In order to separate completely the objects with larger occluded boundaries in an image, we devise a new variational level set model for image segmentation combing the recently proposed Chan-Vese-Euler model with elastica and landmark constraints. For computational efficiency, we deign its Augmented Lagrangian Method(ALM) or Alternating Direction Method of Multiplier(ADMM) method by introducing some auxiliary variables, Lagrange multipliers and penalty parameters. In each loop of alternating iterative optimization, the sub-problems of minimization can be solved via simple Gauss-Seidel iterative method, or generalized soft thresholding formulas with projection methods respectively. Numerical experiments show that the proposed model not only can recover larger broken boundaries, but also can improve segmentation efficiency, decrease the dependence of segmentation on tuning parameters and initialization.
This paper proposes a method for OOD detection. Questioning the premise of previous studies that ID and OOD samples are separated distinctly, we consider samples lying in the intermediate of the two and use them for training a network. We generate such samples using multiple image transformations that corrupt inputs in various ways and with different severity levels. We estimate where the generated samples by a single image transformation lie between ID and OOD using a network trained on clean ID samples. To be specific, we make the network classify the generated samples and calculate their mean classification accuracy, using which we create a soft target label for them. We train the same network from scratch using the original ID samples and the generated samples with the soft labels created for them. We detect OOD samples by thresholding the entropy of the predicted softmax probability. The experimental results show that our method outperforms the previous state-of-the-art in the standard benchmark tests. We also analyze the effect of the number and particular combinations of image corrupting transformations on the performance.
This paper presents a new vision Transformer, called Swin Transformer, that capably serves as a general-purpose backbone for computer vision. Challenges in adapting Transformer from language to vision arise from differences between the two domains, such as large variations in the scale of visual entities and the high resolution of pixels in images compared to words in text. To address these differences, we propose a hierarchical Transformer whose representation is computed with shifted windows. The shifted windowing scheme brings greater efficiency by limiting self-attention computation to non-overlapping local windows while also allowing for cross-window connection. This hierarchical architecture has the flexibility to model at various scales and has linear computational complexity with respect to image size. These qualities of Swin Transformer make it compatible with a broad range of vision tasks, including image classification (86.4 top-1 accuracy on ImageNet-1K) and dense prediction tasks such as object detection (58.7 box AP and 51.1 mask AP on COCO test-dev) and semantic segmentation (53.5 mIoU on ADE20K val). Its performance surpasses the previous state-of-the-art by a large margin of +2.7 box AP and +2.6 mask AP on COCO, and +3.2 mIoU on ADE20K, demonstrating the potential of Transformer-based models as vision backbones. The code and models will be made publicly available at~\url{https://github.com/microsoft/Swin-Transformer}.
Encoder-decoder models have made great progress on handwritten mathematical expression recognition recently. However, it is still a challenge for existing methods to assign attention to image features accurately. Moreover, those encoder-decoder models usually adopt RNN-based models in their decoder part, which makes them inefficient in processing long $\LaTeX{}$ sequences. In this paper, a transformer-based decoder is employed to replace RNN-based ones, which makes the whole model architecture very concise. Furthermore, a novel training strategy is introduced to fully exploit the potential of the transformer in bidirectional language modeling. Compared to several methods that do not use data augmentation, experiments demonstrate that our model improves the ExpRate of current state-of-the-art methods on CROHME 2014 by 2.23%. Similarly, on CROHME 2016 and CROHME 2019, we improve the ExpRate by 1.92% and 2.28% respectively.
Attention-based encoder-decoder framework is widely used in the scene text recognition task. However, for the current state-of-the-art(SOTA) methods, there is room for improvement in terms of the efficient usage of local visual and global context information of the input text image, as well as the robust correlation between the scene processing module(encoder) and the text processing module(decoder). In this paper, we propose a Representation and Correlation Enhanced Encoder-Decoder Framework(RCEED) to address these deficiencies and break performance bottleneck. In the encoder module, local visual feature, global context feature, and position information are aligned and fused to generate a small-size comprehensive feature map. In the decoder module, two methods are utilized to enhance the correlation between scene and text feature space. 1) The decoder initialization is guided by the holistic feature and global glimpse vector exported from the encoder. 2) The feature enriched glimpse vector produced by the Multi-Head General Attention is used to assist the RNN iteration and the character prediction at each time step. Meanwhile, we also design a Layernorm-Dropout LSTM cell to improve model's generalization towards changeable texts. Extensive experiments on the benchmarks demonstrate the advantageous performance of RCEED in scene text recognition tasks, especially the irregular ones.
Recent advancements in computer vision promise to automate medical image analysis. Rheumatoid arthritis is an autoimmune disease that would profit from computer-based diagnosis, as there are no direct markers known, and doctors have to rely on manual inspection of X-ray images. In this work, we present a multi-task deep learning model that simultaneously learns to localize joints on X-ray images and diagnose two kinds of joint damage: narrowing and erosion. Additionally, we propose a modification of label smoothing, which combines classification and regression cues into a single loss and achieves 5% relative error reduction compared to standard loss functions. Our final model obtained 4th place in joint space narrowing and 5th place in joint erosion in the global RA2 DREAM challenge.
Optimizing the training of a machine learning pipeline helps in reducing training costs and improving model performance. One such optimizing strategy is quantum annealing, which is an emerging computing paradigm that has shown potential in optimizing the training of a machine learning model. The implementation of a physical quantum annealer has been realized by D-Wave systems and is available to the research community for experiments. Recent experimental results on a variety of machine learning applications using quantum annealing have shown interesting results where the performance of classical machine learning techniques is limited by limited training data and high dimensional features. This article explores the application of D-Wave's quantum annealer for optimizing machine learning pipelines for real-world classification problems. We review the application domains on which a physical quantum annealer has been used to train machine learning classifiers. We discuss and analyze the experiments performed on the D-Wave quantum annealer for applications such as image recognition, remote sensing imagery, computational biology, and particle physics. We discuss the possible advantages and the problems for which quantum annealing is likely to be advantageous over classical computation.
In this paper, we propose a method to find local-geometry-aware traversal directions on the intermediate latent space of Generative Adversarial Networks (GANs). These directions are defined as an ordered basis of tangent space at a latent code. Motivated by the intrinsic sparsity of the latent space, the basis is discovered by solving the low-rank approximation problem of the differential of the partial network. Moreover, the local traversal basis leads to a natural iterative traversal on the latent space. Iterative Curve-Traversal shows stable traversal on images, since the trajectory of latent code stays close to the latent space even under the strong perturbations compared to the linear traversal. This stability provides far more diverse variations of the given image. Although the proposed method can be applied to various GAN models, we focus on the W-space of the StyleGAN2, which is renowned for showing the better disentanglement of the latent factors of variation. Our quantitative and qualitative analysis provides evidence showing that the W-space is still globally warped while showing a certain degree of global consistency of interpretable variation. In particular, we introduce some metrics on the Grassmannian manifolds to quantify the global warpage of the W-space and the subspace traversal to test the stability of traversal directions.
In the field of forensic imaging, it is important to be able to extract a 'camera fingerprint' from one or a small set of images known to have been taken by the same camera. Ideally, that fingerprint would be used to identify an individual source camera. Camera fingerprint is based on certain kind of random noise present in all image sensors that is due to manufacturing imperfections and thus unique and impossible to avoid. PRNU (Photo-Response Non-Uniformity) has become the most widely used method for SCI (Source Camera Identification). In this paper, we design a set of 'attacks' to a PRNU based SCI system and we measure the success of each method. We understand an attack method as any processing that alters minimally image quality and that is designed to fool PRNU detectors (or, generalizing, any camera fingerprint detector). The PRNU based SCI system was taken from an outstanding reference that is publicly available.
The Intelligent Transportation Systems (ITS) are the subject of a world economic competition. They are the application of new information and communication technologies in the transport sector, to make the infrastructures more efficient, more reliable and more ecological. License Plates Recognition (LPR) is the key module of these systems, in which the License Plate Localization (LPL) is the most important stage, because it determines the speed and robustness of this module. Thus, during this step the algorithm must process the image and overcome several constraints as climatic and lighting conditions, sensors and angles variety, LPs no-standardization, and the real time processing. This paper presents a classification and comparison of License Plates Localization (LPL) algorithms and describes the advantages, disadvantages and improvements made by each of them