Language guided image inpainting aims to fill in the defective regions of an image under the guidance of text while keeping non-defective regions unchanged. However, the encoding process of existing models suffers from either receptive spreading of defective regions or information loss of non-defective regions, giving rise to visually unappealing inpainting results. To address the above issues, this paper proposes N\"UWA-LIP by incorporating defect-free VQGAN (DF-VQGAN) with multi-perspective sequence to sequence (MP-S2S). In particular, DF-VQGAN introduces relative estimation to control receptive spreading and adopts symmetrical connections to protect information. MP-S2S further enhances visual information from complementary perspectives, including both low-level pixels and high-level tokens. Experiments show that DF-VQGAN performs more robustness than VQGAN. To evaluate the inpainting performance of our model, we built up 3 open-domain benchmarks, where N\"UWA-LIP is also superior to recent strong baselines.
Medical image segmentation plays an irreplaceable role in computer-assisted diagnosis, treatment planning, and following-up. Collecting and annotating a large-scale dataset is crucial to training a powerful segmentation model, but producing high-quality segmentation masks is an expensive and time-consuming procedure. Recently, weakly-supervised learning that uses sparse annotations (points, scribbles, bounding boxes) for network training has achieved encouraging performance and shown the potential for annotation cost reduction. However, due to the limited supervision signal of sparse annotations, it is still challenging to employ them for networks training directly. In this work, we propose a simple yet efficient scribble-supervised image segmentation method and apply it to cardiac MRI segmentation. Specifically, we employ a dual-branch network with one encoder and two slightly different decoders for image segmentation and dynamically mix the two decoders' predictions to generate pseudo labels for auxiliary supervision. By combining the scribble supervision and auxiliary pseudo labels supervision, the dual-branch network can efficiently learn from scribble annotations end-to-end. Experiments on the public ACDC dataset show that our method performs better than current scribble-supervised segmentation methods and also outperforms several semi-supervised segmentation methods.
Deep network-based image Compressed Sensing (CS) has attracted much attention in recent years. However, the existing deep network-based CS schemes either reconstruct the target image in a block-by-block manner that leads to serious block artifacts or train the deep network as a black box that brings about limited insights of image prior knowledge. In this paper, a novel image CS framework using non-local neural network (NL-CSNet) is proposed, which utilizes the non-local self-similarity priors with deep network to improve the reconstruction quality. In the proposed NL-CSNet, two non-local subnetworks are constructed for utilizing the non-local self-similarity priors in the measurement domain and the multi-scale feature domain respectively. Specifically, in the subnetwork of measurement domain, the long-distance dependencies between the measurements of different image blocks are established for better initial reconstruction. Analogically, in the subnetwork of multi-scale feature domain, the affinities between the dense feature representations are explored in the multi-scale space for deep reconstruction. Furthermore, a novel loss function is developed to enhance the coupling between the non-local representations, which also enables an end-to-end training of NL-CSNet. Extensive experiments manifest that NL-CSNet outperforms existing state-of-the-art CS methods, while maintaining fast computational speed.
Spatial resolution of medical images can be improved using super-resolution methods. Real Enhanced Super Resolution Generative Adversarial Network (Real-ESRGAN) is one of the recent effective approaches utilized to produce higher resolution images, given input images of lower resolution. In this paper, we apply this method to enhance the spatial resolution of 2D MR images. In our proposed approach, we slightly modify the structure of the Real-ESRGAN to train 2D Magnetic Resonance images (MRI) taken from the Brain Tumor Segmentation Challenge (BraTS) 2018 dataset. The obtained results are validated qualitatively and quantitatively by computing SSIM (Structural Similarity Index Measure), NRMSE (Normalized Root Mean Square Error), MAE (Mean Absolute Error), and VIF (Visual Information Fidelity) values.
Transformers have resulted in remarkable achievements in the field of image processing. Inspired by this great success, the application of Transformers to 3D point cloud processing has drawn more and more attention. This paper presents a novel point cloud representational learning network, 3D Point Cloud Transformer with Dual Self-attention (3DPCT) and an encoder-decoder structure. Specifically, 3DPCT has a hierarchical encoder, which contains two local-global dual-attention modules for the classification task (three modules for the segmentation task), with each module consisting of a Local Feature Aggregation (LFA) block and a Global Feature Learning (GFL) block. The GFL block is dual self-attention, with both point-wise and channel-wise self-attention to improve feature extraction. Moreover, in LFA, to better leverage the local information extracted, a novel point-wise self-attention model, named as Point-Patch Self-Attention (PPSA), is designed. The performance is evaluated on both classification and segmentation datasets, containing both synthetic and real-world data. Extensive experiments demonstrate that the proposed method achieved state-of-the-art results on both classification and segmentation tasks.
Over past few years afterward the birth of ResNet, skip connection has become the defacto standard for the design of modern architectures due to its widespread adoption, easy optimization and proven performance. Prior work has explained the effectiveness of the skip connection mechanism from different perspectives. In this work, we deep dive into the model's behaviors with skip connections which can be formulated as a learnable Markov chain. An efficient Markov chain is preferred as it always maps the input data to the target domain in a better way. However, while a model is explained as a Markov chain, it is not guaranteed to be optimized following an efficient Markov chain by existing SGD-based optimizers which are prone to get trapped in local optimal points. In order to towards a more efficient Markov chain, we propose a simple routine of penal connection to make any residual-like model become a learnable Markov chain. Aside from that, the penal connection can also be viewed as a particular model regularization and can be easily implemented with one line of code in the most popular deep learning frameworks~\footnote{Source code: \url{https://github.com/densechen/penal-connection}}. The encouraging experimental results in multi-modal translation and image recognition empirically confirm our conjecture of the learnable Markov chain view and demonstrate the superiority of the proposed penal connection.
State-of-the-art object detectors have been shown effective in many applications. Usually, their performance is evaluated based on accuracy metrics such as mean Average Precision. In this paper, we consider a safety property of 3D object detectors in the context of Autonomous Driving (AD). In particular, we propose an essential safety requirement for object detectors in AD and formulate it into a specification. During the formulation, we find that abstracting 3D objects with projected 2D bounding boxes on the image and bird's-eye-view planes allows for a necessary and sufficient condition to the proposed safety requirement. We then leverage the analysis and derive qualitative and quantitative safety metrics based on the Intersection-over-Ground-Truth measure and a distance ratio between predictions and ground truths. Finally, for continual improvement, we formulate safety losses that can be used to optimize object detectors towards higher safety scores. Our experiments with public models on the MMDetection3D library and the nuScenes datasets demonstrate the validity of our consideration and proposals.
In the last decade, convolutional neural networks (ConvNets) have dominated the field of medical image analysis. However, it is found that the performances of ConvNets may still be limited by their inability to model long-range spatial relations between voxels in an image. Numerous vision Transformers have been proposed recently to address the shortcomings of ConvNets, demonstrating state-of-the-art performances in many medical imaging applications. Transformers may be a strong candidate for image registration because their self-attention mechanism enables a more precise comprehension of the spatial correspondence between moving and fixed images. In this paper, we present TransMorph, a hybrid Transformer-ConvNet model for volumetric medical image registration. We also introduce three variants of TransMorph, with two diffeomorphic variants ensuring the topology-preserving deformations and a Bayesian variant producing a well-calibrated registration uncertainty estimate. The proposed models are extensively validated against a variety of existing registration methods and Transformer architectures using volumetric medical images from two applications: inter-patient brain MRI registration and phantom-to-CT registration. Qualitative and quantitative results demonstrate that TransMorph and its variants lead to a substantial performance improvement over the baseline methods, demonstrating the effectiveness of Transformers for medical image registration.
Digital image watermarking seeks to protect the digital media information from unauthorized access, where the message is embedded into the digital image and extracted from it, even some noises or distortions are applied under various data processing including lossy image compression and interactive content editing. Traditional image watermarking solutions easily suffer from robustness when specified with some prior constraints, while recent deep learning-based watermarking methods could not tackle the information loss problem well under various separate pipelines of feature encoder and decoder. In this paper, we propose a novel digital image watermarking solution with a compact neural network, named Invertible Watermarking Network (IWN). Our IWN architecture is based on a single Invertible Neural Network (INN), this bijective propagation framework enables us to effectively solve the challenge of message embedding and extraction simultaneously, by taking them as a pair of inverse problems for each other and learning a stable invertible mapping. In order to enhance the robustness of our watermarking solution, we specifically introduce a simple but effective bit message normalization module to condense the bit message to be embedded, and a noise layer is designed to simulate various practical attacks under our IWN framework. Extensive experiments demonstrate the superiority of our solution under various distortions.
The Big Video Data generated in today's smart cities has raised concerns from its purposeful usage perspective, where surveillance cameras, among many others are the most prominent resources to contribute to the huge volumes of data, making its automated analysis a difficult task in terms of computation and preciseness. Violence Detection (VD), broadly plunging under Action and Activity recognition domain, is used to analyze Big Video data for anomalous actions incurred due to humans. The VD literature is traditionally based on manually engineered features, though advancements to deep learning based standalone models are developed for real-time VD analysis. This paper focuses on overview of deep sequence learning approaches along with localization strategies of the detected violence. This overview also dives into the initial image processing and machine learning-based VD literature and their possible advantages such as efficiency against the current complex models. Furthermore,the datasets are discussed, to provide an analysis of the current models, explaining their pros and cons with future directions in VD domain derived from an in-depth analysis of the previous methods.