Coronary CT Angiography (CCTA) is susceptible to various distortions (e.g., artifacts and noise), which severely compromise the exact diagnosis of cardiovascular diseases. The appropriate CCTA Vessel-level Image Quality Assessment (CCTA VIQA) algorithm can be used to reduce the risk of error diagnosis. The primary challenges of CCTA VIQA are that the local part of coronary that determines final quality is hard to locate. To tackle the challenge, we formulate CCTA VIQA as a multiple-instance learning (MIL) problem, and exploit Transformer-based MIL backbone (termed as T-MIL) to aggregate the multiple instances along the coronary centerline into the final quality. However, not all instances are informative for final quality. There are some quality-irrelevant/negative instances intervening the exact quality assessment(e.g., instances covering only background or the coronary in instances is not identifiable). Therefore, we propose a Progressive Reinforcement learning based Instance Discarding module (termed as PRID) to progressively remove quality-irrelevant/negative instances for CCTA VIQA. Based on the above two modules, we propose a Reinforced Transformer Network (RTN) for automatic CCTA VIQA based on end-to-end optimization. Extensive experimental results demonstrate that our proposed method achieves the state-of-the-art performance on the real-world CCTA dataset, exceeding previous MIL methods by a large margin.
We present the Pathways Autoregressive Text-to-Image (Parti) model, which generates high-fidelity photorealistic images and supports content-rich synthesis involving complex compositions and world knowledge. Parti treats text-to-image generation as a sequence-to-sequence modeling problem, akin to machine translation, with sequences of image tokens as the target outputs rather than text tokens in another language. This strategy can naturally tap into the rich body of prior work on large language models, which have seen continued advances in capabilities and performance through scaling data and model sizes. Our approach is simple: First, Parti uses a Transformer-based image tokenizer, ViT-VQGAN, to encode images as sequences of discrete tokens. Second, we achieve consistent quality improvements by scaling the encoder-decoder Transformer model up to 20B parameters, with a new state-of-the-art zero-shot FID score of 7.23 and finetuned FID score of 3.22 on MS-COCO. Our detailed analysis on Localized Narratives as well as PartiPrompts (P2), a new holistic benchmark of over 1600 English prompts, demonstrate the effectiveness of Parti across a wide variety of categories and difficulty aspects. We also explore and highlight limitations of our models in order to define and exemplify key areas of focus for further improvements. See https://parti.research.google/ for high-resolution images.
Vertebral landmark localization is a crucial step for variant spine-related clinical applications, which requires detecting the corner points of 17 vertebrae. However, the neighbor landmarks often disturb each other for the homogeneous appearance of vertebrae, which makes vertebral landmark localization extremely difficult. In this paper, we propose multi-stage cascaded convolutional neural networks (CNNs) to split the single task into two sequential steps, i.e., center point localization to roughly locate 17 center points of vertebrae, and corner point localization to find 4 corner points for each vertebra without distracted by others. Landmarks in each step are located gradually from a set of initialized points by regressing offsets via cascaded CNNs. Principal Component Analysis (PCA) is employed to preserve a shape constraint in offset regression to resist the mutual attraction of vertebrae. We evaluate our method on the AASCE dataset that consists of 609 tight spinal anterior-posterior X-ray images and each image contains 17 vertebrae composed of the thoracic and lumbar spine for spinal shape characterization. Experimental results demonstrate our superior performance of vertebral landmark localization over other state-of-the-arts with the relative error decreasing from 3.2e-3 to 7.2e-4.
Global Positioning Systems (GPS) have played a crucial role in various navigation applications. Nevertheless, localizing the perfect destination within the last few meters remains an important but unresolved problem. Limited by the GPS positioning accuracy, navigation systems always show users a vicinity of a destination, but not its exact location. Street view images (SVI) in maps as an immersive media technology have served as an aid to provide the physical environment for human last-meters wayfinding. However, due to the large diversity of geographic context and acquisition conditions, the captured SVI always contains various distracting objects (e.g., pedestrians and vehicles), which will distract human visual attention from efficiently finding the destination in the last few meters. To address this problem, we highlight the importance of reducing visual distraction in image-based wayfinding by proposing a saliency-guided image inpainting framework. It aims at redirecting human visual attention from distracting objects to destination-related objects for more efficient and accurate wayfinding in the last meters. Specifically, a context-aware distracting object detection method driven by deep salient object detection has been designed to extract distracting objects from three semantic levels in SVI. Then we employ a large-mask inpainting method with fast Fourier convolutions to remove the detected distracting objects. Experimental results with both qualitative and quantitative analysis show that our saliency-guided inpainting method can not only achieve great perceptual quality in street view images but also redirect the human's visual attention to focus more on static location-related objects than distracting ones. The human-based evaluation also justified the effectiveness of our method in improving the efficiency of locating the target destination.
This paper reviews the NTIRE 2022 challenge on efficient single image super-resolution with focus on the proposed solutions and results. The task of the challenge was to super-resolve an input image with a magnification factor of $\times$4 based on pairs of low and corresponding high resolution images. The aim was to design a network for single image super-resolution that achieved improvement of efficiency measured according to several metrics including runtime, parameters, FLOPs, activations, and memory consumption while at least maintaining the PSNR of 29.00dB on DIV2K validation set. IMDN is set as the baseline for efficiency measurement. The challenge had 3 tracks including the main track (runtime), sub-track one (model complexity), and sub-track two (overall performance). In the main track, the practical runtime performance of the submissions was evaluated. The rank of the teams were determined directly by the absolute value of the average runtime on the validation set and test set. In sub-track one, the number of parameters and FLOPs were considered. And the individual rankings of the two metrics were summed up to determine a final ranking in this track. In sub-track two, all of the five metrics mentioned in the description of the challenge including runtime, parameter count, FLOPs, activations, and memory consumption were considered. Similar to sub-track one, the rankings of five metrics were summed up to determine a final ranking. The challenge had 303 registered participants, and 43 teams made valid submissions. They gauge the state-of-the-art in efficient single image super-resolution.
Image compression has raised widespread interest recently due to its significant importance for multimedia storage and transmission. Meanwhile, a reliable image quality assessment (IQA) for compressed images can not only help to verify the performance of various compression algorithms but also help to guide the compression optimization in turn. In this paper, we design a full-reference image quality assessment metric SwinIQA to measure the perceptual quality of compressed images in a learned Swin distance space. It is known that the compression artifacts are usually non-uniformly distributed with diverse distortion types and degrees. To warp the compressed images into the shared representation space while maintaining the complex distortion information, we extract the hierarchical feature representations from each stage of the Swin Transformer. Besides, we utilize cross attention operation to map the extracted feature representations into a learned Swin distance space. Experimental results show that the proposed metric achieves higher consistency with human's perceptual judgment compared with both traditional methods and learning-based methods on CLIC datasets.
Relational understanding is critical for a number of visually-rich documents (VRDs) understanding tasks. Through multi-modal pre-training, recent studies provide comprehensive contextual representations and exploit them as prior knowledge for downstream tasks. In spite of their impressive results, we observe that the widespread relational hints (e.g., relation of key/value fields on receipts) built upon contextual knowledge are not excavated yet. To mitigate this gap, we propose DocReL, a Document Relational Representation Learning framework. The major challenge of DocReL roots in the variety of relations. From the simplest pairwise relation to the complex global structure, it is infeasible to conduct supervised training due to the definition of relation varies and even conflicts in different tasks. To deal with the unpredictable definition of relations, we propose a novel contrastive learning task named Relational Consistency Modeling (RCM), which harnesses the fact that existing relations should be consistent in differently augmented positive views. RCM provides relational representations which are more compatible to the urgent need of downstream tasks, even without any knowledge about the exact definition of relation. DocReL achieves better performance on a wide variety of VRD relational understanding tasks, including table structure recognition, key information extraction and reading order detection.
Gene/protein interactions provide critical information for a thorough understanding of cellular processes. Recently, considerable interest and effort has been focused on the construction and analysis of genome-wide gene networks. The large body of biomedical literature is an important source of gene/protein interaction information. Recent advances in text mining tools have made it possible to automatically extract such documented interactions from free-text literature. In this paper, we propose a comprehensive framework for constructing and analyzing large-scale gene functional networks based on the gene/protein interactions extracted from biomedical literature repositories using text mining tools. Our proposed framework consists of analyses of the network topology, network topology-gene function relationship, and temporal network evolution to distill valuable information embedded in the gene functional interactions in literature. We demonstrate the application of the proposed framework using a testbed of P53-related PubMed abstracts, which shows that literature-based P53 networks exhibit small-world and scale-free properties. We also found that high degree genes in the literature-based networks have a high probability of appearing in the manually curated database and genes in the same pathway tend to form local clusters in our literature-based networks. Temporal analysis showed that genes interacting with many other genes tend to be involved in a large number of newly discovered interactions.
Predicting gene functions is a challenge for biologists in the post genomic era. Interactions among genes and their products compose networks that can be used to infer gene functions. Most previous studies adopt a linkage assumption, i.e., they assume that gene interactions indicate functional similarities between connected genes. In this study, we propose to use a gene's context graph, i.e., the gene interaction network associated with the focal gene, to infer its functions. In a kernel-based machine-learning framework, we design a context graph kernel to capture the information in context graphs. Our experimental study on a testbed of p53-related genes demonstrates the advantage of using indirect gene interactions and shows the empirical superiority of the proposed approach over linkage-assumption-based methods, such as the algorithm to minimize inconsistent connected genes and diffusion kernels.
The self-supervised Masked Image Modeling (MIM) schema, following "mask-and-reconstruct" pipeline of recovering contents from masked image, has recently captured the increasing interest in the multimedia community, owing to the excellent ability of learning visual representation from unlabeled data. Aiming at learning representations with high semantics abstracted, a group of works attempts to reconstruct non-semantic pixels with large-ratio masking strategy, which may suffer from "over-smoothing" problem, while others directly infuse semantics into targets in off-line way requiring extra data. Different from them, we shift the perspective to the Fourier domain which naturally has global perspective and present a new Masked Image Modeling (MIM), termed Geminated Gestalt Autoencoder (Ge$^2$-AE) for visual pre-training. Specifically, we equip our model with geminated decoders in charge of reconstructing image contents from both pixel and frequency space, where each other serves as not only the complementation but also the reciprocal constraints. Through this way, more robust representations can be learned in the pre-trained encoders, of which the effectiveness is confirmed by the juxtaposing experimental results on downstream recognition tasks. We also conduct several quantitative and qualitative experiments to investigate the learning behavior of our method. To our best knowledge, this is the first MIM work to solve the visual pre-training through the lens of frequency domain.