点云分割是计算机视觉中最重要的任务之一，在科研、工业和商业领域有着广泛应用，相关研究已在三维物体与场景理解方面取得诸多突破。现有方法通常采用层级架构进行特征表征，但层级网络中常用的采样与分组方法仅基于逐点三维坐标，忽略了点簇的局部语义同质性；此外，当前普遍使用的最远点采样（Farthest Point Sampling, FPS）方法往往是计算瓶颈。针对这些问题，我们提出一种新型三维点云表征网络——动态聚类Transformer网络（Dynamic Clustering Transformer Network, DCTNet），该网络采用编码器-解码器架构，可同时实现局部与全局特征学习。具体而言，我们在编码器中提出了基于语义特征的新型动态采样与聚类方法，使模型能够感知局部语义同质性，从而进行局部特征聚合；此外，在解码器中提出了一种高效的语义特征引导上采样方法。我们在基于物体的数据集ShapeNet、城市导航数据集Toronto-3D以及一个多光谱激光雷达数据集上对所提方法进行了评估，验证了DCTNet在各类实际工程应用中的性能。在ShapeNet数据集上，DCTNet的推理速度比现有最优（State-of-the-Art, SOTA）模型快3.8-16.8倍，同时达到86.6%的逐实例平均交并比（mIoU），为当前最高得分。在其他数据集上，我们的方法同样优于现有方法，证实其成为点云分割领域新的最优方法。
英文摘要：
Point cloud segmentation is one of the most important tasks in computer vision with widespread scientific, industrial, and commercial applications. The research thereof has resulted in many breakthroughs in 3D object and scene understanding. Previous methods typically utilized hierarchical architectures for feature representation. However, the commonly used sampling and grouping methods in hierarchical networks are only based on point-wise three-dimensional coordinates, ignoring local semantic homogeneity of point clusters. Additionally, the prevalent Farthest Point Sampling (FPS) method is often a computational bottleneck. To address these issues, we propose a novel 3D point cloud representation network, called Dynamic Clustering Transformer Network (DCTNet). It has an encoder-decoder architecture, allowing for both local and global feature learning. Specifically, we propose novel semantic feature-based dynamic sampling and clustering methods in the encoder, which enables the model to be aware of local semantic homogeneity for local feature aggregation. Furthermore, in the decoder, we propose an efficient semantic feature-guided upsampling method. Our method was evaluated on an object-based dataset (ShapeNet), an urban navigation dataset (Toronto-3D), and a multispectral LiDAR dataset, verifying the performance of DCTNet across a wide variety of practical engineering applications. The inference speed of DCTNet is 3.8-16.8$\times$ faster than existing State-of-the-Art (SOTA) models on the ShapeNet dataset, while achieving an instance-wise mIoU of $86.6\%$, the current top score. Our method similarly outperforms previous methods on the other datasets, verifying it as the new State-of-the-Art in point cloud segmentation.
This paper proposes a hierarchical clustering approach for the segmentation of mobile LiDAR point clouds. We perform the hierarchical clustering on unorganized point clouds based on a proximity matrix. The dissimilarity measure in the proximity matrix is calculated by the Euclidean distances between clusters and the difference of normal vectors at given points. The main contribution of this paper is that we succeed to optimize the combination of clusters in the hierarchical clustering. The combination is obtained by achieving the matching of a bipartite graph, and optimized by solving the mini…
Hunan University（湖南大学）；Alibaba Group（阿里巴巴集团）；Jiangxi Provincial Natural Resources Cause Development Center（江西省自然资源事业发展中心）
Segmentation from point cloud data is essential in many applications such as remote sensing, mobile robots, or autonomous cars. However, the point clouds captured by the 3D range sensor are commonly sparse and unstructured, challenging efficient segmentation. In this paper, we present a fast solution to point cloud instance segmentation with small computational demands. To this end, we propose a novel fast Euclidean clustering (FEC) algorithm which applies a pointwise scheme over the clusterwise scheme used in existing works. Our approach is conceptually simple, easy to implement (40 lines in …
Image processing is an important research area in computer vision. Image segmentation plays the vital rule in image processing research. There exist so many methods for image segmentation. Clustering is an unsupervised study. Clustering can also be used for image segmentation. In this paper, an in-depth study is done on different clustering techniques that can be used for image segmentation with their pros and cons. An experiment for color image segmentation based on clustering with K-Means algorithm is performed to observe the accuracy of clustering technique for the segmentation purpose.
Hierarchical clustering is an effective and efficient approach widely used for classical image segmentation methods. However, many existing methods using neural networks generate segmentation masks directly from per-pixel features, complicating the architecture design and degrading the interpretability. In this work, we propose a simpler, more interpretable architecture, called HCFormer. HCFormer accomplishes image segmentation by bottom-up hierarchical clustering and allows us to interpret, visualize, and evaluate the intermediate results as hierarchical clustering results. HCFormer can addre…
Universitat de Barcelona（巴塞罗那大学）；University of Groningen（格罗宁根大学）；Computer Vision Center（计算机视觉中心）
In this paper, we present a new method for egocentric video temporal segmentation based on integrating a statistical mean change detector and agglomerative clustering(AC) within an energy-minimization framework. Given the tendency of most AC methods to oversegment video sequences when clustering their frames, we combine the clustering with a concept drift detection technique (ADWIN) that has rigorous guarantee of performances. ADWIN serves as a statistical upper bound for the clustering-based video segmentation. We integrate both techniques in an energy-minimization framework that serves to di…
We propose Clustering Mask Transformer (CMT-DeepLab), a transformer-based framework for panoptic segmentation designed around clustering. It rethinks the existing transformer architectures used in segmentation and detection; CMT-DeepLab considers the object queries as cluster centers, which fill the role of grouping the pixels when applied to segmentation. The clustering is computed with an alternating procedure, by first assigning pixels to the clusters by their feature affinity, and then updating the cluster centers and pixel features. Together, these operations comprise the Clustering Mask …
Effectively encoding multi-scale contextual information is crucial for accurate semantic segmentation. Existing transformer-based segmentation models combine features across scales without any selection, where features on sub-optimal scales may degrade segmentation outcomes. Leveraging from the inherent properties of Vision Transformers, we propose a simple yet effective module, Transformer Scale Gate (TSG), to optimally combine multi-scale features.TSG exploits cues in self and cross attentions in Vision Transformers for the scale selection. TSG is a highly flexible plug-and-play module, and …
National College of Engineering（国立工程学院）；Sathakathullah Appa College（萨塔卡图拉·阿帕学院）；Manonmaniam Sundaranar University（马诺尼亚姆·孙达拉纳大学）
Medical image segmentation demands an efficient and robust segmentation algorithm against noise. The conventional fuzzy c-means algorithm is an efficient clustering algorithm that is used in medical image segmentation. But FCM is highly vulnerable to noise since it uses only intensity values for clustering the images. This paper aims to develop a novel and efficient fuzzy spatial c-means clustering algorithm which is robust to noise. The proposed clustering algorithm uses fuzzy spatial information to calculate membership value. The input image is clustered using proposed ISFCM algorithm. A com…
Massachusetts Institute of Technology（麻省理工学院）；Princeton University（普林斯顿大学）
We present a method for hierarchical image segmentation that defines a disaffinity graph on the image, over-segments it into watershed basins, defines a new graph on the basins, and then merges basins with a modified, size-dependent version of single linkage clustering. The quasilinear runtime of the method makes it suitable for segmenting large images. We illustrate the method on the challenging problem of segmenting 3D electron microscopic brain images.
Nanjing University of Aeronautics and Astronautics（南京航空航天大学）
It is well believed that Transformer performs better in semantic segmentation compared to convolutional neural networks. Nevertheless, the original Vision Transformer may lack of inductive biases of local neighborhoods and possess a high time complexity. Recently, Swin Transformer sets a new record in various vision tasks by using hierarchical architecture and shifted windows while being more efficient. However, as Swin Transformer is specifically designed for image classification, it may achieve suboptimal performance on dense prediction-based segmentation task. Further, simply combing Swin T…
University of North Carolina at Chapel Hill（北卡罗来纳大学教堂山分校）
We propose iSegFormer, a memory-efficient transformer that combines a Swin transformer with a lightweight multilayer perceptron (MLP) decoder. With the efficient Swin transformer blocks for hierarchical self-attention and the simple MLP decoder for aggregating both local and global attention, iSegFormer learns powerful representations while achieving high computational efficiencies. Specifically, we apply iSegFormer to interactive 3D medical image segmentation.
In computer vision, image segmentation is always selected as a major research topic by researchers. Due to its vital rule in image processing, there always arises the need of a better image segmentation method. Clustering is an unsupervised study with its application in almost every field of science and engineering. Many researchers used clustering in image segmentation process. But still there requires improvement of such approaches. In this paper, a novel approach for clustering based image segmentation is proposed. Here, we give importance on color space and choose lab for this task. The fa…
Institute of Deep Learning, Baidu Research（百度研究院深度学习研究所）；National Engineering Laboratory for Deep Learning Technology and Application（深度学习技术及应用国家工程实验室）；School of Software, XinJiang University（新疆大学软件学院）
Transformers have shown impressive performance in various natural language processing and computer vision tasks, due to the capability of modeling long-range dependencies. Recent progress has demonstrated that combining such Transformers with CNN-based semantic image segmentation models is very promising. However, it is not well studied yet on how well a pure Transformer based approach can achieve for image segmentation. In this work, we explore a novel framework for semantic image segmentation, which is encoder-decoder based Fully Transformer Networks (FTN). Specifically, we first propose a P…
Princeton University（普林斯顿大学）；Middle East Technical University（中东技术大学）
A new segmentation fusion method is proposed that ensembles the output of several segmentation algorithms applied on a remotely sensed image. The candidate segmentation sets are processed to achieve a consensus segmentation using a stochastic optimization algorithm based on the Filtered Stochastic BOEM (Best One Element Move) method. For this purpose, Filtered Stochastic BOEM is reformulated as a segmentation fusion problem by designing a new distance learning approach. The proposed algorithm also embeds the computation of the optimum number of clusters into the segmentation fusion problem.
Transformer-based neural networks have surpassed promising performance on many biomedical image segmentation tasks due to a better global information modeling from the self-attention mechanism. However, most methods are still designed for 2D medical images while ignoring the essential 3D volume information. The main challenge for 3D transformer-based segmentation methods is the quadratic complexity introduced by the self-attention mechanism \cite{vaswani2017attention}. In this paper, we propose a novel transformer architecture for 3D medical image segmentation using an encoder-decoder style ar…
Ulm University（乌尔姆大学）；The University of Edinburgh（爱丁堡大学）；Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）；The University of Tübingen（蒂宾根大学）
We present an effective dynamic clustering algorithm for the task of temporal human action segmentation, which has comprehensive applications such as robotics, motion analysis, and patient monitoring. Our proposed algorithm is unsupervised, fast, generic to process various types of features, and applicable in both the online and offline settings. We perform extensive experiments of processing data streams, and show that our algorithm achieves the state-of-the-art results for both online and offline settings.
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.
We propose a novel solution for the task of video panoptic segmentation, that simultaneously predicts pixel-level semantic and instance segmentation and generates clip-level instance tracks. Our network, named VPS-Transformer, with a hybrid architecture based on the state-of-the-art panoptic segmentation network Panoptic-DeepLab, combines a convolutional architecture for single-frame panoptic segmentation and a novel video module based on an instantiation of the pure Transformer block. The Transformer, equipped with attention mechanisms, models spatio-temporal relations between backbone output…
Image segmentation in the medical domain is a challenging field owing to poor resolution and limited contrast. The predominantly used conventional segmentation techniques and the thresholding methods suffer from limitations because of heavy dependence on user interactions. Uncertainties prevalent in an image cannot be captured by these techniques. The performance further deteriorates when the images are corrupted by noise, outliers and other artifacts. The objective of this paper is to develop an effective robust fuzzy C- means clustering for segmenting vertebral body from magnetic resonance i…
Panoptic segmentation aims to address semantic and instance segmentation simultaneously in a unified framework. However, an efficient solution of panoptic segmentation in applications like autonomous driving is still an open research problem. In this work, we propose a novel LiDAR-based panoptic system, called SMAC-Seg. We present a learnable sparse multi-directional attention clustering to segment multi-scale foreground instances. SMAC-Seg is a real-time clustering-based approach, which removes the complex proposal network to segment instances. Most existing clustering-based methods use the d…
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% …
Imperial College London（帝国理工学院）；Fudan University（复旦大学）
This paper presents a novel method for face clustering in videos using a video-centralised transformer. Previous works often employed contrastive learning to learn frame-level representation and used average pooling to aggregate the features along the temporal dimension. This approach may not fully capture the complicated video dynamics. In addition, despite the recent progress in video-based contrastive learning, few have attempted to learn a self-supervised clustering-friendly face representation that benefits the video face clustering task. To overcome these limitations, our method employs …
The University of Sydney（悉尼大学）；Med-X Research Institute, Shanghai Jiao Tong University（上海交通大学Med-X研究院）
The segmentation of medical images is a fundamental step in automated clinical decision support systems. Existing medical image segmentation methods based on supervised deep learning, however, remain problematic because of their reliance on large amounts of labelled training data. Although medical imaging data repositories continue to expand, there has not been a commensurate increase in the amount of annotated data. Hence, we propose a new spatial guided self-supervised clustering network (SGSCN) for medical image segmentation, where we introduce multiple loss functions designed to aid in gro…
Beijing University of Posts and Telecommunications（北京邮电大学）
The CNN-based methods have achieved impressive results in medical image segmentation, but they failed to capture the long-range dependencies due to the inherent locality of the convolution operation. Transformer-based methods are recently popular in vision tasks because of their capacity for long-range dependencies and promising performance. However, it lacks in modeling local context. In this paper, taking medical image segmentation as an example, we present MISSFormer, an effective and powerful Medical Image Segmentation tranSFormer. MISSFormer is a hierarchical encoder-decoder network with …
Universitat Politècnica de Catalunya Barcelona Tech（加泰罗尼亚理工大学巴塞罗那技术学院）
This paper presents a co-clustering technique that, given a collection of images and their hierarchies, clusters nodes from these hierarchies to obtain a coherent multiresolution representation of the image collection. We formalize the co-clustering as a Quadratic Semi-Assignment Problem and solve it with a linear programming relaxation approach that makes effective use of information from hierarchies. Initially, we address the problem of generating an optimal, coherent partition per image and, afterwards, we extend this method to a multiresolution framework. Finally, we particularize this fra…
Intelligent Vision Research Lab, Federal University of Bahia（巴伊亚联邦大学智能视觉研究实验室）
Several image pattern recognition tasks rely on superpixel generation as a fundamental step. Image analysis based on superpixels facilitates domain-specific applications, also speeding up the overall processing time of the task. Recent superpixel methods have been designed to fit boundary adherence, usually regulating the size and shape of each superpixel in order to mitigate the occurrence of undersegmentation failures. Superpixel regularity and compactness sometimes imposes an excessive number of segments in the image, which ultimately decreases the efficiency of the final segmentation, spec…
Huazhong University of Science and Technology（华中科技大学）；City University of Hong Kong（香港城市大学）；Southeast University（东南大学）；Beijing Jiaotong University（北京交通大学）
Superpixel segmentation aims at dividing the input image into some representative regions containing pixels with similar and consistent intrinsic properties, without any prior knowledge about the shape and size of each superpixel. In this paper, to alleviate the limitation of superpixel segmentation applied in practical industrial tasks that detailed boundaries are difficult to be kept, we regard each representative region with independent semantic information as a subspace, and correspondingly formulate superpixel segmentation as a subspace clustering problem to preserve more detailed content…
Transformers have shown great success in medical image segmentation. However, transformers may exhibit a limited generalization ability due to the underlying single-scale self-attention (SA) mechanism. In this paper, we address this issue by introducing a Multi-scale hiERarchical vIsion Transformer (MERIT) backbone network, which improves the generalizability of the model by computing SA at multiple scales. We also incorporate an attention-based decoder, namely Cascaded Attention Decoding (CASCADE), for further refinement of multi-stage features generated by MERIT. Finally, we introduce an eff…
Beijing University of Posts and Telecommunications（北京邮电大学）；Johns Hopkins University（约翰斯·霍普金斯大学）
Subspace clustering refers to the problem of segmenting data drawn from a union of subspaces. State-of-the-art approaches for solving this problem follow a two-stage approach. In the first step, an affinity matrix is learned from the data using sparse or low-rank minimization techniques. In the second step, the segmentation is found by applying spectral clustering to this affinity. While this approach has led to state-of-the-art results in many applications, it is sub-optimal because it does not exploit the fact that the affinity and the segmentation depend on each other. In this paper, we pro…
Current state-of-the-art instance segmentation methods are not suited for real-time applications like autonomous driving, which require fast execution times at high accuracy. Although the currently dominant proposal-based methods have high accuracy, they are slow and generate masks at a fixed and low resolution. Proposal-free methods, by contrast, can generate masks at high resolution and are often faster, but fail to reach the same accuracy as the proposal-based methods. In this work we propose a new clustering loss function for proposal-free instance segmentation. The loss function pulls the…
University of California at Davis（加州大学戴维斯分校）；Huazhong University of Science and Technology（华中科技大学）；University of Bergen（卑尔根大学）；Hong Kong University of Science and Technology（香港科技大学）
We propose an effective framework for multi-phase image segmentation and semi-supervised data clustering by introducing a novel region force term into the Potts model. Assume the probability that a pixel or a data point belongs to each class is known a priori. We show that the corresponding indicator function obeys the Bernoulli distribution and the new region force function can be computed as the negative log-likelihood function under the Bernoulli distribution. We solve the Potts model by the primal-dual hybrid gradient method and the augmented Lagrangian method, which are based on two diffe…
Tongji University（同济大学）；The University of Hong Kong（香港大学）；SenseTime（商汤科技）；Shanghai AI Lab（上海人工智能实验室）
Although convolutional neural networks (CNNs) have achieved remarkable progress in weakly supervised semantic segmentation (WSSS), the effective receptive field of CNN is insufficient to capture global context information, leading to sub-optimal results. Inspired by the great success of Transformers in fundamental vision areas, this work for the first time introduces Transformer to build a simple and effective WSSS framework, termed WegFormer. Unlike existing CNN-based methods, WegFormer uses Vision Transformer (ViT) as a classifier to produce high-quality pseudo segmentation masks. To this en…
Laboratoire Hubert Curien, Université Jean Monnet（让·莫奈大学于贝尔·居里实验室）
Recent advances in depth imaging sensors provide easy access to the synchronized depth with color, called RGB-D image. In this paper, we propose an unsupervised method for indoor RGB-D image segmentation and analysis. We consider a statistical image generation model based on the color and geometry of the scene. Our method consists of a joint color-spatial-directional clustering method followed by a statistical planar region merging method. We evaluate our method on the NYU depth database and compare it with existing unsupervised RGB-D segmentation methods. Results show that, it is comparable w…
Semantic and instance segmentation algorithms are two general yet distinct image segmentation solutions powered by Convolution Neural Network. While semantic segmentation benefits extensively from the end-to-end training strategy, instance segmentation is frequently framed as a multi-stage task, supported by learning-based discrimination and post-process clustering. Independent optimizations on substages instigate the accumulation of segmentation errors. In this work, we propose to embed prior clustering information into an embedding learning framework FCRNet, stimulating the one-stage instanc…
Assigning consistent temporal identifiers to multiple moving objects in a video sequence is a challenging problem. A solution to that problem would have immediate ramifications in multiple object tracking and segmentation problems. We propose a strategy that treats the temporal identification task as a spatio-temporal clustering problem. We propose an unsupervised learning approach using a convolutional and fully connected autoencoder, which we call deep heterogeneous autoencoder, to learn discriminative features from segmentation masks and detection bounding boxes. We extract masks and their …
Clinically, the accurate annotation of lesions/tissues can significantly facilitate the disease diagnosis. For example, the segmentation of optic disc/cup (OD/OC) on fundus image would facilitate the glaucoma diagnosis, the segmentation of skin lesions on dermoscopic images is helpful to the melanoma diagnosis, etc. With the advancement of deep learning techniques, a wide range of methods proved the lesions/tissues segmentation can also facilitate the automated disease diagnosis models. However, existing methods are limited in the sense that they can only capture static regional correlations i…
Domain adaptive panoptic segmentation aims to mitigate data annotation challenge by leveraging off-the-shelf annotated data in one or multiple related source domains. However, existing studies employ two separate networks for instance segmentation and semantic segmentation which lead to excessive network parameters as well as complicated and computationally intensive training and inference processes. We design UniDAformer, a unified domain adaptive panoptic segmentation transformer that is simple but can achieve domain adaptive instance segmentation and semantic segmentation simultaneously wit…
Most approaches for semantic segmentation use only information from color cameras to parse the scenes, yet recent advancements show that using depth data allows to further improve performances. In this work, we focus on transformer-based deep learning architectures, that have achieved state-of-the-art performances on the segmentation task, and we propose to employ depth information by embedding it in the positional encoding. Effectively, we extend the network to multimodal data without adding any parameters and in a natural way that makes use of the strength of transformers' self-attention mod…
Conservatoire National des Arts et Métiers（法国国立工艺学院）；IRCAD（消化癌症研究所）
Transformer models achieve state-of-the-art results for image segmentation. However, achieving long-range attention, necessary to capture global context, with high-resolution 3D images is a fundamental challenge. This paper introduces the Full resolutIoN mEmory (FINE) transformer to overcome this issue. The core idea behind FINE is to learn memory tokens to indirectly model full range interactions while scaling well in both memory and computational costs. FINE introduces memory tokens at two levels: the first one allows full interaction between voxels within local image regions (patches), the …
Ulsan National Institute of Science and Technology（蔚山科学技术院）
Few-shot learning allows machines to classify novel classes using only a few labeled samples. Recently, few-shot segmentation aiming at semantic segmentation on low sample data has also seen great interest. In this paper, we propose a learnable module that can be placed on top of existing segmentation networks for performing few-shot segmentation. This module, called the task-adaptive feature transformer (TAFT), linearly transforms task-specific high-level features to a set of task agnostic features well-suited to conducting few-shot segmentation. The task-conditioned feature transformation al…
Video co-segmentation refers to the task of jointly segmenting common objects appearing in a given group of videos. In practice, high-dimensional data such as videos can be conceptually thought as being drawn from a union of subspaces corresponding to categories rather than from a smooth manifold. Therefore, segmenting data into respective subspaces --- subspace clustering --- finds widespread applications in computer vision, including co-segmentation. State-of-the-art methods via subspace clustering seek to solve the problem in two steps: First, an affinity matrix is built from data, with app…
Wuhan Institute of Technology（武汉工程大学）；Huazhong University of Science and technology（华中科技大学）
Medical image segmentation plays an essential role in developing computer-assisted diagnosis and therapy systems, yet still faces many challenges. In the past few years, the popular encoder-decoder architectures based on CNNs (e.g., U-Net) have been successfully applied in the task of medical image segmentation. However, due to the locality of convolution operations, they demonstrate limitations in learning global context and long-range spatial relations. Recently, several researchers try to introduce transformers to both the encoder and decoder components with promising results, but the effic…
When Swin Transformer Meets KANs: An Improved Transformer Architecture for Medical Image Segmentation
Department of Computer Science and Engineering, University of Notre Dame（计算机科学与工程系，诺丁汉大学）；Department of Computer Science, University of Texas Rio Grande Valley（计算机科学系，德克萨斯大学里奥格兰德谷分校）
Timestamp-Supervised Action Segmentation from the Perspective of Clustering
Institute of Software, Chinese Academy of Science（中国科学院软件研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；Tsinghua University（清华大学）
Tsinghua University（清华大学）；Tencent（腾讯）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）
Incremental semantic segmentation(ISS) is an emerging task where old model is updated by incrementally adding new classes. At present, methods based on convolutional neural networks are dominant in ISS. However, studies have shown that such methods have difficulty in learning new tasks while maintaining good performance on old ones (catastrophic forgetting). In contrast, a Transformer based method has a natural advantage in curbing catastrophic forgetting due to its ability to model both long-term and short-term tasks. In this work, we explore the reasons why Transformer based architecture are…
Deep neural networks have been a prevailing technique in the field of medical image processing. However, the most popular convolutional neural networks (CNNs) based methods for medical image segmentation are imperfect because they model long-range dependencies by stacking layers or enlarging filters. Transformers and the self-attention mechanism are recently proposed to effectively learn long-range dependencies by modeling all pairs of word-to-word attention regardless of their positions. The idea has also been extended to the computer vision field by creating and treating image patches as emb…
Johns Hopkins University（约翰斯·霍普金斯大学）；Rutgers, The State University of New Jersey（罗格斯新泽西州立大学）
Over the past decade, Deep Convolutional Neural Networks have been widely adopted for medical image segmentation and shown to achieve adequate performance. However, due to the inherent inductive biases present in the convolutional architectures, they lack understanding of long-range dependencies in the image. Recently proposed Transformer-based architectures that leverage self-attention mechanism encode long-range dependencies and learn representations that are highly expressive. This motivates us to explore Transformer-based solutions and study the feasibility of using Transformer-based netwo…
