Manifold models consider natural-image patches to be on a low-dimensional manifold embedded in a high dimensional state space and each patch and its similar patches to approximately lie on a linear affine subspace. Manifold models are closely related to semi-local similarity, a well-known property of natural images, referring to that for most natural-image patches, several similar patches can be found in its spatial neighborhood. Many approaches to single image interpolation use manifold models to exploit semi-local similarity by two mutually exclusive parts: i) searching each target patch's similar patches and ii) operating on the searched similar patches, the target patch and the measured input pixels to estimate the target patch. Unfortunately, aliasing in the input image makes it challenging for both parts. A very few works explicitly deal with those challenges and only ad-hoc solutions are proposed. To overcome the challenge in the first part, we propose a carefully-designed adaptive technique to remove aliasing in severely aliased regions, which cannot be removed from traditional techniques. This technique enables reliable identification of similar patches even in the presence of strong aliasing. To overcome the challenge in the second part, we propose to use the aliasing-removed image to guide the initialization of the interpolated image and develop a progressive scheme to refine the interpolated image based on manifold models. Experimental results demonstrate that our approach reconstructs edges with both smoothness along contours and sharpness across profiles, and achieves an average Peak Signal-to-Noise Ratio (PSNR) significantly higher than existing model-based approaches.
Generative learning is a powerful tool for representation learning, and shows particular promise for problems in biomedical imaging. However, in this context, sampling from the distribution is secondary to finding representations of real images, which often come with labels and explicitly represent the content and quality of the target distribution. It remains difficult to faithfully reconstruct images from generative models, particularly those as complex as histological images. In this work, two existing methods (autoencoders and adversarial latent autoencoders) are combined in attempt to improve our ability to encode and decode real images of non-melanoma skin cancer, specifically intra-epidermal carcinoma (IEC). Utilising a dataset of high-quality images of IEC (256 x 256), this work assesses the result of both image reconstruction quality and representation learning. It is shown that adversarial training can improve baseline FID scores from 76 to 50, and that benchmarks on representation learning can be improved by up to 3%. Smooth and realistic interpolations of the variation in the morphological structure are also presented for the first time, positioning representation learning as a promising direction in the context of computational pathology.
Deep learning provides a new avenue for image restoration, which demands a delicate balance between fine-grained details and high-level contextualized information during recovering the latent clear image. In practice, however, existing methods empirically construct encapsulated end-to-end mapping networks without deepening into the rationality, and neglect the intrinsic prior knowledge of restoration task. To solve the above problems, inspired by Taylor's Approximations, we unfold Taylor's Formula to construct a novel framework for image restoration. We find the main part and the derivative part of Taylor's Approximations take the same effect as the two competing goals of high-level contextualized information and spatial details of image restoration respectively. Specifically, our framework consists of two steps, correspondingly responsible for the mapping and derivative functions. The former first learns the high-level contextualized information and the later combines it with the degraded input to progressively recover local high-order spatial details. Our proposed framework is orthogonal to existing methods and thus can be easily integrated with them for further improvement, and extensive experiments demonstrate the effectiveness and scalability of our proposed framework.
Medical image segmentation is one of the fundamental problems for artificial intelligence-based clinical decision systems. Current automatic medical image segmentation methods are often failed to meet clinical requirements. As such, a series of interactive segmentation algorithms are proposed to utilize expert correction information. However, existing methods suffer from some segmentation refining failure problems after long-term interactions and some cost problems from expert annotation, which hinder clinical applications. This paper proposes an interactive segmentation framework, called interactive MEdical segmentation with self-adaptive Confidence CAlibration (MECCA), by introducing the corrective action evaluation, which combines the action-based confidence learning and multi-agent reinforcement learning (MARL). The evaluation is established through a novel action-based confidence network, and the corrective actions are obtained from MARL. Based on the confidential information, a self-adaptive reward function is designed to provide more detailed feedback, and a simulated label generation mechanism is proposed on unsupervised data to reduce over-reliance on labeled data. Experimental results on various medical image datasets have shown the significant performance of the proposed algorithm.
Hyperspectral image (HSI) classification is the most vibrant area of research in the hyperspectral community due to the rich spectral information contained in HSI can greatly aid in identifying objects of interest. However, inherent non-linearity between materials and the corresponding spectral profiles brings two major challenges in HSI classification: interclass similarity and intraclass variability. Many advanced deep learning methods have attempted to address these issues from the perspective of a region/patch-based approach, instead of a pixel-based alternate. However, the patch-based approaches hypothesize that neighborhood pixels of a target pixel in a fixed spatial window belong to the same class. And this assumption is not always true. To address this problem, we herein propose a new deep learning architecture, namely Gramian Angular Field encoded Neighborhood Attention U-Net (GAF-NAU), for pixel-based HSI classification. The proposed method does not require regions or patches centered around a raw target pixel to perform 2D-CNN based classification, instead, our approach transforms 1D pixel vector in HSI into 2D angular feature space using Gramian Angular Field (GAF) and then embed it to a new neighborhood attention network to suppress irrelevant angular feature while emphasizing on pertinent features useful for HSI classification task. Evaluation results on three publicly available HSI datasets demonstrate the superior performance of the proposed model.
Visual Entailment with natural language explanations aims to infer the relationship between a text-image pair and generate a sentence to explain the decision-making process. Previous methods rely mainly on a pre-trained vision-language model to perform the relation inference and a language model to generate the corresponding explanation. However, the pre-trained vision-language models mainly build token-level alignment between text and image yet ignore the high-level semantic alignment between the phrases (chunks) and visual contents, which is critical for vision-language reasoning. Moreover, the explanation generator based only on the encoded joint representation does not explicitly consider the critical decision-making points of relation inference. Thus the generated explanations are less faithful to visual-language reasoning. To mitigate these problems, we propose a unified Chunk-aware Alignment and Lexical Constraint based method, dubbed as CALeC. It contains a Chunk-aware Semantic Interactor (arr. CSI), a relation inferrer, and a Lexical Constraint-aware Generator (arr. LeCG). Specifically, CSI exploits the sentence structure inherent in language and various image regions to build chunk-aware semantic alignment. Relation inferrer uses an attention-based reasoning network to incorporate the token-level and chunk-level vision-language representations. LeCG utilizes lexical constraints to expressly incorporate the words or chunks focused by the relation inferrer into explanation generation, improving the faithfulness and informativeness of the explanations. We conduct extensive experiments on three datasets, and experimental results indicate that CALeC significantly outperforms other competitor models on inference accuracy and quality of generated explanations.
Single image dehazing is a prerequisite which affects the performance of many computer vision tasks and has attracted increasing attention in recent years. However, most existing dehazing methods emphasize more on haze removal but less on the detail recovery of the dehazed images. In this paper, we propose a single image dehazing method with an independent Detail Recovery Network (DRN), which considers capturing the details from the input image over a separate network and then integrates them into a coarse dehazed image. The overall network consists of two independent networks, named DRN and the dehazing network respectively. Specifically, the DRN aims to recover the dehazed image details through local and global branches respectively. The local branch can obtain local detail information through the convolution layer and the global branch can capture more global information by the Smooth Dilated Convolution (SDC). The detail feature map is fused into the coarse dehazed image to obtain the dehazed image with rich image details. Besides, we integrate the DRN, the physical-model-based dehazing network and the reconstruction loss into an end-to-end joint learning framework. Extensive experiments on the public image dehazing datasets (RESIDE-Indoor, RESIDE-Outdoor and the TrainA-TestA) illustrate the effectiveness of the modules in the proposed method and show that our method outperforms the state-of-the-art dehazing methods both quantitatively and qualitatively. The code is released in https://github.com/YanLi-LY/Dehazing-DRN.
Segmentation of marine oil spills in Synthetic Aperture Radar (SAR) images is a challenging task because of the complexity and irregularities in SAR images. In this work, we aim to develop an effective segmentation method which addresses marine oil spill identification in SAR images by investigating the distribution representation of SAR images. To seek effective oil spill segmentation, we revisit the SAR imaging mechanism in order to attain the probability distribution representation of oil spill SAR images, in which the characteristics of SAR images are properly modelled. We then exploit the distribution representation to formulate the segmentation energy functional, by which oil spill characteristics are incorporated to guide oil spill segmentation. Moreover, the oil spill segmentation model contains the oil spill contour regularisation term and the updated level set regularisation term which enhance the representational power of the segmentation energy functional. Benefiting from the synchronisation of SAR image representation and oil spill segmentation, our proposed method establishes an effective oil spill segmentation framework. Experimental evaluations demonstrate the effectiveness of our proposed segmentation framework for different types of marine oil spill SAR image segmentation.
Decomposing an image through Fourier, DCT or wavelet transforms is still a common approach in digital image processing, in number of applications such as denoising. In this context, data-driven dictionaries and in particular exploiting the redundancy withing patches extracted from one or several images allowed important improvements. This paper proposes an original idea of constructing such an image-dependent basis inspired by the principles of quantum many-body physics. The similarity between two image patches is introduced in the formalism through a term akin to interaction terms in quantum mechanics. The main contribution of the paper is thus to introduce this original way of exploiting quantum many-body ideas in image processing, which opens interesting perspectives in image denoising. The potential of the proposed adaptive decomposition is illustrated through image denoising in presence of additive white Gaussian noise, but the method can be used for other types of noise such as image-dependent noise as well. Finally, the results show that our method achieves comparable or slightly better results than existing approaches.
Dropout is designed to relieve the overfitting problem in high-level vision tasks but is rarely applied in low-level vision tasks, like image super-resolution (SR). As a classic regression problem, SR exhibits a different behaviour as high-level tasks and is sensitive to the dropout operation. However, in this paper, we show that appropriate usage of dropout benefits SR networks and improves the generalization ability. Specifically, dropout is better embedded at the end of the network and is significantly helpful for the multi-degradation settings. This discovery breaks our common sense and inspires us to explore its working mechanism. We further use two analysis tools -- one is from recent network interpretation works, and the other is specially designed for this task. The analysis results provide side proofs to our experimental findings and show us a new perspective to understand SR networks.