This paper proposes a novel deep learning architecture for semantic segmentation. The proposed Global and Selective Attention Network (GSANet) features Atrous Spatial Pyramid Pooling (ASPP) with a novel sparsemax global attention and a novel selective attention that deploys a condensation and diffusion mechanism to aggregate the multi-scale contextual information from the extracted deep features. A selective attention decoder is also proposed to process the GSA-ASPP outputs for optimizing the softmax volume. We are the first to benchmark the performance of semantic segmentation networks with the low-complexity feature extraction network (FXN) MobileNetEdge, that is optimized for low latency on edge devices. We show that GSANet can result in more accurate segmentation with MobileNetEdge, as well as with strong FXNs, such as Xception. GSANet improves the state-of-art semantic segmentation accuracy on both the ADE20k and the Cityscapes datasets.
Nagoya Institute of Technology（名古屋工业大学）；RIKEN Center for Advanced Intelligence Project（理化学研究所先进智能项目中心）；National Institute for Material Science（国立材料科学研究所）
Image segmentation is one of the most fundamental tasks of computer vision. In many practical applications, it is essential to properly evaluate the reliability of individual segmentation results. In this study, we propose a novel framework to provide the statistical significance of segmentation results in the form of p-values. Specifically, we consider a statistical hypothesis test for determining the difference between the object and the background regions. This problem is challenging because the difference can be deceptively large (called segmentation bias) due to the adaptation of the segm…
Nagoya Institute of Technology（名古屋工业大学）；RIKEN（理化学研究所）；Nagoya University（名古屋大学）
Although a vast body of literature relates to image segmentation methods that use deep neural networks (DNNs), less attention has been paid to assessing the statistical reliability of segmentation results. In this study, we interpret the segmentation results as hypotheses driven by DNN (called DNN-driven hypotheses) and propose a method by which to quantify the reliability of these hypotheses within a statistical hypothesis testing framework. Specifically, we consider a statistical hypothesis test for the difference between the object and background regions. This problem is challenging, as the…
Wuhan University（武汉大学）；Renmin Hospital of Wuhan University（武汉大学人民医院）；Xi’an Aeronautical University（西安航空学院）
Automated medical image segmentation plays an important role in many clinical applications, which however is a very challenging task, due to complex background texture, lack of clear boundary and significant shape and texture variation between images. Many researchers proposed an encoder-decoder architecture with skip connections to combine low-level feature maps from the encoder path with high-level feature maps from the decoder path for automatically segmenting medical images. The skip connections have been shown to be effective in recovering fine-grained details of the target objects and ma…
Real-time semantic segmentation has received considerable attention due to growing demands in many practical applications, such as autonomous vehicles, robotics, etc. Existing real-time segmentation approaches often utilize feature fusion to improve segmentation accuracy. However, they fail to fully consider the feature information at different resolutions and the receptive fields of the networks are relatively limited, thereby compromising the performance. To tackle this problem, we propose a light Cascaded Selective Resolution Network (CSRNet) to improve the performance of real-time segmenta…
This paper presents a novel selective constraint propagation method for constrained image segmentation. In the literature, many pairwise constraint propagation methods have been developed to exploit pairwise constraints for cluster analysis. However, since most of these methods have a polynomial time complexity, they are not much suitable for segmentation of images even with a moderate size, which is actually equivalent to cluster analysis with a large data size. Considering the local homogeneousness of a natural image, we choose to perform pairwise constraint propagation only over a selected …
Baidu Research（百度研究院）；National Engineering Laboratory for Deep Learning Technology and Application（深度学习技术与应用国家工程实验室）
Recently, it has attracted more and more attentions to fuse multi-scale features for semantic image segmentation. Various works were proposed to employ progressive local or global fusion, but the feature fusions are not rich enough for modeling multi-scale context features. In this work, we focus on fusing multi-scale features from Transformer-based backbones for semantic segmentation, and propose a Feature Selective Transformer (FeSeFormer), which aggregates features from all scales (or levels) for each query feature. Specifically, we first propose a Scale-level Feature Selection (SFS) module…
University of Central Florida（中佛罗里达大学）；Google Research（谷歌研究院）
We study the problem of semantic segmentation calibration. Lots of solutions have been proposed to approach model miscalibration of confidence in image classification. However, to date, confidence calibration research on semantic segmentation is still limited. We provide a systematic study on the calibration of semantic segmentation models and propose a simple yet effective approach. First, we find that model capacity, crop size, multi-scale testing, and prediction correctness have impact on calibration. Among them, prediction correctness, especially misprediction, is more important to miscali…
Convolutional neural networks model the transformation of the input sensory data at the bottom of a network hierarchy to the semantic information at the top of the visual hierarchy. Feedforward processing is sufficient for some object recognition tasks. Top-Down selection is potentially required in addition to the Bottom-Up feedforward pass. It can, in part, address the shortcoming of the loss of location information imposed by the hierarchical feature pyramids. We propose a unified 2-pass framework for object segmentation that augments Bottom-Up \convnets with a Top-Down selection network. We…
Medical image segmentation has been widely recognized as a pivot procedure for clinical diagnosis, analysis, and treatment planning. However, the laborious and expensive annotation process lags down the speed of further advances. Contrastive learning-based weight pre-training provides an alternative by leveraging unlabeled data to learn a good representation. In this paper, we investigate how contrastive learning benefits the general supervised medical segmentation tasks. To this end, patch-dragsaw contrastive regularization (PDCR) is proposed to perform patch-level tugging and repulsing with …
Hong Kong Centre for Cerebro-Cardiovascular Health Engineering（香港心脑血管健康工程中心）；City University of Hong Kong（香港城市大学）；King Fahd University of Petroleum and Minerals（法赫德国王石油矿产大学）；The Hong Kong Polytechnic University（香港理工大学）
Despite recent advances in data-independent and deep-learning algorithms, unstained live adherent cell instance segmentation remains a long-standing challenge in cell image processing. Adherent cells' inherent visual characteristics, such as low contrast structures, fading edges, and irregular morphology, have made it difficult to distinguish from one another, even by human experts, let alone computational methods. In this study, we developed a novel deep-learning algorithm called dual-view selective instance segmentation network (DVSISN) for segmenting unstained adherent cells in differential…
Handong Global University（韩东国际大学）；Sungkyunkwan University（成均馆大学）；Institute for Basic Science（基础科学研究院）
Monocular simultaneous localization and mapping (SLAM) is emerging in advanced driver assistance systems and autonomous driving, because a single camera is cheap and easy to install. Conventional monocular SLAM has two major challenges leading inaccurate localization and mapping. First, it is challenging to estimate scales in localization and mapping. Second, conventional monocular SLAM uses inappropriate mapping factors such as dynamic objects and low-parallax areas in mapping. This paper proposes an improved real-time monocular SLAM that resolves the aforementioned challenges by efficiently …
We present a novel lightweight convolutional neural network for point cloud analysis. In contrast to many current CNNs which increase receptive field by downsampling point cloud, our method directly operates on the entire point sets without sampling and achieves good performances efficiently. Our network consists of point voxel convolution (PVC) layer as building block. Each layer has two parallel branches, namely the voxel branch and the point branch. For the voxel branch specifically, we aggregate local features on non-empty voxel centers to reduce geometric information loss caused by voxeli…
Adapting Medical Vision Foundation Models for Volumetric Medical Image Segmentation via Active Learning and Selective Semi-supervised Fine-tuning
Mallinckrodt Institute of Radiology（马林克罗德放射医学研究所）；Institute for Informatics, Data Science and Biostatistics（信息学、数据科学与生物统计学研究所）；Department of Radiology, Perelman School of Medicine（放射科，佩尔曼医学院）；Center for AI and Data Science for Integrated Diagnostics (AI2D)（集成诊断人工智能与数据科学中心（AI2D））
Layer-wise Noise Guided Selective Wavelet Reconstruction for Robust Medical Image Segmentation
Big Data and Software College, Chongqing University（重庆大学大数据与软件学院）；Office of Scientific Research, Peking University（北京大学科研办公室）；Key Lab of High Confidence Software Technology, Ministry of Education (Peking University)（教育部高可信软件技术重点实验室（北京大学））；School of Computer Science, Peking University（北京大学计算机学院）；Department of Cardiology and Institute of Vascular Medicine, Peking University Third Hospital（北京大学第三医院心内科和血管医学研究院）
DAS-SK: An Adaptive Model Integrating Dual Atrous Separable and Selective Kernel CNN for Agriculture Semantic Segmentation
Electrical & Computer Engineering Department of Lakehead University（拉夫莱德大学电气与计算机工程系）；Faculty of Software Engineering of Lakehead University（拉夫莱德大学软件工程系）；Faculty of Applied Science of the University of Alabama（阿拉巴马大学应用科学系）；School of Computer Science Engineering and Information Systems, Vellore Institute of Technology（维洛雷理工学院计算机科学工程与信息系统学院）
University of Central Florida（中佛罗里达大学）；Mayo Clinic Cancer Center（妙佑医疗国际癌症中心）
Adversarial learning has been proven to be effective for capturing long-range and high-level label consistencies in semantic segmentation. Unique to medical imaging, capturing 3D semantics in an effective yet computationally efficient way remains an open problem. In this study, we address this computational burden by proposing a novel projective adversarial network, called PAN, which incorporates high-level 3D information through 2D projections. Furthermore, we introduce an attention module into our framework that helps for a selective integration of global information directly from our segmen…
FisherTune: Fisher-Guided Robust Tuning of Vision Foundation Models for Domain Generalized Segmentation
School of Artificial Intelligence, Xidian University（西安电子科技大学人工智能学院）；University of Trento（特伦托大学）；School of Computer Science and Information Engineering, Hefei University of Technology（合肥工业大学计算机与信息工程学院）
College of Electrical Engineering, Zhejiang University（浙江大学电气工程学院）
Compared with other semantic segmentation tasks, portrait segmentation requires both higher precision and faster inference speed. However, this problem has not been well studied in previous works. In this paper, we propose a lightweight network architecture, called Boundary-Aware Network (BANet) which selectively extracts detail information in boundary area to make high-quality segmentation output with real-time( >25FPS) speed. In addition, we design a new loss function called refine loss which supervises the network with image level gradient information. Our model is able to produce finer seg…
Most modern approaches for domain adaptive semantic segmentation rely on continued access to source data during adaptation, which may be infeasible due to computational or privacy constraints. We focus on source-free domain adaptation for semantic segmentation, wherein a source model must adapt itself to a new target domain given only unlabeled target data. We propose Augmentation Consistency-guided Self-training (AUGCO), a source-free adaptation algorithm that uses the model's pixel-level predictive consistency across diverse, automatically generated views of each target image along with mode…
Adaptive Frequency Enhancement Network for Remote Sensing Image Semantic Segmentation
School of Computer Science and Technology, Ocean University of China（中国海洋大学计算机科学与技术学院）；Department of Electrical and Computer Engineering, Mississippi State University（密西西比州立大学电气与计算机工程系）
University of Waterloo（滑铁卢大学）；Waterloo Artificial Intelligence Institute（滑铁卢人工智能研究所）；DarwinAI Corp.（DarwinAI公司）
In this study, we introduce \textbf{AttendSeg}, a low-precision, highly compact deep neural network tailored for on-device semantic segmentation. AttendSeg possesses a self-attention network architecture comprising of light-weight attention condensers for improved spatial-channel selective attention at a very low complexity. The unique macro-architecture and micro-architecture design properties of AttendSeg strike a strong balance between representational power and efficiency, achieved via a machine-driven design exploration strategy tailored specifically for the task at hand. Experimental res…
CAD: Confidence-Aware Adaptive Displacement for Semi-Supervised Medical Image Segmentation
College of Information and Intelligence, Hunan Agricultural University（湖南农业大学信息与智能科学学院）；School of Computer Science and Engineering, University of New South Wales（新南威尔士大学计算机科学与工程学院）
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…
Friedrich-Alexander University Erlangen-Nürnberg (FAU)（埃尔朗根-纽伦堡大学）；Siemens Healthcare GmbH（西门子医疗有限公司）；Erlangen Graduate School in Advanced Optical Technologies (SAOT)（埃尔朗根先进光学技术研究生院）
In interactive medical image segmentation, anatomical structures are extracted from reconstructed volumetric images. The first iterations of user interaction traditionally consist of drawing pictorial hints as an initial estimate of the object to extract. Only after this time consuming first phase, the efficient selective refinement of current segmentation results begins. Erroneously labeled seeds, especially near the border of the object, are challenging to detect and replace for a human and may substantially impact the overall segmentation quality. We propose an automatic seeding pipeline as…
University of Georgia（佐治亚大学）；Shanghai Jiao Tong University（上海交通大学）
We introduce a neural network framework, utilizing adversarial learning to partition an image into two cuts, with one cut falling into a reference distribution provided by the user. This concept tackles the task of unsupervised anomaly segmentation, which has attracted increasing attention in recent years due to their broad applications in tasks with unlabelled data. This Adversarial-based Selective Cutting network (ASC-Net) bridges the two domains of cluster-based deep learning methods and adversarial-based anomaly/novelty detection algorithms. We evaluate this unsupervised learning model on …
University of Twente（特文特大学）；Wuhan University（武汉大学）
In recent years, the task of segmenting foreground objects from background in a video, i.e. video object segmentation (VOS), has received considerable attention. In this paper, we propose a single end-to-end trainable deep neural network, convolutional gated recurrent Mask-RCNN, for tackling the semi-supervised VOS task. We take advantage of both the instance segmentation network (Mask-RCNN) and the visual memory module (Conv-GRU) to tackle the VOS task. The instance segmentation network predicts masks for instances, while the visual memory module learns to selectively propagate information fo…
Training deep networks for semantic segmentation requires annotation of large amounts of data, which can be time-consuming and expensive. Unfortunately, these trained networks still generalize poorly when tested in domains not consistent with the training data. In this paper, we show that by carefully presenting a mixture of labeled source domain and proxy-labeled target domain data to a network, we can achieve state-of-the-art unsupervised domain adaptation results. With our design, the network progressively learns features specific to the target domain using annotation from only the source d…
Guangdong General Hospital（广东省人民医院）；Guangdong Academy of Medical Sciences（广东省医学科学院）；Henan Provincial People’s Hospital（河南省人民医院）；Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）
Multi-modal magnetic resonance imaging (MRI) is essential in clinics for comprehensive diagnosis and surgical planning. Nevertheless, the segmentation of multi-modal MR images tends to be time-consuming and challenging. Convolutional neural network (CNN)-based multi-modal MR image analysis commonly proceeds with multiple down-sampling streams fused at one or several layers. Although inspiring performance has been achieved, the feature fusion is usually conducted through simple summation or concatenation without optimization. In this work, we propose a supervised image fusion method to selectiv…
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 Science and Technology of China（中国科学技术大学）
Skin lesion segmentation is an important step for automatic melanoma diagnosis. Due to the non-negligible diversity of lesions from different patients, extracting powerful context for fine-grained semantic segmentation is still challenging today. Although the deep convolutional neural network (CNNs) have made significant improvements on skin lesion segmentation, they often fail to reserve the spatial details and long-range dependencies context due to consecutive convolution striding and pooling operations inside CNNs. In this paper, we formulate a cascaded context enhancement neural network fo…
Huazhong University of Science and Technology（华中科技大学）
It is well known that attention mechanisms can effectively improve the performance of many CNNs including object detectors. Instead of refining feature maps prevalently, we reduce the prohibitive computational complexity by a novel attempt at attention. Therefore, we introduce an efficient object detector called Selective Convolutional Network (SCN), which selectively calculates only on the locations that contain meaningful and conducive information. The basic idea is to exclude the insignificant background areas, which effectively reduces the computational cost especially during the feature e…
Animals have evolved to restrict their sensing capabilities to certain region of electromagnetic spectrum. This is surprisingly a very narrow band on a vast scale which makes one think if there is a systematic bias underlying such selective filtration. The situation becomes even more intriguing when we find a sharp cutoff point at Near-infrared point whereby almost all animal vision systems seem to have a lower bound. This brings us to an interesting question: did evolution "intentionally" performed such a restriction in order to evolve higher visual cognition? In this work this question is ad…
UCAD: Uncertainty-guided Contour-aware Displacement for semi-supervised medical image segmentation
University of Science and Technology of China（科学技术大学）；Suzhou Institute for Advanced Research（苏州先进研究院）；State Key Laboratory of Precision and Intelligent Chemistry（精密与智能化学国家重点实验室）
Carnegie Mellon University（卡内基梅隆大学）；Ryerson University（瑞尔森大学）；Facebook AI Research（Facebook人工智能研究院）
We introduce an approach to integrate segmentation information within a convolutional neural network (CNN). This counter-acts the tendency of CNNs to smooth information across regions and increases their spatial precision. To obtain segmentation information, we set up a CNN to provide an embedding space where region co-membership can be estimated based on Euclidean distance. We use these embeddings to compute a local attention mask relative to every neuron position. We incorporate such masks in CNNs and replace the convolution operation with a "segmentation-aware" variant that allows a neuron …
Among the neural network compression techniques, knowledge distillation is an effective one which forces a simpler student network to mimic the output of a larger teacher network. However, most of such model distillation methods focus on the image-level classification task. Directly adapting these methods to the task of semantic segmentation only brings marginal improvements. In this paper, we propose a simple, yet effective knowledge representation referred to as pixel-wise feature similarities (PFS) to tackle the challenging distillation problem of semantic segmentation. The developed PFS en…
