artificial intelligence algorithm would provide useful input to this task. For example to reduce the subjectiveness and save time for the nuclear medicine physicians working with this time consuming task. In this work we have developed a deep learning algorithm for multi-label classification based on a convolutional neural network to estimate the probability of obstructive coronary artery disease in the left anterior artery, left circumflex artery and right coronary artery. The prediction is based on data from myocardial perfusion scintigraphy studies conducted in a dedicated Cadmium-Zinc-Telluride cardio camera (D-SPECT Spectrum Dynamics). Data from 588 patients was available, with stress images in both upright and supine position, as well as a number of auxiliary parameters such as angina symptoms and age. The data was used to train and evaluate the algorithm using 5-fold cross-validation. We achieve state-of-the-art results for this task with an area under the receiver operating characteristics curve of 0.89 as average on per-vessel level and 0.95 on per-patient level.
|
|
| 8. |
- Berg, Axel, et al.
(författare)
-
Deep ordinal regression with label diversity
- 2021
-
Ingår i: 2020 25th International Conference on Pattern Recognition (ICPR). - 1051-4651. - 9781728188089 ; , s. 2740-2747
-
Konferensbidrag (refereegranskat)abstract
- Regression via classification (RvC) is a common method used for regression problems in deep learning, where the target variable belongs to a set of continuous values. By discretizing the target into a set of non-overlapping classes, it has been shown that training a classifier can improve neural network accuracy compared to using a standard regression approach. However, it is not clear how the set of discrete classes should be chosen and how it affects the overall solution. In this work, we propose that using several discrete data representations simultaneously can improve neural network learning compared to a single representation. Our approach is end-to-end differentiable and can be added as a simple extension to conventional learning methods, such as deep neural networks. We test our method on three challenging tasks and show that our method reduces the prediction error compared to a baseline RvC approach while maintaining a similar model complexity.
|
|
| 9. |
- Blomqvist, Christopher, et al.
(författare)
-
Joint Handwritten Text Recognition and Word Classification for Tabular Information Extraction
- 2022
-
Ingår i: 2022 26th International Conference on Pattern Recognition (ICPR). - 9781665490627 - 9781665490634 ; , s. 1564-1570
-
Konferensbidrag (refereegranskat)abstract
- In this paper, we present a system for extracting tabular information from loosely structured handwritten documents. The system consists of three parts, (i) a u-net like CNN-based method for text detection and segmentation, (ii) a new attention-based method for simultaneous text recognition and classification of word-parts, and (iii) a method for matching the word parts into a tabular structure for each entry. A key contribution is the observation that the new attention-based recognition and classification module makes it possible for improved spatial analysis of the tabular information. The method is evaluated on a unique historical document: The Swedish Wealth Tax of 1571, consisting of 11,453 pages of hand-written tax records. The evaluation shows that the system provides a significant improvement to the state-of-the-art to the problem of tabular extraction from loosely structured historical documents.
|
|
| 10. |
|
|
