We present a method for estimating articulated human pose from a single static image based on a graphical model with novel pairwise relations that make adaptive use of local image measurements. More precisely, we specify a graphical model for human pose which exploits the fact the local image measurements can be used both to detect parts (or joints) and also to predict the spatial relationships between them (Image Dependent Pairwise Relations). These spatial relationships are represented by a mixture model. We use Deep Convolutional Neural Networks (DCNNs) to learn conditional probabilities for the presence of parts and their spatial relationships within image patches. Hence our model combines the representational flexibility of graphical models with the efficiency and statistical power of DCNNs. Our method significantly outperforms the state of the art methods on the LSP and FLIC datasets and also performs very well on the Buffy dataset without any training.
In computer vision, convolutional networks (CNNs) often adopts pooling to enlarge receptive field which has the advantage of low computational complexity. However, pooling can cause information loss and thus is detrimental to further operations such as features extraction and analysis. Recently, dilated filter has been proposed to trade off between receptive field size and efficiency. But the accompanying gridding effect can cause a sparse sampling of input images with checkerboard patterns. To address this problem, in this paper, we propose a novel multi-level wavelet CNN (MWCNN) model to achieve better trade-off between receptive field size and computational efficiency. The core idea is to embed wavelet transform into CNN architecture to reduce the resolution of feature maps while at the same time, increasing receptive field. Specifically, MWCNN for image restoration is based on U-Net architecture, and inverse wavelet transform (IWT) is deployed to reconstruct the high resolution (HR) feature maps. The proposed MWCNN can also be viewed as an improvement of dilated filter and a generalization of average pooling, and can be applied to not only image restoration tasks, but also any CNNs requiring a pooling operation. The experimental results demonstrate effectiveness of the proposed MWCNN for tasks such as image denoising, single image super-resolution, JPEG image artifacts removal and object classification.
We propose Unicoder-VL, a universal encoder that aims to learn joint representations of vision and language in a pre-training manner. Borrow ideas from cross-lingual pre-trained models, such as XLM and Unicoder, both visual and linguistic contents are fed into a multi-layer transformer for the cross-modal pre-training, where three pre-trained tasks are employed, including masked language model, masked object label prediction and visual-linguistic matching. The first two tasks learn context-aware representations for input tokens based on linguistic and visual contents jointly. The last task tries to predict whether an image and a text describe each other. After pretraining on large amounts of image-caption pairs, we transfer Unicoder-VL to image-text retrieval tasks with just one additional output layer, and achieve state-of-the-art performances on both MSCOCO and Flicker30K.
Since the introduction of optical coherence tomography (OCT), it has been possible to study the complex 3D morphological changes of the optic nerve head (ONH) tissues that occur along with the progression of glaucoma. Although several deep learning (DL) techniques have been recently proposed for the automated extraction (segmentation) and quantification of these morphological changes, the device specific nature and the difficulty in preparing manual segmentations (training data) limit their clinical adoption. With several new manufacturers and next-generation OCT devices entering the market, the complexity in deploying DL algorithms clinically is only increasing. To address this, we propose a DL based 3D segmentation framework that is easily translatable across OCT devices in a label-free manner (i.e. without the need to manually re-segment data for each device). Specifically, we developed 2 sets of DL networks. The first (referred to as the enhancer) was able to enhance OCT image quality from 3 OCT devices, and harmonized image-characteristics across these devices. The second performed 3D segmentation of 6 important ONH tissue layers. We found that the use of the enhancer was critical for our segmentation network to achieve device independency. In other words, our 3D segmentation network trained on any of 3 devices successfully segmented ONH tissue layers from the other two devices with high performance (Dice coefficients > 0.92). With such an approach, we could automatically segment images from new OCT devices without ever needing manual segmentation data from such devices.
In this paper we are proposing the use of Kaniadakis entropy in the bi-level thresholding of images, in the framework of a maximum entropy principle. We discuss the role of its entropic index in determining the threshold and in driving an "image transition", that is, an abrupt transition in the appearance of the corresponding bi-level image. Some examples are proposed to illustrate the method and for comparing it to the approach which is using the Tsallis entropy.
We propose an unsupervised deep learning method for atlas based registration to achieve segmentation and spatial alignment of the embryonic brain in a single framework. Our approach consists of two sequential networks with a specifically designed loss function to address the challenges in 3D first trimester ultrasound. The first part learns the affine transformation and the second part learns the voxelwise nonrigid deformation between the target image and the atlas. We trained this network end-to-end and validated it against a ground truth on synthetic datasets designed to resemble the challenges present in 3D first trimester ultrasound. The method was tested on a dataset of human embryonic ultrasound volumes acquired at 9 weeks gestational age, which showed alignment of the brain in some cases and gave insight in open challenges for the proposed method. We conclude that our method is a promising approach towards fully automated spatial alignment and segmentation of embryonic brains in 3D ultrasound.
This paper presents a novel framework for visual object recognition using infinite-dimensional covariance operators of input features in the paradigm of kernel methods on infinite-dimensional Riemannian manifolds. Our formulation provides in particular a rich representation of image features by exploiting their non-linear correlations. Theoretically, we provide a finite-dimensional approximation of the Log-Hilbert-Schmidt (Log-HS) distance between covariance operators that is scalable to large datasets, while maintaining an effective discriminating capability. This allows us to efficiently approximate any continuous shift-invariant kernel defined using the Log-HS distance. At the same time, we prove that the Log-HS inner product between covariance operators is only approximable by its finite-dimensional counterpart in a very limited scenario. Consequently, kernels defined using the Log-HS inner product, such as polynomial kernels, are not scalable in the same way as shift-invariant kernels. Computationally, we apply the approximate Log-HS distance formulation to covariance operators of both handcrafted and convolutional features, exploiting both the expressiveness of these features and the power of the covariance representation. Empirically, we tested our framework on the task of image classification on twelve challenging datasets. In almost all cases, the results obtained outperform other state of the art methods, demonstrating the competitiveness and potential of our framework.
We present a visualization algorithm based on a novel unsupervised Siamese neural network training regime and loss function, called Differentiating Embedding Networks (DEN). The Siamese neural network finds differentiating or similar features between specific pairs of samples in a dataset, and uses these features to embed the dataset in a lower dimensional space where it can be visualized. Unlike existing visualization algorithms such as UMAP or $t$-SNE, DEN is parametric, meaning it can be interpreted by techniques such as SHAP. To interpret DEN, we create an end-to-end parametric clustering algorithm on top of the visualization, and then leverage SHAP scores to determine which features in the sample space are important for understanding the structures shown in the visualization based on the clusters found. We compare DEN visualizations with existing techniques on a variety of datasets, including image and scRNA-seq data. We then show that our clustering algorithm performs similarly to the state of the art despite not having prior knowledge of the number of clusters, and sets a new state of the art on FashionMNIST. Finally, we demonstrate finding differentiating features of a dataset. Code available at https://github.com/isaacrob/DEN
This paper focuses on semantic scene completion, a task for producing a complete 3D voxel representation of volumetric occupancy and semantic labels for a scene from a single-view depth map observation. Previous work has considered scene completion and semantic labeling of depth maps separately. However, we observe that these two problems are tightly intertwined. To leverage the coupled nature of these two tasks, we introduce the semantic scene completion network (SSCNet), an end-to-end 3D convolutional network that takes a single depth image as input and simultaneously outputs occupancy and semantic labels for all voxels in the camera view frustum. Our network uses a dilation-based 3D context module to efficiently expand the receptive field and enable 3D context learning. To train our network, we construct SUNCG - a manually created large-scale dataset of synthetic 3D scenes with dense volumetric annotations. Our experiments demonstrate that the joint model outperforms methods addressing each task in isolation and outperforms alternative approaches on the semantic scene completion task.
Medical imaging AI systems such as disease classification and segmentation are increasingly inspired and transformed from computer vision based AI systems. Although an array of adversarial training and/or loss function based defense techniques have been developed and proved to be effective in computer vision, defending against adversarial attacks on medical images remains largely an uncharted territory due to the following unique challenges: 1) label scarcity in medical images significantly limits adversarial generalizability of the AI system; 2) vastly similar and dominant fore- and background in medical images make it hard samples for learning the discriminating features between different disease classes; and 3) crafted adversarial noises added to the entire medical image as opposed to the focused organ target can make clean and adversarial examples more discriminate than that between different disease classes. In this paper, we propose a novel robust medical imaging AI framework based on Semi-Supervised Adversarial Training (SSAT) and Unsupervised Adversarial Detection (UAD), followed by designing a new measure for assessing systems adversarial risk. We systematically demonstrate the advantages of our robust medical imaging AI system over the existing adversarial defense techniques under diverse real-world settings of adversarial attacks using a benchmark OCT imaging data set.