Feng Yang

Zhengzhong Tu, Hossein Talebi, Han Zhang et al.

Transformers have recently gained significant attention in the computer vision community. However, the lack of scalability of self-attention mechanisms with respect to image size has limited their wide adoption in state-of-the-art vision backbones. In this paper we introduce an efficient and scalable attention model we call multi-axis attention, which consists of two aspects: blocked local and dilated global attention. These design choices allow global-local spatial interactions on arbitrary input resolutions with only linear complexity. We also present a new architectural element by effectively blending our proposed attention model with convolutions, and accordingly propose a simple hierarchical vision backbone, dubbed MaxViT, by simply repeating the basic building block over multiple stages. Notably, MaxViT is able to ''see'' globally throughout the entire network, even in earlier, high-resolution stages. We demonstrate the effectiveness of our model on a broad spectrum of vision tasks. On image classification, MaxViT achieves state-of-the-art performance under various settings: without extra data, MaxViT attains 86.5% ImageNet-1K top-1 accuracy; with ImageNet-21K pre-training, our model achieves 88.7% top-1 accuracy. For downstream tasks, MaxViT as a backbone delivers favorable performance on object detection as well as visual aesthetic assessment. We also show that our proposed model expresses strong generative modeling capability on ImageNet, demonstrating the superior potential of MaxViT blocks as a universal vision module. The source code and trained models will be available at https://github.com/google-research/maxvit.

Ligong Han, Yinxiao Li, Han Zhang et al.

Diffusion models have achieved remarkable success in text-to-image generation, enabling the creation of high-quality images from text prompts or other modalities. However, existing methods for customizing these models are limited by handling multiple personalized subjects and the risk of overfitting. Moreover, their large number of parameters is inefficient for model storage. In this paper, we propose a novel approach to address these limitations in existing text-to-image diffusion models for personalization. Our method involves fine-tuning the singular values of the weight matrices, leading to a compact and efficient parameter space that reduces the risk of overfitting and language drifting. We also propose a Cut-Mix-Unmix data-augmentation technique to enhance the quality of multi-subject image generation and a simple text-based image editing framework. Our proposed SVDiff method has a significantly smaller model size compared to existing methods (approximately 2,200 times fewer parameters compared with vanilla DreamBooth), making it more practical for real-world applications.

Junjie Ke, Keren Ye, Jiahui Yu et al.

Assessing the aesthetics of an image is challenging, as it is influenced by multiple factors including composition, color, style, and high-level semantics. Existing image aesthetic assessment (IAA) methods primarily rely on human-labeled rating scores, which oversimplify the visual aesthetic information that humans perceive. Conversely, user comments offer more comprehensive information and are a more natural way to express human opinions and preferences regarding image aesthetics. In light of this, we propose learning image aesthetics from user comments, and exploring vision-language pretraining methods to learn multimodal aesthetic representations. Specifically, we pretrain an image-text encoder-decoder model with image-comment pairs, using contrastive and generative objectives to learn rich and generic aesthetic semantics without human labels. To efficiently adapt the pretrained model for downstream IAA tasks, we further propose a lightweight rank-based adapter that employs text as an anchor to learn the aesthetic ranking concept. Our results show that our pretrained aesthetic vision-language model outperforms prior works on image aesthetic captioning over the AVA-Captions dataset, and it has powerful zero-shot capability for aesthetic tasks such as zero-shot style classification and zero-shot IAA, surpassing many supervised baselines. With only minimal finetuning parameters using the proposed adapter module, our model achieves state-of-the-art IAA performance over the AVA dataset.

Junjie Ke, Tianhao Zhang, Yilin Wang et al.

No-reference video quality assessment (NR-VQA) for user generated content (UGC) is crucial for understanding and improving visual experience. Unlike video recognition tasks, VQA tasks are sensitive to changes in input resolution. Since large amounts of UGC videos nowadays are 720p or above, the fixed and relatively small input used in conventional NR-VQA methods results in missing high-frequency details for many videos. In this paper, we propose a novel Transformer-based NR-VQA framework that preserves the high-resolution quality information. With the multi-resolution input representation and a novel multi-resolution patch sampling mechanism, our method enables a comprehensive view of both the global video composition and local high-resolution details. The proposed approach can effectively aggregate quality information across different granularities in spatial and temporal dimensions, making the model robust to input resolution variations. Our method achieves state-of-the-art performance on large-scale UGC VQA datasets LSVQ and LSVQ-1080p, and on KoNViD-1k and LIVE-VQC without fine-tuning.

Seung Hyun Lee, Sieun Kim, Innfarn Yoo et al.

We propose a method for adding sound-guided visual effects to specific regions of videos with a zero-shot setting. Animating the appearance of the visual effect is challenging because each frame of the edited video should have visual changes while maintaining temporal consistency. Moreover, existing video editing solutions focus on temporal consistency across frames, ignoring the visual style variations over time, e.g., thunderstorm, wave, fire crackling. To overcome this limitation, we utilize temporal sound features for the dynamic style. Specifically, we guide denoising diffusion probabilistic models with an audio latent representation in the audio-visual latent space. To the best of our knowledge, our work is the first to explore sound-guided natural video editing from various sound sources with sound-specialized properties, such as intensity, timbre, and volume. Additionally, we design optical flow-based guidance to generate temporally consistent video frames, capturing the pixel-wise relationship between adjacent frames. Experimental results show that our method outperforms existing video editing techniques, producing more realistic visual effects that reflect the properties of sound. Please visit our page: https://kuai-lab.github.io/soundini-gallery/.

Sivaramakrishnan Rajaraman, Feng Yang, Ghada Zamzmi et al.

Automated segmentation of tuberculosis (TB)-consistent lesions in chest X-rays (CXRs) using deep learning (DL) methods can help reduce radiologist effort, supplement clinical decision-making, and potentially result in improved patient treatment. The majority of works in the literature discuss training automatic segmentation models using coarse bounding box annotations. However, the granularity of the bounding box annotation could result in the inclusion of a considerable fraction of false positives and negatives at the pixel level that may adversely impact overall semantic segmentation performance. This study (i) evaluates the benefits of using fine-grained annotations of TB-consistent lesions and (ii) trains and constructs ensembles of the variants of U-Net models for semantically segmenting TB-consistent lesions in both original and bone-suppressed frontal CXRs. We evaluated segmentation performance using several ensemble methods such as bitwise AND, bitwise-OR, bitwise-MAX, and stacking. We observed that the stacking ensemble demonstrated superior segmentation performance (Dice score: 0.5743, 95% confidence interval: (0.4055,0.7431)) compared to the individual constituent models and other ensemble methods. To the best of our knowledge, this is the first study to apply ensemble learning to improve fine-grained TB-consistent lesion segmentation performance.

Sivaramakrishnan Rajaraman, Feng Yang, Ghada Zamzmi et al.

Deep learning (DL) models are state-of-the-art in segmenting anatomical and disease regions of interest (ROIs) in medical images. Particularly, a large number of DL-based techniques have been reported using chest X-rays (CXRs). However, these models are reportedly trained on reduced image resolutions for reasons related to the lack of computational resources. Literature is sparse in discussing the optimal image resolution to train these models for segmenting the Tuberculosis (TB)-consistent lesions in CXRs. In this study, we investigated the performance variations using an Inception-V3 UNet model using various image resolutions with/without lung ROI cropping and aspect ratio adjustments, and (ii) identified the optimal image resolution through extensive empirical evaluations to improve TB-consistent lesion segmentation performance. We used the Shenzhen CXR dataset for the study which includes 326 normal patients and 336 TB patients. We proposed a combinatorial approach consisting of storing model snapshots, optimizing segmentation threshold and test-time augmentation (TTA), and averaging the snapshot predictions, to further improve performance with the optimal resolution. Our experimental results demonstrate that higher image resolutions are not always necessary, however, identifying the optimal image resolution is critical to achieving superior performance.

Sivaramakrishnan Rajaraman, Feng Yang, Ghada Zamzmi et al.

Lung segmentation in chest X-rays (CXRs) is an important prerequisite for improving the specificity of diagnoses of cardiopulmonary diseases in a clinical decision support system. Current deep learning models for lung segmentation are trained and evaluated on CXR datasets in which the radiographic projections are captured predominantly from the adult population. However, the shape of the lungs is reported to be significantly different across the developmental stages from infancy to adulthood. This might result in age-related data domain shifts that would adversely impact lung segmentation performance when the models trained on the adult population are deployed for pediatric lung segmentation. In this work, our goal is to (i) analyze the generalizability of deep adult lung segmentation models to the pediatric population and (ii) improve performance through a stage-wise, systematic approach consisting of CXR modality-specific weight initializations, stacked ensembles, and an ensemble of stacked ensembles. To evaluate segmentation performance and generalizability, novel evaluation metrics consisting of mean lung contour distance (MLCD) and average hash score (AHS) are proposed in addition to the multi-scale structural similarity index measure (MS-SSIM), the intersection of union (IoU), Dice score, 95% Hausdorff distance (HD95), and average symmetric surface distance (ASSD). Our results showed a significant improvement (p < 0.05) in cross-domain generalization through our approach. This study could serve as a paradigm to analyze the cross-domain generalizability of deep segmentation models for other medical imaging modalities and applications.

Feng Yang, Xingle Zhang, Bo Liu

Multiple object tracking (MOT) is an important technology in the field of computer vision, which is widely used in automatic driving, intelligent monitoring, behavior recognition and other directions. Among the current popular MOT methods based on deep learning, Detection Based Tracking (DBT) is the most widely used in industry, and the performance of them depend on their object detection network. At present, the DBT algorithm with good performance and the most widely used is YOLOv5-DeepSORT. Inspired by YOLOv5-DeepSORT, with the proposal of YOLOv7 network, which performs better in object detection, we apply YOLOv7 as the object detection part to the DeepSORT, and propose YOLOv7-DeepSORT. After experimental evaluation, compared with the previous YOLOv5-DeepSORT, YOLOv7-DeepSORT performances better in tracking accuracy.

Shaofeng Yuan, Feng Yang

Intravascular ultrasound (IVUS) is the preferred modality for capturing real-time and high resolution cross-sectional images of the coronary arteries, and evaluating the stenosis. Accurate and real-time segmentation of IVUS images involves the delineation of lumen and external elastic membrane borders. In this paper, we propose a two-stream framework for efficient segmentation of 60 MHz high resolution IVUS images. It combines shallow and deep networks, namely, CSDN. The shallow network with thick channels focuses to extract low-level details. The deep network with thin channels takes charge of learning high-level semantics. Treating the above information separately enables learning a model to achieve high accuracy and high efficiency for accurate real-time segmentation. To further improve the segmentation performance, mutual guided fusion module is used to enhance and fuse both different types of feature representation. The experimental results show that our CSDN accomplishes a good trade-off between analysis speed and segmentation accuracy.

Zhengzhong Tu, Hossein Talebi, Han Zhang et al.

Recent progress on Transformers and multi-layer perceptron (MLP) models provide new network architectural designs for computer vision tasks. Although these models proved to be effective in many vision tasks such as image recognition, there remain challenges in adapting them for low-level vision. The inflexibility to support high-resolution images and limitations of local attention are perhaps the main bottlenecks. In this work, we present a multi-axis MLP based architecture called MAXIM, that can serve as an efficient and flexible general-purpose vision backbone for image processing tasks. MAXIM uses a UNet-shaped hierarchical structure and supports long-range interactions enabled by spatially-gated MLPs. Specifically, MAXIM contains two MLP-based building blocks: a multi-axis gated MLP that allows for efficient and scalable spatial mixing of local and global visual cues, and a cross-gating block, an alternative to cross-attention, which accounts for cross-feature conditioning. Both these modules are exclusively based on MLPs, but also benefit from being both global and `fully-convolutional', two properties that are desirable for image processing. Our extensive experimental results show that the proposed MAXIM model achieves state-of-the-art performance on more than ten benchmarks across a range of image processing tasks, including denoising, deblurring, deraining, dehazing, and enhancement while requiring fewer or comparable numbers of parameters and FLOPs than competitive models. The source code and trained models will be available at \url{https://github.com/google-research/maxim}.

Ilker Oguz, Junjie Ke, Qifei Wang et al.

Neural networks (NN) have demonstrated remarkable capabilities in various tasks, but their computation-intensive nature demands faster and more energy-efficient hardware implementations. Optics-based platforms, using technologies such as silicon photonics and spatial light modulators, offer promising avenues for achieving this goal. However, training multiple trainable layers in tandem with these physical systems poses challenges, as they are difficult to fully characterize and describe with differentiable functions, hindering the use of error backpropagation algorithm. The recently introduced Forward-Forward Algorithm (FFA) eliminates the need for perfect characterization of the learning system and shows promise for efficient training with large numbers of programmable parameters. The FFA does not require backpropagating an error signal to update the weights, rather the weights are updated by only sending information in one direction. The local loss function for each set of trainable weights enables low-power analog hardware implementations without resorting to metaheuristic algorithms or reinforcement learning. In this paper, we present an experiment utilizing multimode nonlinear wave propagation in an optical fiber demonstrating the feasibility of the FFA approach using an optical system. The results show that incorporating optical transforms in multilayer NN architectures trained with the FFA, can lead to performance improvements, even with a relatively small number of trainable weights. The proposed method offers a new path to the challenge of training optical NNs and provides insights into leveraging physical transformations for enhancing NN performance.

Shaofeng Yuan, Feng Yang

Automatic and accurate segmentation of aortic vessel tree (AVT) in computed tomography (CT) scans is crucial for early detection, diagnosis and prognosis of aortic diseases, such as aneurysms, dissections and stenosis. However, this task remains challenges, due to the complexity of aortic vessel tree and amount of CT angiography data. In this technical report, we use two-stage fully convolutional networks (FCNs) to automatically segment AVT in CTA scans from multiple centers. Specifically, we firstly adopt a 3D FCN with U-shape network architecture to segment AVT in order to produce topology attention and accelerate medical image analysis pipeline. And then another one 3D FCN is trained to segment branches of AVT along the pseudo-centerline of AVT. In the 2023 MICCAI Segmentation of the Aorta (SEG.A.) Challenge , the reported method was evaluated on the public dataset of 56 cases. The resulting Dice Similarity Coefficient (DSC) is 0.920, Jaccard Similarity Coefficient (JSC) is 0.861, Recall is 0.922, and Precision is 0.926 on a 5-fold random split of training and validation set.

Feng Yang, Yichao Cao, Qifan Xue et al.

Learning a powerful representation from point clouds is a fundamental and challenging problem in the field of computer vision. Different from images where RGB pixels are stored in the regular grid, for point clouds, the underlying semantic and structural information of point clouds is the spatial layout of the points. Moreover, the properties of challenging in-context and background noise pose more challenges to point cloud analysis. One assumption is that the poor performance of the classification model can be attributed to the indistinguishable embedding feature that impedes the search for the optimal classifier. This work offers a new strategy for learning powerful representations via a contrastive learning approach that can be embedded into any point cloud classification network. First, we propose a supervised contrastive classification method to implement embedding feature distribution refinement by improving the intra-class compactness and inter-class separability. Second, to solve the confusion problem caused by small inter-class compactness and inter-class separability. Second, to solve the confusion problem caused by small inter-class variations between some similar-looking categories, we propose a confusion-prone class mining strategy to alleviate the confusion effect. Finally, considering that outliers of the sample clusters in the embedding space may cause performance degradation, we design an entropy-aware attention module with information entropy theory to identify the outlier cases and the unstable samples by measuring the uncertainty of predicted probability. The results of extensive experiments demonstrate that our method outperforms the state-of-the-art approaches by achieving 82.9% accuracy on the real-world ScanObjectNN dataset and substantial performance gains up to 2.9% in DCGNN, 3.1% in PointNet++, and 2.4% in GBNet.

Fei Zhang, Chaochen Gu, Feng Yang

Deep Q Network (DQN) has several limitations when applied in planning a path in environment with a number of dilemmas according to our experiment. The reward function may be hard to model, and successful experience transitions are difficult to find in experience replay. In this context, this paper proposes an improved Double DQN (DDQN) to solve the problem by reference to A* and Rapidly-Exploring Random Tree (RRT). In order to achieve the rich experiments in experience replay, the initialization of robot in each training round is redefined based on RRT strategy. In addition, reward for the free positions is specially designed to accelerate the learning process according to the definition of position cost in A*. The simulation experimental results validate the efficiency of the improved DDQN, and robot could successfully learn the ability of obstacle avoidance and optimal path planning in which DQN or DDQN has no effect.

Feng Yang, C. Devon Lin, Pritam Ranjan

Computer simulators are nowadays widely used to understand complex physical systems in many areas such as aerospace, renewable energy, climate modeling, and manufacturing. One fundamental issue in the study of computer simulators is known as experimental design, that is, how to select the input settings where the computer simulator is run and the corresponding response is collected. Extra care should be taken in the selection process because computer simulators can be computationally expensive to run. The selection shall acknowledge and achieve the goal of the analysis. This article focuses on the goal of producing more accurate prediction which is important for risk assessment and decision making. We propose two new methods of design approaches that sequentially select input settings to achieve this goal. The approaches make novel applications of simultaneous and sequential contour estimations. Numerical examples are employed to demonstrate the effectiveness of the proposed approaches.

Yujiao Tang, Feng Yang, Shaofeng Yuan et al.

The computer-aided diagnosis (CAD) systems can highly improve the reliability and efficiency of melanoma recognition. As a crucial step of CAD, skin lesion segmentation has the unsatisfactory accuracy in existing methods due to large variability in lesion appearance and artifacts. In this work, we propose a framework employing multi-stage UNets (MS-UNet) in the auto-context scheme to segment skin lesion accurately end-to-end. We apply two approaches to boost the performance of MS-UNet. First, UNet is coupled with a context information fusion structure (CIFS) to integrate the low-level and context information in the multi-scale feature space. Second, to alleviate the gradient vanishing problem, we use deep supervision mechanism through supervising MS-UNet by minimizing a weighted Jaccard distance loss function. Four out of five commonly used performance metrics, including Jaccard index and Dice coefficient, show that our approach outperforms the state-ofthe-art deep learning based methods on the ISBI 2016 Skin Lesion Challenge dataset.