U-Net has been providing state-of-the-art performance in many medical image segmentation problems. Many modifications have been proposed for U-Net, such as attention U-Net, recurrent residual convolutional U-Net (R2-UNet), and U-Net with residual blocks or blocks with dense connections. However, all these modifications have an encoder-decoder structure with skip connections, and the number of paths for information flow is limited. We propose LadderNet in this paper, which can be viewed as a chain of multiple U-Nets. Instead of only one pair of encoder branch and decoder branch in U-Net, a LadderNet has multiple pairs of encoder-decoder branches, and has skip connections between every pair of adjacent decoder and decoder branches in each level. Inspired by the success of ResNet and R2-UNet, we use modified residual blocks where two convolutional layers in one block share the same weights. A LadderNet has more paths for information flow because of skip connections and residual blocks, and can be viewed as an ensemble of Fully Convolutional Networks (FCN). The equivalence to an ensemble of FCNs improves segmentation accuracy, while the shared weights within each residual block reduce parameter number. Semantic segmentation is essential for retinal disease detection. We tested LadderNet on two benchmark datasets for blood vessel segmentation in retinal images, and achieved superior performance over methods in the literature.
Prior work to infer 3D texture use either texture atlases, which require uv-mappings and hence have discontinuities, or colored voxels, which are memory inefficient and limited in resolution. Recent work, predicts RGB color at every XYZ coordinate forming a texture field, but focus on completing texture given a single 2D image. Instead, we focus on 3D texture and geometry completion from partial and incomplete 3D scans. IF-Nets have recently achieved state-of-the-art results on 3D geometry completion using a multi-scale deep feature encoding, but the outputs lack texture. In this work, we generalize IF-Nets to texture completion from partial textured scans of humans and arbitrary objects. Our key insight is that 3D texture completion benefits from incorporating local and global deep features extracted from both the 3D partial texture and completed geometry. Specifically, given the partial 3D texture and the 3D geometry completed with IF-Nets, our model successfully in-paints the missing texture parts in consistence with the completed geometry. Our model won the SHARP ECCV'20 challenge, achieving highest performance on all challenges.
Clinical decision support using deep neural networks has become a topic of steadily growing interest. While recent work has repeatedly demonstrated that deep learning offers major advantages for medical image classification over traditional methods, clinicians are often hesitant to adopt the technology because its underlying decision-making process is considered to be intransparent and difficult to comprehend. In recent years, this has been addressed by a variety of approaches that have successfully contributed to providing deeper insight. Most notably, additive feature attribution methods are able to propagate decisions back into the input space by creating a saliency map which allows the practitioner to "see what the network sees." However, the quality of the generated maps can become poor and the images noisy if only limited data is available - a typical scenario in clinical contexts. We propose a novel decision explanation scheme based on CycleGAN activation maximization which generates high-quality visualizations of classifier decisions even in smaller data sets. We conducted a user study in which these visualizations significantly outperformed existing methods on the LIDC dataset for lung lesion malignancy classification. With our approach we make a significant contribution to a better understanding of clinical decision support systems based on deep neural networks and thus aim to foster overall clinical acceptance.
This paper deals with a reduced reference (RR) image quality measure based on natural image statistics modeling. For this purpose, Tetrolet transform is used since it provides a convenient way to capture local geometric structures. This transform is applied to both reference and distorted images. Then, Gaussian Scale Mixture (GSM) is proposed to model subbands in order to take account statistical dependencies between tetrolet coefficients. In order to quantify the visual degradation, a measure based on Kullback Leibler Divergence (KLD) is provided. The proposed measure was tested on the Cornell VCL A-57 dataset and compared with other measures according to FR-TV1 VQEG framework.
In image classification tasks, the evaluation of models' robustness to increased dataset shifts with a probabilistic framework is very well studied. However, Object Detection (OD) tasks pose other challenges for uncertainty estimation and evaluation. For example, one needs to evaluate both the quality of the label uncertainty (i.e., what?) and spatial uncertainty (i.e., where?) for a given bounding box, but that evaluation cannot be performed with more traditional average precision metrics (e.g., mAP). In this paper, we adapt the well-established YOLOv3 architecture to generate uncertainty estimations by introducing stochasticity in the form of Monte Carlo Dropout (MC-Drop), and evaluate it across different levels of dataset shift. We call this novel architecture Stochastic-YOLO, and provide an efficient implementation to effectively reduce the burden of the MC-Drop sampling mechanism at inference time. Finally, we provide some sensitivity analyses, while arguing that Stochastic-YOLO is a sound approach that improves different components of uncertainty estimations, in particular spatial uncertainties.
Unsupervised image representations have significantly reduced the gap with supervised pretraining, notably with the recent achievements of contrastive learning methods. These contrastive methods typically work online and rely on a large number of explicit pairwise feature comparisons, which is computationally challenging. In this paper, we propose an online algorithm, SwAV, that takes advantage of contrastive methods without requiring to compute pairwise comparisons. Specifically, our method simultaneously clusters the data while enforcing consistency between cluster assignments produced for different augmentations (or views) of the same image, instead of comparing features directly as in contrastive learning. Simply put, we use a swapped prediction mechanism where we predict the cluster assignment of a view from the representation of another view. Our method can be trained with large and small batches and can scale to unlimited amounts of data. Compared to previous contrastive methods, our method is more memory efficient since it does not require a large memory bank or a special momentum network. In addition, we also propose a new data augmentation strategy, multi-crop, that uses a mix of views with different resolutions in place of two full-resolution views, without increasing the memory or compute requirements much. We validate our findings by achieving 75.3% top-1 accuracy on ImageNet with ResNet-50, as well as surpassing supervised pretraining on all the considered transfer tasks.
Drowsiness driving is a major cause of traffic accidents and thus numerous previous researches have focused on driver drowsiness detection. Many drive relevant factors have been taken into consideration for fatigue detection and can lead to high precision, but there are still several serious constraints, such as most existing models are environmentally susceptible. In this paper, fatigue detection is considered as temporal action detection problem instead of image classification. The proposed detection system can be divided into four parts: (1) Localize the key patches of the detected driver picture which are critical for fatigue detection and calculate the corresponding optical flow. (2) Contrast Limited Adaptive Histogram Equalization (CLAHE) is used in our system to reduce the impact of different light conditions. (3) Three individual two-stream networks combined with attention mechanism are designed for each feature to extract temporal information. (4) The outputs of the three sub-networks will be concatenated and sent to the fully-connected network, which judges the status of the driver. The drowsiness detection system is trained and evaluated on the famous Nation Tsing Hua University Driver Drowsiness Detection (NTHU-DDD) dataset and we obtain an accuracy of 94.46%, which outperforms most existing fatigue detection models.
Chest X-ray is one of the most widespread examinations of the human body. In interventional radiology, its use is frequently associated with the need to visualize various tube-like objects, such as puncture needles, guiding sheaths, wires, and catheters. Detection and precise localization of these tube-like objects in the X-ray images is, therefore, of utmost value, catalyzing the development of accurate target-specific segmentation algorithms. Similar to the other medical imaging tasks, the manual pixel-wise annotation of the tubes is a resource-consuming process. In this work, we aim to alleviate the lack of the annotated images by using artificial data. Specifically, we present an approach for synthetic data generation of the tube-shaped objects, with a generative adversarial network being regularized with a prior-shape constraint. Our method eliminates the need for paired image--mask data and requires only a weakly-labeled dataset (10--20 images) to reach the accuracy of the fully-supervised models. We report the applicability of the approach for the task of segmenting tubes and catheters in the X-ray images, whereas the results should also hold for the other imaging modalities.
A major obstacle in radar based methods for concealed object detection on humans and seamless integration into security and access control system is the difficulty in collecting high quality radar signal data. Generative adversarial networks (GAN) have shown promise in data generation application in the fields of image and audio processing. As such, this paper proposes the design of a GAN for application in radar signal generation. Data collected using the Finite-Difference Time-Domain (FDTD) method on three concealed object classes (no object, large object, and small object) were used as training data to train a GAN to generate radar signal samples for each class. The proposed GAN generated radar signal data which was indistinguishable from the training data by qualitative human observers.
Neural Architecture Search (NAS) aims to optimize deep neural networks' architecture for better accuracy or smaller computational cost and has recently gained more research interests. Despite various successful approaches proposed to solve the NAS task, the landscape of it, along with its properties, are rarely investigated. In this paper, we argue for the necessity of studying the landscape property thereof and propose to use the so-called Exploratory Landscape Analysis (ELA) techniques for this goal. Taking a broad set of designs of the deep convolutional network, we conduct extensive experimentation to obtain their performance. Based on our analysis of the experimental results, we observed high similarities between well-performing architecture designs, which is then used to significantly narrow the search space to improve the efficiency of any NAS algorithm. Moreover, we extract the ELA features over the NAS landscapes on three common image classification data sets, MNIST, Fashion, and CIFAR-10, which shows that the NAS landscape can be distinguished for those three data sets. Also, when comparing to the ELA features of the well-known Black-Box Optimization Benchmarking (BBOB) problem set, we found out that the NAS landscapes surprisingly form a new problem class on its own, which can be separated from all $24$ BBOB problems. Given this interesting observation, we, therefore, state the importance of further investigation on selecting an efficient optimizer for the NAS landscape as well as the necessity of augmenting the current benchmark problem set.