In this work, we present SeqFormer for video instance segmentation. SeqFormer follows the principle of vision transformer that models instance relationships among video frames. Nevertheless, we observe that a stand-alone instance query suffices for capturing a time sequence of instances in a video, but attention mechanisms shall be done with each frame independently. To achieve this, SeqFormer locates an instance in each frame and aggregates temporal information to learn a powerful representation of a video-level instance, which is used to predict the mask sequences on each frame dynamically. Instance tracking is achieved naturally without tracking branches or post-processing. On YouTube-VIS, SeqFormer achieves 47.4 AP with a ResNet-50 backbone and 49.0 AP with a ResNet-101 backbone without bells and whistles. Such achievement significantly exceeds the previous state-of-the-art performance by 4.6 and 4.4, respectively. In addition, integrated with the recently-proposed Swin transformer, SeqFormer achieves a much higher AP of 59.3. We hope SeqFormer could be a strong baseline that fosters future research in video instance segmentation, and in the meantime, advances this field with a more robust, accurate, neat model. The code is available at https://github.com/wjf5203/SeqFormer.
Mohamed bin Zayed University of AI（穆罕默德·本·扎耶德人工智能大学）；Technology Innovation Institute（技术创新研究院）；Aalto University（阿尔托大学）；University of Central Florida（中佛罗里达大学）；Linköping University（林雪平大学）
Nanjing University（南京大学）；University of Wollongong（伍伦贡大学）；Nanjing Normal University（南京师范大学）；University of North Carolina at Chapel Hill（北卡罗来纳大学教堂山分校）
Due to low tissue contrast, irregular object appearance, and unpredictable location variation, segmenting the objects from different medical imaging modalities (e.g., CT, MR) is considered as an important yet challenging task. In this paper, we present a novel method for interactive medical image segmentation with the following merits. (1) Our design is fundamentally different from previous pure patch-based and image-based segmentation methods. We observe that during delineation, the physician repeatedly check the inside-outside intensity changing to determine the boundary, which indicates tha…
Johns Hopkins University（约翰斯·霍普金斯大学）；AWS AI Labs（AWS人工智能实验室）
In this work, instead of directly predicting the pixel-level segmentation masks, the problem of referring image segmentation is formulated as sequential polygon generation, and the predicted polygons can be later converted into segmentation masks. This is enabled by a new sequence-to-sequence framework, Polygon Transformer (PolyFormer), which takes a sequence of image patches and text query tokens as input, and outputs a sequence of polygon vertices autoregressively. For more accurate geometric localization, we propose a regression-based decoder, which predicts the precise floating-point coord…
This work examines the use of a fully convolutional net (FCN) to find an image segment, given a pixel within this segment region. The net receives an image, a point in the image and a region of interest (RoI ) mask. The net output is a binary mask of the segment in which the point is located. The region where the segment can be found is contained within the input RoI mask. Full image segmentation can be achieved by running this net sequentially, region-by-region on the image, and stitching the output segments into a single segmentation map. This simple method addresses two major challenges of …
Malong Technologies（码隆科技）；Shenzhen Malong Artificial Intelligence Research Center（深圳码隆人工智能研究中心）；The University of Hong Kong（香港大学）
Weakly-supervised instance segmentation aims to detect and segment object instances precisely, given imagelevel labels only. Unlike previous methods which are composed of multiple offline stages, we propose Sequential Label Propagation and Enhancement Networks (referred as Label-PEnet) that progressively transform image-level labels to pixel-wise labels in a coarse-to-fine manner. We design four cascaded modules including multi-label classification, object detection, instance refinement and instance segmentation, which are implemented sequentially by sharing the same backbone. The cascaded pip…
In this paper we propose a novel deep learning-based algorithm for biomedical image segmentation which uses a sequential attention mechanism able to shift the focus of attention across the image in a selective way, allowing subareas which are more difficult to classify to be processed at increased resolution. The spatial distribution of class information in each subarea is learned using a retina-like representation where resolution decreases with distance from the center of attention. The final segmentation is achieved by averaging class predictions over overlapping subareas, utilizing the pow…
MedSeqFT: Sequential Fine-tuning Foundation Models for 3D Medical Image Segmentation
School of Computer Science and Engineering, Northwestern Polytechnical University（计算机科学与工程学院，西北工业大学）；Monash University（墨尔本大学）；Department of Radiation Oncology, Sichuan Cancer Hospital（肿瘤医院放射肿瘤科）；RMIT（皇家墨尔本理工大学）；University of Melbourne（墨尔本大学）
TM-UNet: Token-Memory Enhanced Sequential Modeling for Efficient Medical Image Segmentation
Dalian University of Technology（大连理工大学）；University of Lincoln（林肯大学）；University of Nottingham（诺丁汉大学）；Waseda University（早稻田大学）；University of Nottingham Ningbo China（宁波诺丁汉大学）；Yale University（耶鲁大学）
SegMamba: Long-range Sequential Modeling Mamba For 3D Medical Image Segmentation
The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；Beijing Academy of Artificial Intelligence（北京智源人工智能研究院）；The Hong Kong University of Science and Technology（香港科技大学）
University of Sydney（悉尼大学）；Royal Prince Alfred Hospital（皇家阿尔弗雷德王子医院）
Sequential whole-body 18F-Fluorodeoxyglucose (FDG) positron emission tomography (PET) scans are regarded as the imaging modality of choice for the assessment of treatment response in the lymphomas because they detect treatment response when there may not be changes on anatomical imaging. Any computerized analysis of lymphomas in whole-body PET requires automatic segmentation of the studies so that sites of disease can be quantitatively monitored over time. State-of-the-art PET image segmentation methods are based on convolutional neural networks (CNNs) given their ability to leverage annotated…
Ensemble approaches for deep-learning-based semantic segmentation remain insufficiently explored despite the proliferation of competitive benchmarks and downstream applications. In this work, we explore and benchmark the popular ensembling approach of combining predictions of multiple, independently-trained, state-of-the-art models at test time on popular datasets. Furthermore, we propose a novel method inspired by boosting to sequentially ensemble networks that significantly outperforms the naive ensemble baseline. Our approach trains a cascade of models conditioned on class probabilities pre…
In current practice, many image processing tasks are done sequentially (e.g. denoising, dehazing, followed by semantic segmentation). In this paper, we propose a novel multi-task neural network architecture designed for combining sequential image processing tasks. We extend U-Net by additional decoding pathways for each individual task, and explore deep cascading of outputs and connectivity from one pathway to another. We demonstrate effectiveness of the proposed approach on denoising and semantic segmentation, as well as on progressive coarse-to-fine semantic segmentation, and achieve better …
In this paper, we propose a novel technique for sampling sequential images using a cylindrical transform in a cylindrical coordinate system for kidney semantic segmentation in abdominal computed tomography (CT). The images generated from a cylindrical transform augment a limited annotated set of images in three dimensions. This approach enables us to train contemporary classification deep convolutional neural networks (DCNNs) instead of fully convolutional networks (FCNs) for semantic segmentation. Typical semantic segmentation models segment a sequential set of images (e.g. CT or video) by se…
SPT: Sequence Prompt Transformer for Interactive Image Segmentation
Ant Group（蚂蚁集团）；BAIDU（百度）；Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；University of Chinese Academy of Sciences（中国科学院大学）
Co-Seg++: Mutual Prompt-Guided Collaborative Learning for Versatile Medical Segmentation
School of Computer Science, University of Nottingham Ningbo China（诺丁汉大学宁波校区计算机科学学院）；University of Nottingham, UK（诺丁汉大学（英国））；Graduate School of Information, Production and Systems, Waseda University, Japan（早稻田大学信息、生产与系统研究生院）；Yale University（耶鲁大学）
Instance segmentation is the problem of detecting and delineating each distinct object of interest appearing in an image. Current instance segmentation approaches consist of ensembles of modules that are trained independently of each other, thus missing opportunities for joint learning. Here we propose a new instance segmentation paradigm consisting in an end-to-end method that learns how to segment instances sequentially. The model is based on a recurrent neural network that sequentially finds objects and their segmentations one at a time. This net is provided with a spatial memory that keeps…
St. Petersburg Institute for Informatics and Automation of RAS（俄罗斯科学院圣彼得堡信息学与自动化研究所）
In the paper a piecewise constant image approximations of sequential number of pixel clusters or segments are treated. A majorizing of optimal approximation sequence by hierarchical sequence of image approximations is studied. Transition from pixel clustering to image segmentation by reducing of segment numbers in clusters is provided. Algorithms are proved by elementary formulas.
St. Petersburg Institute for Informatics and Automation of RAS（俄罗斯科学院圣彼得堡信息学与自动化研究所）
Piecewise constant image approximations of sequential number of segments or clusters of disconnected pixels are treated. The method of majorizing of optimal approximation sequence by hierarchical sequence of image approximations is proposed. A generalization for multidimensional case of color and multispectral images is foreseen.
We investigate Referring Image Segmentation (RIS), which outputs a segmentation map corresponding to the natural language description. Addressing RIS efficiently requires considering the interactions happening across visual and linguistic modalities and the interactions within each modality. Existing methods are limited because they either compute different forms of interactions sequentially (leading to error propagation) or ignore intramodal interactions. We address this limitation by performing all three interactions simultaneously through a Synchronous Multi-Modal Fusion Module (SFM). Moreo…
Universitat Politècnica de Catalunya（加泰罗尼亚理工大学）；Barcelona Supercomputing Center（巴塞罗那超级计算中心）
We present a recurrent model for semantic instance segmentation that sequentially generates binary masks and their associated class probabilities for every object in an image. Our proposed system is trainable end-to-end from an input image to a sequence of labeled masks and, compared to methods relying on object proposals, does not require post-processing steps on its output. We study the suitability of our recurrent model on three different instance segmentation benchmarks, namely Pascal VOC 2012, CVPPP Plant Leaf Segmentation and Cityscapes. Further, we analyze the object sorting patterns ge…
Opel Automobile GmbH（欧宝汽车公司）；Institute of Measurement and Control Systems, Karlsruhe Institute of Technology (KIT)（卡尔斯鲁厄理工学院测量与控制系统研究所）
3D pedestrian detection is a challenging task in automated driving because pedestrians are relatively small, frequently occluded and easily confused with narrow vertical objects. LiDAR and camera are two commonly used sensor modalities for this task, which should provide complementary information. Unexpectedly, LiDAR-only detection methods tend to outperform multisensor fusion methods in public benchmarks. Recently, PointPainting has been presented to eliminate this performance drop by effectively fusing the output of a semantic segmentation network instead of the raw image information. In thi…
The Chinese University of Hong Kong（香港中文大学）；Shenzhen University（深圳大学）；The Hong Kong Polytechnic University（香港理工大学）；Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）
Boundary incompleteness raises great challenges to automatic prostate segmentation in ultrasound images. Shape prior can provide strong guidance in estimating the missing boundary, but traditional shape models often suffer from hand-crafted descriptors and local information loss in the fitting procedure. In this paper, we attempt to address those issues with a novel framework. The proposed framework can seamlessly integrate feature extraction and shape prior exploring, and estimate the complete boundary with a sequential manner. Our framework is composed of three key modules. Firstly, we seria…
In this paper we are interested in the problem of image segmentation given natural language descriptions, i.e. referring expressions. Existing works tackle this problem by first modeling images and sentences independently and then segment images by combining these two types of representations. We argue that learning word-to-image interaction is more native in the sense of jointly modeling two modalities for the image segmentation task, and we propose convolutional multimodal LSTM to encode the sequential interactions between individual words, visual information, and spatial information. We sho…
Harvard University（哈佛大学）；Technical University of Munich（慕尼黑工业大学）；MIT（麻省理工学院）；University of Cambridge（剑桥大学）；Donostia International Physics Center（多诺斯蒂亚国际物理中心）；University of the Basque Country（巴斯克大学）；Ikerbasque, Basque Foundation for Science（巴斯克科学基金会伊克巴斯克）；HHMI（霍华德·休斯医学研究所）；Boston College（波士顿学院）
Instance segmentation for unlabeled imaging modalities is a challenging but essential task as collecting expert annotation can be expensive and time-consuming. Existing works segment a new modality by either deploying a pre-trained model optimized on diverse training data or conducting domain translation and image segmentation as two independent steps. In this work, we propose a novel Cyclic Segmentation Generative Adversarial Network (CySGAN) that conducts image translation and instance segmentation jointly using a unified framework. Besides the CycleGAN losses for image translation and super…
SRPR-Net: Semantic and Relational Prompt Refinement for Automated SAM-based Instance Segmentation
Ruijin-XJTLU Intelligent Medicine Institute, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine（瑞金-西交利物浦智能医学研究所，瑞金医院，上海交通大学医学院）；School of Biomedical Engineering, Shanghai Jiao Tong University（上海交通大学生物医学工程学院）
Beijing Institute of Technology（北京理工大学）；MEGVII Technology（旷视科技）；Beijing Academy of Artificial Intelligence（北京智源人工智能研究院）
Sparsely annotated semantic segmentation (SASS) aims to train a segmentation network with coarse-grained (i.e., point-, scribble-, and block-wise) supervisions, where only a small proportion of pixels are labeled in each image. In this paper, we propose a novel tree energy loss for SASS by providing semantic guidance for unlabeled pixels. The tree energy loss represents images as minimum spanning trees to model both low-level and high-level pair-wise affinities. By sequentially applying these affinities to the network prediction, soft pseudo labels for unlabeled pixels are generated in a coars…
Adobe Research（Adobe研究院）；Snapchat Research（Snapchat研究院）；University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
Learning long-term spatial-temporal features are critical for many video analysis tasks. However, existing video segmentation methods predominantly rely on static image segmentation techniques, and methods capturing temporal dependency for segmentation have to depend on pretrained optical flow models, leading to suboptimal solutions for the problem. End-to-end sequential learning to explore spatial-temporal features for video segmentation is largely limited by the scale of available video segmentation datasets, i.e., even the largest video segmentation dataset only contains 90 short video clip…
Deep learning approaches are nowadays ubiquitously used to tackle computer vision tasks such as semantic segmentation, requiring large datasets and substantial computational power. Continual learning for semantic segmentation (CSS) is an emerging trend that consists in updating an old model by sequentially adding new classes. However, continual learning methods are usually prone to catastrophic forgetting. This issue is further aggravated in CSS where, at each step, old classes from previous iterations are collapsed into the background. In this paper, we propose Local POD, a multi-scale poolin…
University of Manitoba（曼尼托巴大学）；Shanghai University（上海大学）
We consider referring image segmentation. It is a problem at the intersection of computer vision and natural language understanding. Given an input image and a referring expression in the form of a natural language sentence, the goal is to segment the object of interest in the image referred by the linguistic query. To this end, we propose a dual convolutional LSTM (ConvLSTM) network to tackle this problem. Our model consists of an encoder network and a decoder network, where ConvLSTM is used in both encoder and decoder networks to capture spatial and sequential information. The encoder networ…
Deep learning approaches are nowadays ubiquitously used to tackle computer vision tasks such as semantic segmentation, requiring large datasets and substantial computational power. Continual learning for semantic segmentation (CSS) is an emerging trend that consists in updating an old model by sequentially adding new classes. However, continual learning methods are usually prone to catastrophic forgetting. This issue is further aggravated in CSS where, at each step, old classes from previous iterations are collapsed into the background. In this paper, we propose Local POD, a multi-scale poolin…
In this work we address the task of observing the performance of a semantic segmentation deep neural network (DNN) during online operation, i.e., during inference, which is of high importance in safety-critical applications such as autonomous driving. Here, many high-level decisions rely on such DNNs, which are usually evaluated offline, while their performance in online operation remains unknown. To solve this problem, we propose an improved online performance prediction scheme, building on a recently proposed concept of predicting the primary semantic segmentation task's performance. This ca…
Porsche Engineering Group GmbH（保时捷工程集团有限公司）；Fraunhofer Institute of Optronics, Systems Technologies and Image Exploitation IOSB（弗劳恩霍夫光电、系统技术与图像利用研究所IOSB）；Karlsruhe Institute of Technology（卡尔斯鲁厄理工学院）
Class-incremental learning for semantic segmentation (CiSS) is presently a highly researched field which aims at updating a semantic segmentation model by sequentially learning new semantic classes. A major challenge in CiSS is overcoming the effects of catastrophic forgetting, which describes the sudden drop of accuracy on previously learned classes after the model is trained on a new set of classes. Despite latest advances in mitigating catastrophic forgetting, the underlying causes of forgetting specifically in CiSS are not well understood. Therefore, in a set of experiments and representat…
National University of Singapore（新加坡国立大学）；CMU（卡内基梅隆大学）；Nankai University（南开大学）；Beijing Jiaotong University（北京交通大学）；AI Institute（360人工智能研究院）
We investigate a principle way to progressively mine discriminative object regions using classification networks to address the weakly-supervised semantic segmentation problems. Classification networks are only responsive to small and sparse discriminative regions from the object of interest, which deviates from the requirement of the segmentation task that needs to localize dense, interior and integral regions for pixel-wise inference. To mitigate this gap, we propose a new adversarial erasing approach for localizing and expanding object regions progressively. Starting with a single small obj…
Recent efforts in multi-domain learning for semantic segmentation attempt to learn multiple geographical datasets in a universal, joint model. A simple fine-tuning experiment performed sequentially on three popular road scene segmentation datasets demonstrates that existing segmentation frameworks fail at incrementally learning on a series of visually disparate geographical domains. When learning a new domain, the model catastrophically forgets previously learned knowledge. In this work, we pose the problem of multi-domain incremental learning for semantic segmentation. Given a model trained o…
Dynamic Prompt Generation for Interactive 3D Medical Image Segmentation Training
Medical Physics, Department of Diagnostic and Interventional Radiology, Medical Center—University of Freiburg, Faculty of Medicine, University of Freiburg（医学物理，诊断与介入放射科，弗赖堡大学医学中心，医学院，弗赖堡大学）；University of Freiburg（弗赖堡大学）；ELLIS Institute Tübingen（图宾根ELLIS研究所）
Hausdorff Centre for Mathematics, Rheinische Friedrich-Wilhelms-Universität Bonn（波恩莱茵弗里德里希·威廉大学豪斯多夫数学中心）；Delft Institute of Applied Mathematics, Technische Universiteit Delft（代尔夫特理工大学代尔夫特应用数学研究所）；Maxwell Institute for Mathematical Sciences & School of Mathematical and Computer Sciences, Heriot-Watt University（赫瑞-瓦特大学麦克斯韦数学科学研究所与数学和计算机科学学院）；Department of Applied Mathematics and Theoretical Physics, University of Cambridge（剑桥大学应用数学与理论物理系）
In clinical settings, where acquisition conditions and patient populations change over time, continual learning is key for ensuring the safe use of deep neural networks. Yet most existing work focuses on convolutional architectures and image classification. Instead, radiologists prefer to work with segmentation models that outline specific regions-of-interest, for which Transformer-based architectures are gaining traction. The self-attention mechanism of Transformers could potentially mitigate catastrophic forgetting, opening the way for more robust medical image segmentation. In this work, we…
FSANet: Frequency-Spatial Aware Network for Image Segmentation
Delft University of Technology（代尔夫特理工大学）；Southern Medical University（南方医科大学）；Tianjin University（天津大学）；Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）
University of Bern（伯尔尼大学）；Shanghai Jiao Tong University（上海交通大学）
Convolutional Neural Networks (CNNs) have achieved state-of-the-art performance in many different 2D medical image analysis tasks. In clinical practice, however, a large part of the medical imaging data available is in 3D. This has motivated the development of 3D CNNs for volumetric image segmentation in order to benefit from more spatial context. Due to GPU memory restrictions caused by moving to fully 3D, state-of-the-art methods depend on subvolume/patch processing and the size of the input patch is usually small, limiting the incorporation of larger context information for a better perform…
University of Toronto（多伦多大学）；Canadian Institute for Advanced Research（加拿大高级研究院）
While convolutional neural networks have gained impressive success recently in solving structured prediction problems such as semantic segmentation, it remains a challenge to differentiate individual object instances in the scene. Instance segmentation is very important in a variety of applications, such as autonomous driving, image captioning, and visual question answering. Techniques that combine large graphical models with low-level vision have been proposed to address this problem; however, we propose an end-to-end recurrent neural network (RNN) architecture with an attention mechanism to …
In this paper, a fast and practical GPU-based implementation of Fuzzy C-Means(FCM) clustering algorithm for image segmentation is proposed. First, an extensive analysis is conducted to study the dependency among the image pixels in the algorithm for parallelization. The proposed GPU-based FCM has been tested on digital brain simulated dataset to segment white matter(WM), gray matter(GM) and cerebrospinal fluid (CSF) soft tissue regions. The execution time of the sequential FCM is 519 seconds for an image dataset with the size of 1MB. While the proposed GPU-based FCM requires only 2.33 seconds …
Camera and lidar are important sensor modalities for robotics in general and self-driving cars in particular. The sensors provide complementary information offering an opportunity for tight sensor-fusion. Surprisingly, lidar-only methods outperform fusion methods on the main benchmark datasets, suggesting a gap in the literature. In this work, we propose PointPainting: a sequential fusion method to fill this gap. PointPainting works by projecting lidar points into the output of an image-only semantic segmentation network and appending the class scores to each point. The appended (painted) poin…
Nanjing University（南京大学）；Medical School of Nanjing University（南京大学医学院）；National Institute of Healthcare Data Science, Nanjing University（南京大学国家健康数据科学研究院）；UNC Chapel Hill（北卡罗来纳大学教堂山分校）
Conventional data augmentation realized by performing simple pre-processing operations (\eg, rotation, crop, \etc) has been validated for its advantage in enhancing the performance for medical image segmentation. However, the data generated by these conventional augmentation methods are random and sometimes harmful to the subsequent segmentation. In this paper, we developed a novel automatic learning-based data augmentation method for medical image segmentation which models the augmentation task as a trial-and-error procedure using deep reinforcement learning (DRL). In our method, we innovativ…
Charles Sturt University（查尔斯特大学）；CSIRO（联邦科学与工业研究组织）
We propose Ordered Subspace Clustering (OSC) to segment data drawn from a sequentially ordered union of subspaces. Similar to Sparse Subspace Clustering (SSC) we formulate the problem as one of finding a sparse representation but include an additional penalty term to take care of sequential data. We test our method on data drawn from infrared hyper spectral, video and motion capture data. Experiments show that our method, OSC, outperforms the state of the art methods: Spatial Subspace Clustering (SpatSC), Low-Rank Representation (LRR) and SSC.
Future advancements in robot autonomy and sophistication of robotics tasks rest on robust, efficient, and task-dependent semantic understanding of the environment. Semantic segmentation is the problem of simultaneous segmentation and categorization of a partition of sensory data. The majority of current approaches tackle this using multi-class segmentation and labeling in a Conditional Random Field (CRF) framework or by generating multiple object hypotheses and combining them sequentially. In practical settings, the subset of semantic labels that are needed depend on the task and particular sc…
