Xiao Liang

Chen Min, Xinli Xu, Dawei Zhao et al.

Current perception models in autonomous driving heavily rely on large-scale labelled 3D data, which is both costly and time-consuming to annotate. This work proposes a solution to reduce the dependence on labelled 3D training data by leveraging pre-training on large-scale unlabeled outdoor LiDAR point clouds using masked autoencoders (MAE). While existing masked point autoencoding methods mainly focus on small-scale indoor point clouds or pillar-based large-scale outdoor LiDAR data, our approach introduces a new self-supervised masked occupancy pre-training method called Occupancy-MAE, specifically designed for voxel-based large-scale outdoor LiDAR point clouds. Occupancy-MAE takes advantage of the gradually sparse voxel occupancy structure of outdoor LiDAR point clouds and incorporates a range-aware random masking strategy and a pretext task of occupancy prediction. By randomly masking voxels based on their distance to the LiDAR and predicting the masked occupancy structure of the entire 3D surrounding scene, Occupancy-MAE encourages the extraction of high-level semantic information to reconstruct the masked voxel using only a small number of visible voxels. Extensive experiments demonstrate the effectiveness of Occupancy-MAE across several downstream tasks. For 3D object detection, Occupancy-MAE reduces the labelled data required for car detection on the KITTI dataset by half and improves small object detection by approximately 2% in AP on the Waymo dataset. For 3D semantic segmentation, Occupancy-MAE outperforms training from scratch by around 2% in mIoU. For multi-object tracking, Occupancy-MAE enhances training from scratch by approximately 1% in terms of AMOTA and AMOTP. Codes are publicly available at https://github.com/chaytonmin/Occupancy-MAE.

Xun Wang, Bingqing Ke, Xuanping Li et al. · deepmind

Video search has become the main routine for users to discover videos relevant to a text query on large short-video sharing platforms. During training a query-video bi-encoder model using online search logs, we identify a modality bias phenomenon that the video encoder almost entirely relies on text matching, neglecting other modalities of the videos such as vision, audio. This modality imbalanceresults from a) modality gap: the relevance between a query and a video text is much easier to learn as the query is also a piece of text, with the same modality as the video text; b) data bias: most training samples can be solved solely by text matching. Here we share our practices to improve the first retrieval stage including our solution for the modality imbalance issue. We propose MBVR (short for Modality Balanced Video Retrieval) with two key components: manually generated modality-shuffled (MS) samples and a dynamic margin (DM) based on visual relevance. They can encourage the video encoder to pay balanced attentions to each modality. Through extensive experiments on a real world dataset, we show empirically that our method is both effective and efficient in solving modality bias problem. We have also deployed our MBVR in a large video platform and observed statistically significant boost over a highly optimized baseline in an A/B test and manual GSB evaluations.

Liang Xiao, Jiaolong Xu, Dawei Zhao et al. · berkeley

Data augmentation has been widely used to improve generalization in training deep neural networks. Recent works show that using worst-case transformations or adversarial augmentation strategies can significantly improve the accuracy and robustness. However, due to the non-differentiable properties of image transformations, searching algorithms such as reinforcement learning or evolution strategy have to be applied, which are not computationally practical for large scale problems. In this work, we show that by simply applying consistency training with random data augmentation, state-of-the-art results on domain adaptation (DA) and generalization (DG) can be obtained. To further improve the accuracy and robustness with adversarial examples, we propose a differentiable adversarial data augmentation method based on spatial transformer networks (STN). The combined adversarial and random transformations based method outperforms the state-of-the-art on multiple DA and DG benchmark datasets. Besides, the proposed method shows desirable robustness to corruption, which is also validated on commonly used datasets.

Yunxiang Li, Hua-Chieh Shao, Xiao Liang et al.

Recently, the diffusion model has emerged as a superior generative model that can produce high quality and realistic images. However, for medical image translation, the existing diffusion models are deficient in accurately retaining structural information since the structure details of source domain images are lost during the forward diffusion process and cannot be fully recovered through learned reverse diffusion, while the integrity of anatomical structures is extremely important in medical images. For instance, errors in image translation may distort, shift, or even remove structures and tumors, leading to incorrect diagnosis and inadequate treatments. Training and conditioning diffusion models using paired source and target images with matching anatomy can help. However, such paired data are very difficult and costly to obtain, and may also reduce the robustness of the developed model to out-of-distribution testing data. We propose a frequency-guided diffusion model (FGDM) that employs frequency-domain filters to guide the diffusion model for structure-preserving image translation. Based on its design, FGDM allows zero-shot learning, as it can be trained solely on the data from the target domain, and used directly for source-to-target domain translation without any exposure to the source-domain data during training. We evaluated it on three cone-beam CT (CBCT)-to-CT translation tasks for different anatomical sites, and a cross-institutional MR imaging translation task. FGDM outperformed the state-of-the-art methods (GAN-based, VAE-based, and diffusion-based) in metrics of Frechet Inception Distance (FID), Peak Signal-to-Noise Ratio (PSNR), and Structural Similarity Index Measure (SSIM), showing its significant advantages in zero-shot medical image translation.

Jiaxin Cheng, Xiao Liang, Xingjian Shi et al.

Layout-to-image generation refers to the task of synthesizing photo-realistic images based on semantic layouts. In this paper, we propose LayoutDiffuse that adapts a foundational diffusion model pretrained on large-scale image or text-image datasets for layout-to-image generation. By adopting a novel neural adaptor based on layout attention and task-aware prompts, our method trains efficiently, generates images with both high perceptual quality and layout alignment, and needs less data. Experiments on three datasets show that our method significantly outperforms other 10 generative models based on GANs, VQ-VAE, and diffusion models.

Yusuke Takimoto, Hiroyuki Sato, Hikari Takehara et al.

Differentiable rendering (DR) enables various computer graphics and computer vision applications through gradient-based optimization with derivatives of the rendering equation. Most rasterization-based approaches are built on general-purpose automatic differentiation (AD) libraries and DR-specific modules handcrafted using CUDA. Such a system design mixes DR algorithm implementation and algorithm building blocks, resulting in hardware dependency and limited performance. In this paper, we present a practical hardware-agnostic differentiable renderer called Dressi, which is based on a new full AD design. The DR algorithms of Dressi are fully written in our Vulkan-based AD for DR, Dressi-AD, which supports all primitive operations for DR. Dressi-AD and our inverse UV technique inside it bring hardware independence and acceleration by graphics hardware. Stage packing, our runtime optimization technique, can adapt hardware constraints and efficiently execute complex computational graphs of DR with reactive cache considering the render pass hierarchy of Vulkan. HardSoftRas, our novel rendering process, is designed for inverse rendering with a graphics pipeline. Under the limited functionalities of the graphics pipeline, HardSoftRas can propagate the gradients of pixels from the screen space to far-range triangle attributes. Our experiments and applications demonstrate that Dressi establishes hardware independence, high-quality and robust optimization with fast speed, and photorealistic rendering.

Ti Bai, Muhan Lin, Xiao Liang et al.

Medical image registration is a fundamental and vital task which will affect the efficacy of many downstream clinical tasks. Deep learning (DL)-based deformable image registration (DIR) methods have been investigated, showing state-of-the-art performance. A test time optimization (TTO) technique was proposed to further improve the DL models' performance. Despite the substantial accuracy improvement with this TTO technique, there still remained some regions that exhibited large registration errors even after many TTO iterations. To mitigate this challenge, we firstly identified the reason why the TTO technique was slow, or even failed, to improve those regions' registration results. We then proposed a two-levels TTO technique, i.e., image-specific optimization (ISO) and region-specific optimization (RSO), where the region can be interactively indicated by the clinician during the registration result reviewing process. For both efficiency and accuracy, we further envisioned a three-step DL-based image registration workflow. Experimental results showed that our proposed method outperformed the conventional method qualitatively and quantitatively.

Kareem Eltouny, Seyedomid Sajedi, Xiao Liang

Visual inspection is predominantly used to evaluate the state of civil structures, but recent developments in unmanned aerial vehicles (UAVs) and artificial intelligence have increased the speed, safety, and reliability of the inspection process. In this study, we develop a semantic segmentation network based on vision transformers and Laplacian pyramids scaling networks for efficiently parsing high-resolution visual inspection images. The massive amounts of collected high-resolution images during inspections can slow down the investigation efforts. And while there have been extensive studies dedicated to the use of deep learning models for damage segmentation, processing high-resolution visual data can pose major computational difficulties. Traditionally, images are either uniformly downsampled or partitioned to cope with computational demands. However, the input is at risk of losing local fine details, such as thin cracks, or global contextual information. Inspired by super-resolution architectures, our vision transformer model learns to resize high-resolution images and masks to retain both the valuable local features and the global semantics without sacrificing computational efficiency. The proposed framework has been evaluated through comprehensive experiments on a dataset of bridge inspection report images using multiple metrics for pixel-wise materials detection.

Weijie Yin, Dingkang Yang, Hongyuan Dong et al.

Vision Transformers (ViTs) are essential as foundation backbones in establishing the visual comprehension capabilities of Multimodal Large Language Models (MLLMs). Although most ViTs achieve impressive performance through image-text pair-based contrastive learning or self-supervised mechanisms, they struggle to engage in connector-based co-training directly with LLMs due to potential parameter initialization conflicts and modality semantic gaps. To address the above challenges, this paper proposes SAILViT, a gradual feature learning-enhanced ViT for facilitating MLLMs to break through performance bottlenecks in complex multimodal interactions. SAILViT achieves coarse-to-fine-grained feature alignment and world knowledge infusion with gradual feature refinement, which better serves target training demands. We perform thorough empirical analyses to confirm the powerful robustness and generalizability of SAILViT across different dimensions, including parameter sizes, model architectures, training strategies, and data scales. Equipped with SAILViT, existing MLLMs show significant and consistent performance improvements on the OpenCompass benchmark across extensive downstream tasks. SAILViT series models are released at https://huggingface.co/BytedanceDouyinContent.

Sitong Liu, Zhichao Lian, Siqi Gu et al.

Deepfake detection methods based on convolutional neural networks (CNN) have demonstrated high accuracy. \textcolor{black}{However, these methods often suffer from decreased performance when faced with unknown forgery methods and common transformations such as resizing and blurring, resulting in deviations between training and testing domains.} This phenomenon, known as overfitting, poses a significant challenge. To address this issue, we propose a novel block shuffling regularization method. Firstly, our approach involves dividing the images into blocks and applying both intra-block and inter-block shuffling techniques. This process indirectly achieves weight-sharing across different dimensions. Secondly, we introduce an adversarial loss algorithm to mitigate the overfitting problem induced by the shuffling noise. Finally, we restore the spatial layout of the blocks to capture the semantic associations among them. Extensive experiments validate the effectiveness of our proposed method, which surpasses existing approaches in forgery face detection. Notably, our method exhibits excellent generalization capabilities, demonstrating robustness against cross-dataset evaluations and common image transformations. Especially our method can be easily integrated with various CNN models. Source code is available at \href{https://github.com/NoWindButRain/BlockShuffleLearning}{Github}.

Jiaolong Xu, Liang Xiao, Dawei Zhao et al.

State-of-the-art autonomous driving systems rely on high definition (HD) maps for localization and navigation. However, building and maintaining HD maps is time-consuming and expensive. Furthermore, the HD maps assume structured environment such as the existence of major road and lanes, which are not present in rural areas. In this work, we propose an end-to-end transformer networks based approach for map-less autonomous driving. The proposed model takes raw LiDAR data and noisy topometric map as input and produces precise local trajectory for navigation. We demonstrate the effectiveness of our method in real-world driving data, including both urban and rural areas. The experimental results show that the proposed method outperforms state-of-the-art multimodal methods and is robust to the perturbations of the topometric map. The code of the proposed method is publicly available at \url{https://github.com/Jiaolong/trajectory-prediction}.

Zekai Liang, Kazuya Miyata, Xiao Liang et al.

Accurate camera-to-robot calibration is essential for any vision-based robotic control system and especially critical in minimally invasive surgical robots, where instruments conduct precise micro-manipulations. However, MIS robots have long kinematic chains and partial visibility of their degrees of freedom in the camera, which introduces challenges for conventional camera-to-robot calibration methods that assume stiff robots with good visibility. Previous works have investigated both keypoint-based and rendering-based approaches to address this challenge in real-world conditions; however, they often struggle with consistent feature detection or have long inference times, neither of which are ideal for online robot control. In this work, we propose a novel framework that unifies the detection of geometric primitives (keypoints and shaft edges) through a shared encoding, enabling efficient pose estimation via projection geometry. This architecture detects both keypoints and edges in a single inference and is trained on large-scale synthetic data with projective labeling. This method is evaluated across both feature detection and pose estimation, with qualitative and quantitative results demonstrating fast performance and state-of-the-art accuracy in challenging surgical environments.

Seyed Omid Sajedi, Xiao Liang

Bridges are an essential part of the transportation infrastructure and need to be monitored periodically. Visual inspections by dedicated teams have been one of the primary tools in structural health monitoring (SHM) of bridge structures. However, such conventional methods have certain shortcomings. Manual inspections may be challenging in harsh environments and are commonly biased in nature. In the last decade, camera-equipped unmanned aerial vehicles (UAVs) have been widely used for visual inspections; however, the task of automatically extracting useful information from raw images is still challenging. In this paper, a deep learning semantic segmentation framework is proposed to automatically localize surface cracks. Due to the high imbalance of crack and background classes in images, different strategies are investigated to improve performance and reliability. The trained models are tested on real-world crack images showing impressive robustness in terms of the metrics defined by the concepts of precision and recall. These techniques can be used in SHM of bridges to extract useful information from the unprocessed images taken from UAVs.