Scene text recognition (STR) is very challenging due to the diversity of text instances and the complexity of scenes. The community has paid increasing attention to boost the performance by improving the pre-processing image module, like rectification and deblurring, or the sequence translator. However, another critical module, i.e., the feature sequence extractor, has not been extensively explored. In this work, inspired by the success of neural architecture search (NAS), which can identify better architectures than human-designed ones, we propose automated STR (AutoSTR) to search data-dependent backbones to boost text recognition performance. First, we design a domain-specific search space for STR, which contains both choices on operations and constraints on the downsampling path. Then, we propose a two-step search algorithm, which decouples operations and downsampling path, for an efficient search in the given space. Experiments demonstrate that, by searching data-dependent backbones, AutoSTR can outperform the state-of-the-art approaches on standard benchmarks with much fewer FLOPS and model parameters.
Scene Text Recognition (STR), the task of recognizing text against complex image backgrounds, is an active area of research. Current state-of-the-art (SOTA) methods still struggle to recognize text written in arbitrary shapes. In this paper, we introduce a novel architecture for STR, named Selective Context ATtentional Text Recognizer (SCATTER). SCATTER utilizes a stacked block architecture with intermediate supervision during training, that paves the way to successfully train a deep BiLSTM encoder, thus improving the encoding of contextual dependencies. Decoding is done using a two-step 1D at…
South China University of Technology（华南理工大学）；Chinese University of Hong Kong（香港中文大学）；Huawei Cloud AI（华为云人工智能部门）；IntSig Information Co., Ltd（合合信息科技股份有限公司）；Peng Cheng Laboratory（鹏城实验室）
End-to-end scene text spotting has attracted great attention in recent years due to the success of excavating the intrinsic synergy of the scene text detection and recognition. However, recent state-of-the-art methods usually incorporate detection and recognition simply by sharing the backbone, which does not directly take advantage of the feature interaction between the two tasks. In this paper, we propose a new end-to-end scene text spotting framework termed SwinTextSpotter. Using a transformer encoder with dynamic head as the detector, we unify the two tasks with a novel Recognition Convers…
The task of detecting 3D objects in traffic scenes has a pivotal role in many real-world applications. However, the performance of 3D object detection is lower than that of 2D object detection due to the lack of powerful 3D feature extraction methods. To address this issue, this study proposes a 3D backbone network to acquire comprehensive 3D feature maps for 3D object detection. It primarily consists of sparse 3D convolutional neural network operations in the point cloud. The 3D backbone network can inherently learn 3D features from the raw data without compressing the point cloud into multip…
Technical University of Munich（慕尼黑工业大学）；Tongji University（同济大学）
State-of-the-art lidar-based 3D object detection methods rely on supervised learning and large labeled datasets. However, annotating lidar data is resource-consuming, and depending only on supervised learning limits the applicability of trained models. Self-supervised training strategies can alleviate these issues by learning a general point cloud backbone model for downstream 3D vision tasks. Against this backdrop, we show the relationship between self-supervised multi-frame flow representations and single-frame 3D detection hypotheses. Our main contribution leverages learned flow and motion …
Technical Report for ICRA 2025 GOOSE 2D Semantic Segmentation Challenge: Leveraging Color Shift Correction, RoPE-Swin Backbone, and Quantile-based Label Denoising Strategy for Robust Outdoor Scene Understanding
Institute of Intelligent Systems（智能系统研究所）；College of Artificial Intelligence, National Yang Ming Chiao Tung University（人工智能学院，阳明交通大学）；Institute of Data Science, National Cheng Kung University（数据科学研究所，成功大学）
Most deep learning backbones are evaluated on ImageNet. Using scenery images as an example, we conducted extensive experiments to demonstrate the widely accepted principles in network design may result in dramatic performance differences when the data is altered. Exploratory experiments are engaged to explain the underlining cause of the differences. Based on our observation, this paper presents a novel network design methodology: data-oriented network design. In other words, instead of designing universal backbones, the scheming of the networks should treat the characteristics of data as a cr…
Remote sensing scene classification has been extensively studied for its critical roles in geological survey, oil exploration, traffic management, earthquake prediction, wildfire monitoring, and intelligence monitoring. In the past, the Machine Learning (ML) methods for performing the task mainly used the backbones pretrained in the manner of supervised learning (SL). As Masked Image Modeling (MIM), a self-supervised learning (SSL) technique, has been shown as a better way for learning visual feature representation, it presents a new opportunity for improving ML performance on the scene classi…
Hunan University（湖南大学）；University of Pittsburgh（匹兹堡大学）
The rapid development of autonomous driving in recent years presents lots of challenges for scene understanding. As an essential step towards scene understanding, semantic segmentation thus received lots of attention in past few years. Although deep learning based state-of-the-arts have achieved great success in improving the segmentation accuracy, most of them suffer from an inefficiency problem and can hardly applied to practical applications. In this paper, we systematically analyze the computation cost of Convolutional Neural Network(CNN) and found that the inefficiency of CNN is mainly ca…
Huazhong University of Science and Technology（华中科技大学）；Megvii（旷视科技）；Shanghai Jiao Tong University（上海交通大学）；Onlyou Tech.（唯友科技）
Recently, segmentation-based methods are quite popular in scene text detection, as the segmentation results can more accurately describe scene text of various shapes such as curve text. However, the post-processing of binarization is essential for segmentation-based detection, which converts probability maps produced by a segmentation method into bounding boxes/regions of text. In this paper, we propose a module named Differentiable Binarization (DB), which can perform the binarization process in a segmentation network. Optimized along with a DB module, a segmentation network can adaptively se…
Nankai University（南开大学）；Institute for Infocomm Research (I2R), Agency for Science, Technology and Research (A*STAR)（新加坡科技研究局资讯通信研究院）；Alibaba DAMO Academy（阿里巴巴达摩院）
Recently, the vision transformer has achieved great success by pushing the state-of-the-art of various vision tasks. One of the most challenging problems in the vision transformer is that the large sequence length of image tokens leads to high computational cost (quadratic complexity). A popular solution to this problem is to use a single pooling operation to reduce the sequence length. This paper considers how to improve existing vision transformers, where the pooled feature extracted by a single pooling operation seems less powerful. To this end, we note that pyramid pooling has been demonst…
This report presents our 2nd place solution to ECCV 2022 challenge on Out-of-Vocabulary Scene Text Understanding (OOV-ST) : Cropped Word Recognition. This challenge is held in the context of ECCV 2022 workshop on Text in Everything (TiE), which aims to extract out-of-vocabulary words from natural scene images. In the competition, we first pre-train SCATTER on the synthetic datasets, then fine-tune the model on the training set with data augmentations. Meanwhile, two additional models are trained specifically for long and vertical texts. Finally, we combine the output from different models with…
Peking University（北京大学）；Microsoft Research Asia（微软亚洲研究院）；South China University of Technology（华南理工大学）
In this paper, we present a new Mask R-CNN based text detection approach which can robustly detect multi-oriented and curved text from natural scene images in a unified manner. To enhance the feature representation ability of Mask R-CNN for text detection tasks, we propose to use the Pyramid Attention Network (PAN) as a new backbone network of Mask R-CNN. Experiments demonstrate that PAN can suppress false alarms caused by text-like backgrounds more effectively. Our proposed approach has achieved superior performance on both multi-oriented (ICDAR-2015, ICDAR-2017 MLT) and curved (SCUT-CTW1500)…
University of Science and Technology of China（中国科学技术大学）；the University of Sydney（悉尼大学）
It is crucial to understand the robustness of text detection models with regard to extensive corruptions, since scene text detection techniques have many practical applications. For systematically exploring this problem, we propose two datasets from which to evaluate scene text detection models: ICDAR2015-C (IC15-C) and CTW1500-C (CTW-C). Our study extends the investigation of the performance and robustness of the proposed region proposal, regression and segmentation-based scene text detection frameworks. Furthermore, we perform a robustness analysis of six key components: pre-training data, b…
Semantic segmentation is an important task in computer vision, from which some important usage scenarios are derived, such as autonomous driving, scene parsing, etc. Due to the emphasis on the task of video semantic segmentation, we participated in this competition. In this report, we briefly introduce the solutions of team 'BetterThing' for the ICCV2021 - Video Scene Parsing in the Wild Challenge. Transformer is used as the backbone for extracting video frame features, and the final result is the aggregation of the output of two Transformer models, SWIN and VOLO. This solution achieves 57.3% …
National University of Singapore（新加坡国立大学）；University of Oxford（牛津大学）；Nankai University（南开大学）
Spatial pooling has been proven highly effective in capturing long-range contextual information for pixel-wise prediction tasks, such as scene parsing. In this paper, beyond conventional spatial pooling that usually has a regular shape of NxN, we rethink the formulation of spatial pooling by introducing a new pooling strategy, called strip pooling, which considers a long but narrow kernel, i.e., 1xN or Nx1. Based on strip pooling, we further investigate spatial pooling architecture design by 1) introducing a new strip pooling module that enables backbone networks to efficiently model long-rang…
Stereo matching has recently witnessed remarkable progress using Deep Neural Networks (DNNs). But, how robust are they? Although it has been well-known that DNNs often suffer from adversarial vulnerability with a catastrophic drop in performance, the situation is even worse in stereo matching. This paper first shows that a type of weak white-box attacks can overwhelm state-of-the-art methods. The attack is learned by a proposed stereo-constrained projected gradient descent (PGD) method in stereo matching. This observation raises serious concerns for the deployment of DNN-based stereo matching.…
Tianjin DM AILab（天津DM人工智能实验室）；Tianjin University of Finance and Economics（天津财经大学）
It is an extremely challenging task to detect arbitrary shape text in natural scenes on high accuracy and efficiency. In this paper, we propose a scene text detection framework, namely GWNet, which mainly includes two modules: Global module and RCNN module. Specifically, Global module improves the adaptive performance of the DB (Differentiable Binarization) module by adding k submodule and shift submodule. Two submodules enhance the adaptability of amplifying factor k, accelerate the convergence of models and help to produce more accurate detection results. RCNN module fuses global-level and w…
Nanyang Technological University（南洋理工大学）；University of Adelaide（阿德莱德大学）；Shanghai Jiao Tong University（上海交通大学）
In this work, we propose a novel hybrid method for scene text detection namely Correlation Propagation Network (CPN). It is an end-to-end trainable framework engined by advanced Convolutional Neural Networks. Our CPN predicts text objects according to both top-down observations and the bottom-up cues. Multiple candidate boxes are assembled by a spatial communication mechanism call Correlation Propagation (CP). The extracted spatial features by CNN are regarded as node features in a latticed graph and Correlation Propagation algorithm runs distributively on each node to update the hypothesis of…
Arbitrarily Shaped Scene Text Detection: A Decade of Advances and Systematic Analysis
School of Cyber Science and Technology, Shenzhen Campus of Sun Yat-sen University（中山大学深圳校区网络空间科学与技术学院）；School of Cyber Science and Engineering, Nanjing University of Science and Technology（南京理工大学网络空间科学与工程学院）
Institute for Anthropomatics and Robotics, Karlsruhe Institute of Technology（卡尔斯鲁厄理工学院人形机器人与智能系统研究所）；Hangzhou SurImage Technology Company Ltd.（杭州 SurImage 科技有限公司）；Hangzhou KrVision Technology Company Ltd.（杭州 KrVision 科技有限公司）
As the scene information, including objectness and scene type, are important for people with visual impairment, in this work we present a multi-task efficient perception system for the scene parsing and recognition tasks. Building on the compact ResNet backbone, our designed network architecture has two paths with shared parameters. In the structure, the semantic segmentation path integrates fast attention, with the aim of harvesting long-range contextual information in an efficient manner. Simultaneously, the scene recognition path attains the scene type inference by passing the semantic feat…
Recently, a massive number of deep learning based approaches have been successfully applied to various remote sensing image (RSI) recognition tasks. However, most existing advances of deep learning methods in the RSI field heavily rely on the features extracted by the manually designed backbone network, which severely hinders the potential of deep learning models due the complexity of RSI and the limitation of prior knowledge. In this paper, we research a new design paradigm for the backbone architecture in RSI recognition tasks, including scene classification, land-cover classification and ob…
GaussEdit: Adaptive 3D Scene Editing with Text and Image Prompts
School of Computer and Data Engineering, NingboTech University（计算机与数据工程学院，宁波科技学院）；Ningbo Institute, Zhejiang University（浙江大学宁波学院）；School of Software Technology, Zhejiang University（软件技术学院，浙江大学）；School of Big Data and Artificial Intelligence Management, Xi’an Jiaotong University（大数据与人工智能管理学院，西安交通大学）；School of Computer Science and Technology, ShanDong University（计算机科学与技术学院，山东大学）；Graphics & Geometric Computing Laboratory, School of Mathematical Sciences, University of Science and Technology of China（图形与几何计算实验室，数学科学学院，中国科学技术大学）
University of Padova（帕多瓦大学）；University of Modena and Reggio Emilia（摩德纳-雷焦艾米利亚大学）
Human trajectory forecasting is a key component of autonomous vehicles, social-aware robots and advanced video-surveillance applications. This challenging task typically requires knowledge about past motion, the environment and likely destination areas. In this context, multi-modality is a fundamental aspect and its effective modeling can be beneficial to any architecture. Inferring accurate trajectories is nevertheless challenging, due to the inherently uncertain nature of the future. To overcome these difficulties, recent models use different inputs and propose to model human intentions usin…
