Fine-grained visual classification (FGVC) which aims at recognizing objects from subcategories is a very challenging task due to the inherently subtle inter-class differences. Recent works mainly tackle this problem by focusing on how to locate the most discriminative image regions and rely on them to improve the capability of networks to capture subtle variances. Most of these works achieve this by re-using the backbone network to extract features of selected regions. However, this strategy inevitably complicates the pipeline and pushes the proposed regions to contain most parts of the objects. Recently, vision transformer (ViT) shows its strong performance in the traditional classification task. The self-attention mechanism of the transformer links every patch token to the classification token. The strength of the attention link can be intuitively considered as an indicator of the importance of tokens. In this work, we propose a novel transformer-based framework TransFG where we integrate all raw attention weights of the transformer into an attention map for guiding the network to effectively and accurately select discriminative image patches and compute their relations. A contrastive loss is applied to further enlarge the distance between feature representations of similar sub-classes. We demonstrate the value of TransFG by conducting experiments on five popular fine-grained benchmarks: CUB-200-2011, Stanford Cars, Stanford Dogs, NABirds and iNat2017 where we achieve state-of-the-art performance. Qualitative results are presented for better understanding of our model. Code is available at https://github.com/TACJu/TransFG.
Logical relations widely exist in human activities. Human use them for making judgement and decision according to various conditions, which are embodied in the form of \emph{if-then} rules. As an important kind of cognitive intelligence, it is prerequisite of representing and storing logical relations rightly into computer systems so as to make automatic judgement and decision, especially for high-risk domains like medical diagnosis. However, current numeric ANN (Artificial Neural Network) models are good at perceptual intelligence such as image recognition while they are not good at cognitive intelligence such as logical representation, blocking the further application of ANN. To solve it, researchers have tried to design logical ANN models to represent and store logical relations. Although there are some advances in this research area, recent works still have disadvantages because the structures of these logical ANN models still don't map more directly with logical relations which will cause the corresponding logical relations cannot be read out from their network structures. Therefore, in order to represent logical relations more clearly by the neural network structure and to read out logical relations from it, this paper proposes a novel logical ANN model by designing the new logical neurons and links in demand of logical representation. Compared with the recent works on logical ANN models, this logical ANN model has more clear corresponding with logical relations using the more direct mapping method herein, thus logical relations can be read out following the connection patterns of the network structure. Additionally, less neurons are used.
In spite of showing unreasonable effectiveness in modalities like Text and Image, Deep Learning has always lagged Gradient Boosting in tabular data - both in popularity and performance. But recently there have been newer models created specifically for tabular data, which is pushing the performance bar. But popularity is still a challenge because there is no easy, ready-to-use library like Sci-Kit Learn for deep learning. PyTorch Tabular is a new deep learning library which makes working with Deep Learning and tabular data easy and fast. It is a library built on top of PyTorch and PyTorch Lightning and works on pandas dataframes directly. Many SOTA models like NODE and TabNet are already integrated and implemented in the library with a unified API. PyTorch Tabular is designed to be easily extensible for researchers, simple for practitioners, and robust in industrial deployments.
We propose a self-supervised method for image relighting of single view images in the wild. The method is based on an auto-encoder which deconstructs an image into two separate encodings, relating to the scene illumination and content, respectively. In order to disentangle this embedding information without supervision, we exploit the assumption that some augmentation operations do not affect the image content and only affect the direction of the light. A novel loss function, called spherical harmonic loss, is introduced that forces the illumination embedding to convert to a spherical harmonic vector. We train our model on large-scale datasets such as Youtube 8M and CelebA. Our experiments show that our method can correctly estimate scene illumination and realistically re-light input images, without any supervision or a prior shape model. Compared to supervised methods, our approach has similar performance and avoids common lighting artifacts.
Online shopping has become a valuable modern convenience, but blind or low vision (BLV) users still face significant challenges using it, because of: 1) inadequate image descriptions and 2) the inability to filter large amounts of information using screen readers. To address those challenges, we propose Revamp, a system that leverages customer reviews for interactive information retrieval. Revamp is a browser integration that supports review-based question-answering interactions on a reconstructed product page. From our interview, we identified four main aspects (color, logo, shape, and size) that are vital for BLV users to understand the visual appearance of a product. Based on the findings, we formulated syntactic rules to extract review snippets, which were used to generate image descriptions and responses to users' queries. Evaluations with eight BLV users showed that Revamp 1) provided useful descriptive information for understanding product appearance and 2) helped the participants locate key information efficiently.
Purpose: To develop a semi-automated, AI-assisted workflow for segmentation of inflammatory lesions on STIR MRI of sacroiliac joints (SIJs) in adult patients with axial spondyloarthritis. Methods: Baseline human performance in manual segmentation of inflammatory lesions was first established in eight patients with axial spondyloarthritis recruited within a prospective study conducted between April 2018 and July 2019. To improve readers' consistency a semi-automated procedure was developed, comprising (1) manual segmentation of 'normal bone' and 'disease' regions (2) automatic segmentation of lesions, i.e., voxels in the disease region with outlying intensity with respect to the normal bone, and (3) human intervention to remove erroneously segmented areas. Segmentation of disease region (subchondral bone) was automated via supervised deep learning; 200 image slices (eight subjects) were used for algorithm training with cross validation, 48 (two subjects) - for testing and 500 (20 subjects) - for evaluation based on visual assessment. The data, code, and model are available at https://github.com/c-hepburn/Bone_MRI. Human and model performance were assessed in terms of Dice coefficient. Results: Intra-reader median Dice coefficients, evaluated from comparison of manual segmentation trials of inflammatory lesions, were 0.63 and 0.69 for the two readers, respectively. Inter-reader median Dice was in the range of 0.53 to 0.56 and increased to 0.84 using the semi-automated approach. Deep learning model ensemble showed average Dice of 0.94 in subchondral bone segmentation. Conclusions: We describe a semi-automated, AI-assisted workflow which improves the objectivity and consistency of radiological segmentation of inflammatory load in SIJs.
Magnetic resonance elastography (MRE) for measuring viscoelasticity heavily depends on proper tissue segmentation, especially in heterogeneous organs such as the prostate. Using trained network-based image segmentation, we investigated if MRE data suffice to extract anatomical and viscoelastic information for automatic tabulation of zonal mechanical properties of the prostate. Overall, 40 patients with benign prostatic hyperplasia (BPH) or prostate cancer (PCa) were examined with three magnetic resonance imaging (MRI) sequences: T2-weighted MRI (T2w), diffusion-weighted imaging (DWI), and MRE-based tomoelastography yielding six independent sets of imaging data per patient (T2w, DWI, apparent diffusion coefficient (ADC), MRE magnitude, shear wave speed, and loss angle maps). Combinations of these data were used to train Dense U-nets with manually segmented masks of the entire prostate gland (PG), central zone (CZ), and peripheral zone (PZ) in 30 patients and to validate them in 10 patients. Dice score (DS), sensitivity, specificity, and Hausdorff distance were determined. We found that segmentation based on MRE magnitude maps alone (DS, PG: 0.93$\pm$0.04, CZ: 0.95$\pm$0.03, PZ: 0.77$\pm$0.05) was more accurate than magnitude maps combined with T2w and DWI_b (DS, PG: 0.91$\pm$0.04, CZ: 0.91$\pm$0.06, PZ: 0.63$\pm$0.16) or T2w alone (DS, PG: 0.92$\pm$0.03, CZ: 0.91$\pm$0.04, PZ: 0.65$\pm$0.08). Automatically tabulated MRE values were not different from ground-truth values (P>0.05). In conclusion: MRE combined with Dense U-net segmentation allows tabulation of quantitative imaging markers without manual analysis and independent of other MRI sequences and can thus contribute to PCa detection and classification.
Convolutional neural networks (CNNs) have led to significant improvements in tasks involving semantic segmentation of images. CNNs are vulnerable in the area of biomedical image segmentation because of distributional gap between two source and target domains with different data modalities which leads to domain shift. Domain shift makes data annotations in new modalities necessary because models must be retrained from scratch. Unsupervised domain adaptation (UDA) is proposed to adapt a model to new modalities using solely unlabeled target domain data. Common UDA algorithms require access to data points in the source domain which may not be feasible in medical imaging due to privacy concerns. In this work, we develop an algorithm for UDA in a privacy-constrained setting, where the source domain data is inaccessible. Our idea is based on encoding the information from the source samples into a prototypical distribution that is used as an intermediate distribution for aligning the target domain distribution with the source domain distribution. We demonstrate the effectiveness of our algorithm by comparing it to state-of-the-art medical image semantic segmentation approaches on two medical image semantic segmentation datasets.
Analysis of respiratory sounds increases its importance every day. Many different methods are available in the analysis, and new techniques are continuing to be developed to further improve these methods. Features are extracted from audio signals and trained using different machine learning techniques. The use of deep learning, which is a different method and has increased in recent years, also shows its influence in this field. Deep learning techniques applied to the image of audio signals give good results and continue to be developed. In this study, image filters were applied to the values obtained from audio signals and the results of the features formed from this were examined in machine learning and deep learning techniques. Their results were compared with the results of methods that had previously achieved good results.
Today, the use of social networking data has attracted a lot of academic and commercial attention in predicting the stock market. In most studies in this area, the sentiment analysis of the content of user posts on social networks is used to predict market fluctuations. Predicting stock marketing is challenging because of the variables involved. In the short run, the market behaves like a voting machine, but in the long run, it acts like a weighing machine. The purpose of this study is to predict EUR/USD stock behavior using Capsule Network on finance texts and Candlestick images. One of the most important features of Capsule Network is the maintenance of features in a vector, which also takes into account the space between features. The proposed model, TI-Capsule (Text and Image information based Capsule Neural Network), is trained with both the text and image information simultaneously. Extensive experiments carried on the collected dataset have demonstrated the effectiveness of TI-Capsule in solving the stock exchange prediction problem with 91% accuracy.