本文提出轻量级模型HRSAM，通过视觉长度外推、Flexible Local Attention框架及Cycle-scan模块，在高分辨率交互式分割中以更低延迟超越SOTA。
摘要：
Segment Anything Model（SAM）推动了交互式分割的发展，但在高分辨率图像上受限于高昂的计算成本。这要求进行下采样以满足GPU约束，从而牺牲了高精度交互式分割所需的细粒度细节。为解决SAM的局限性，我们聚焦于视觉长度外推，并提出一个名为HRSAM的轻量级模型。该外推能力使在低分辨率上训练的HRSAM能够泛化到高分辨率。我们首先发现外推与注意力分数之间的联系，这促使我们将HRSAM建立在Swin注意力之上。随后，我们引入Flexible Local Attention（FLA）框架，利用CUDA优化的Efficient Memory Attention来加速HRSAM。在FLA中，我们实现了Flash Swin注意力，相比传统Swin注意力实现了超过35%的加速，并提出一种仅对KV进行填充的机制以增强外推能力。我们还开发了Cycle-scan模块，利用State Space模型高效扩展HRSAM的感受野。我们进一步在FLA中开发了HRSAM++，通过添加锚点图，以轻微的计算代价为外推提供多尺度数据增强和更大的感受野。实验表明，在标准训练下，HRSAM系列仅以38%的延迟超越了此前的SOTA。借助SAM蒸馏，外推能力使HRSAM系列在更低延迟下优于教师模型。进一步微调后，其性能显著超过此前的SOTA。
英文摘要：
The Segment Anything Model (SAM) has advanced interactive segmentation but is limited by the high computational cost on high-resolution images. This requires downsampling to meet GPU constraints, sacrificing the fine-grained details needed for high-precision interactive segmentation. To address SAM's limitations, we focus on visual length extrapolation and propose a lightweight model named HRSAM. The extrapolation enables HRSAM trained on low resolutions to generalize to high resolutions. We begin by finding the link between the extrapolation and attention scores, which leads us to base HRSAM on Swin attention. We then introduce the Flexible Local Attention (FLA) framework, using CUDA-optimized Efficient Memory Attention to accelerate HRSAM. Within FLA, we implement Flash Swin attention, achieving over a 35% speedup compared to traditional Swin attention, and propose a KV-only padding mechanism to enhance extrapolation. We also develop the Cycle-scan module that uses State Space models to efficiently expand HRSAM's receptive field. We further develop the HRSAM++ within FLA by adding an anchor map, providing multi-scale data augmentation for the extrapolation and a larger receptive field at slight computational cost. Experiments show that, under standard training, HRSAMs surpass the previous SOTA with only 38% of the latency. With SAM-distillation, the extrapolation enables HRSAMs to outperform the teacher model at lower latency. Further finetuning achieves performance significantly exceeding the previous SOTA.
University of Toronto（多伦多大学）；Vector Institute（向量研究所）；NVIDIA（英伟达）
Manually labeling video datasets for segmentation tasks is extremely time consuming. In this paper, we introduce ScribbleBox, a novel interactive framework for annotating object instances with masks in videos. In particular, we split annotation into two steps: annotating objects with tracked boxes, and labeling masks inside these tracks. We introduce automation and interaction in both steps. Box tracks are annotated efficiently by approximating the trajectory using a parametric curve with a small number of control points which the annotator can interactively correct. Our approach tolerates a m…
Shanghai Jiao Tong University（上海交通大学）；East China Normal University（华东师范大学）；Tongji University（同济大学）
Interactive segmentation has recently been explored to effectively and efficiently harvest high-quality segmentation masks by iteratively incorporating user hints. While iterative in nature, most existing interactive segmentation methods tend to ignore the dynamics of successive interactions and take each interaction independently. We here propose to model iterative interactive image segmentation with a Markov decision process (MDP) and solve it with reinforcement learning (RL) where each voxel is treated as an agent. Considering the large exploration space for voxel-wise prediction and the de…
Université de Toulouse（图卢兹大学）；UPS（巴黎第十一大学（注：此处UPS为Université Paris-Sud的常见缩写，若为图卢兹相关分支需结合语境，此处取通用常见译法））；IRIT（图卢兹计算机科学研究所）；ENFA（法国国立民航大学（注：ENFA全称为École Nationale de l'Aviation Civile，常见译法为法国国立民航大学））
This paper adresses the problem of interactive multiclass segmentation. We propose a fast and efficient new interactive segmentation method called Superpixel Classification-based Interactive Segmentation (SCIS). From a few strokes drawn by a human user over an image, this method extracts relevant semantic objects. To get a fast calculation and an accurate segmentation, SCIS uses superpixel over-segmentation and support vector machine classification. In this paper, we demonstrate that SCIS significantly outperfoms competing algorithms by evaluating its performances on the reference benchmarks o…
Structured Click Control in Transformer-based Interactive Segmentation
Shenzhen Institute of Artificial Intelligence and Robotics for Society, The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳）深圳市人工智能与机器人研究院）；University of Science and Technology of China（中国科学技术大学）；Maxvision Technology Corp.（视辰科技有限公司）
University of Campinas（坎皮纳斯大学）；Université Gustave Eiffel（古斯塔夫·埃菲尔大学）
Despite the progress of interactive image segmentation methods, high-quality pixel-level annotation is still time-consuming and laborious - a bottleneck for several deep learning applications. We take a step back to propose interactive and simultaneous segment annotation from multiple images guided by feature space projection. This strategy is in stark contrast to existing interactive segmentation methodologies, which perform annotation in the image domain. We show that feature space annotation achieves competitive results with state-of-the-art methods in foreground segmentation datasets: iCoS…
We address interactive full image annotation, where the goal is to accurately segment all object and stuff regions in an image. We propose an interactive, scribble-based annotation framework which operates on the whole image to produce segmentations for all regions. This enables sharing scribble corrections across regions, and allows the annotator to focus on the largest errors made by the machine across the whole image. To realize this, we adapt Mask-RCNN into a fast interactive segmentation framework and introduce an instance-aware loss measured at the pixel-level in the full image canvas, w…
Manually annotating object segmentation masks is very time consuming. Interactive object segmentation methods offer a more efficient alternative where a human annotator and a machine segmentation model collaborate. In this paper we make several contributions to interactive segmentation: (1) we systematically explore in simulation the design space of deep interactive segmentation models and report new insights and caveats; (2) we execute a large-scale annotation campaign with real human annotators, producing masks for 2.5M instances on the OpenImages dataset. We plan to release this data public…
We address interactive panoptic annotation, where one segment all object and stuff regions in an image. We investigate two graph-based segmentation algorithms that both enforce connectivity of each region, with a notable class-aware Integer Linear Programming (ILP) formulation that ensures global optimum. Both algorithms can take RGB, or utilize the feature maps from any DCNN, whether trained on the target dataset or not, as input. We then propose an interactive, scribble-based annotation framework.
Recent works on click-based interactive segmentation have demonstrated state-of-the-art results by using various inference-time optimization schemes. These methods are considerably more computationally expensive compared to feedforward approaches, as they require performing backward passes through a network during inference and are hard to deploy on mobile frameworks that usually support only forward passes. In this paper, we extensively evaluate various design choices for interactive segmentation and discover that new state-of-the-art results can be obtained without any additional optimizatio…
In this paper we present our system for human-in-the-loop video object segmentation. The backbone of our system is a method for one-shot video object segmentation. While fast, this method requires an accurate pixel-level segmentation of one (or several) frames as input. As manually annotating such a segmentation is impractical, we propose a deep interactive image segmentation method, that can accurately segment objects with only a handful of clicks. On the GrabCut dataset, our method obtains 90% IOU with just 3.8 clicks on average, setting the new state of the art. Furthermore, as our method i…
The interactive image segmentation algorithm can provide an intelligent ways to understand the intention of user input. Many interactive methods have the problem of that ask for large number of user input. To efficient produce intuitive segmentation under limited user input is important for industrial application. In this paper, we reveal a positive feedback system on image segmentation to show the pixels of self-learning. Two approaches, iterative random walks and boundary random walks, are proposed for segmentation potential, which is the key step in feedback system. Experiment results on im…
Deep learning requires large amounts of training data to be effective. For the task of object segmentation, manually labeling data is very expensive, and hence interactive methods are needed. Following recent approaches, we develop an interactive object segmentation system which uses user input in the form of clicks as the input to a convolutional network. While previous methods use heuristic click sampling strategies to emulate user clicks during training, we propose a new iterative training strategy. During training, we iteratively add clicks based on the errors of the currently predicted se…
Interactive segmentation has recently attracted attention for specialized tasks where expert input is required to further enhance the segmentation performance. In this work, we propose a novel interactive segmentation framework, where user clicks are dynamically adapted in size based on the current segmentation mask. The clicked regions form a weight map and are fed to a deep neural network as a novel weighted loss function. To evaluate our loss function, an interactive U-Net (IU-Net) model which applies both foreground and background user clicks as the main method of interaction is employed. …
Deep learning-based interactive segmentation in remote sensing
National Center for Ecological Analysis and Synthesis, University of California, Santa Barbara（加州大学圣塔芭芭拉分校国家生态分析与综合中心）；University of Idaho（爱达荷大学）；Fujian Agriculture and Forestry University（福建农林大学）；Bren School of Environmental Science and Management, University of California, Santa Barbara（加州大学圣塔芭芭拉分校布伦环境科学与管理学院）
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.
SpinalSAM-R1: A Vision-Language Multimodal Interactive System for Spine CT Segmentation
College of Artificial Intelligence, Nanjing University of Aeronautics and Astronautics（人工智能学院，南京航空航天大学）；Department of Orthopedics, Qilu Hospital, Shandong University（骨科部，齐鲁医院，山东大学）；Key Laboratory of Qingdao in Medicine and Engineering（医学与工程青岛重点实验室）
Image segmentation is a fundamental problem in computational vision and medical imaging. Designing a generic, automated method that works for various objects and imaging modalities is a formidable task. Instead of proposing a new specific segmentation algorithm, we present a general design principle on how to integrate user interactions from the perspective of feedback control theory. Impulsive control and Lyapunov stability analysis are employed to design and analyze an interactive segmentation system. Then stabilization conditions are derived to guide algorithm design. Finally, the effective…
Korea University（高丽大学）；Chungnam National University（忠南大学）
We propose a novel guided interactive segmentation (GIS) algorithm for video objects to improve the segmentation accuracy and reduce the interaction time. First, we design the reliability-based attention module to analyze the reliability of multiple annotated frames. Second, we develop the intersection-aware propagation module to propagate segmentation results to neighboring frames. Third, we introduce the GIS mechanism for a user to select unsatisfactory frames quickly with less effort. Experimental results demonstrate that the proposed algorithm provides more accurate segmentation results at…
Institute of Computer Science II（第二计算机科学研究所）；University of Bonn（波恩大学）；School of Computing（计算学院）；National University of Singapore（新加坡国立大学）
In interactive instance segmentation, users give feedback to iteratively refine segmentation masks. The user-provided clicks are transformed into guidance maps which provide the network with necessary cues on the whereabouts of the object of interest. Guidance maps used in current systems are purely distance-based and are either too localized or non-informative. We propose a novel transformation of user clicks to generate scale-aware guidance maps that leverage the hierarchical structural information present in an image. Using our guidance maps, even the most basic FCNs are able to outperform …
Pretrained, Curriculum-Tuned, and Ensembled: A Tracer-Aware Interactive Segmentation Pipeline for AutoPET V
The Netherlands Cancer Institute（荷兰癌症研究所）；Radboud University Medical Centre（拉德堡德大学医学中心）；Macao Polytechnic University（澳门理工大学）；Amsterdam University Medical Center（阿姆斯特丹大学医学中心）
Common users have changed from mere consumers to active producers of multimedia data content. Video editing plays an important role in this scenario, calling for simple segmentation tools that can handle fast-moving and deformable video objects with possible occlusions, color similarities with the background, among other challenges. We present an interactive video segmentation method, named FOMTrace, which addresses the problem in an effective and efficient way. From a user-provided object mask in a first frame, the method performs semi-automatic video segmentation on a spatiotemporal superpix…
Harvard University（哈佛大学）；John A. Paulson School of Engineering and Applied Sciences（约翰·A·保尔森工程与应用科学学院）
We present an interactive approach to train a deep neural network pixel classifier for the segmentation of neuronal structures. An interactive training scheme reduces the extremely tedious manual annotation task that is typically required for deep networks to perform well on image segmentation problems. Our proposed method employs a feedback loop that captures sparse annotations using a graphical user interface, trains a deep neural network based on recent and past annotations, and displays the prediction output to users in almost real-time. Our implementation of the algorithm also allows mult…
University of North Carolina at Chapel Hill（北卡罗来纳大学教堂山分校）；United Imaging Intelligence（联影智能）
The goal of click-based interactive image segmentation is to obtain precise object segmentation masks with limited user interaction, i.e., by a minimal number of user clicks. Existing methods require users to provide all the clicks: by first inspecting the segmentation mask and then providing points on mislabeled regions, iteratively. We ask the question: can our model directly predict where to click, so as to further reduce the user interaction cost? To this end, we propose {\PseudoClick}, a generic framework that enables existing segmentation networks to propose candidate next clicks. These …
Clore: Interactive Pathology Image Segmentation with Click-based Local Refinement
School of Computer Science and Technology, University of Science and Technology of China（中国科学技术大学计算机科学与技术学院）；School of Artificial Intelligence and Data Science, University of Science and Technology of China（中国科学技术大学人工智能与数据科学学院）
In recent years, the rapid development of deep learning has brought great advancements to image and video segmentation methods based on neural networks. However, to unleash the full potential of such models, large numbers of high-quality annotated images are necessary for model training. Currently, many widely used open-source image segmentation software relies heavily on manual annotation which is tedious and time-consuming. In this work, we introduce EISeg, an Efficient Interactive SEGmentation annotation tool that can drastically improve image segmentation annotation efficiency, generating …
Korea University（高丽大学）；Chungnam National University（忠南国立大学）
An interactive video object segmentation algorithm, which takes scribble annotations on query objects as input, is proposed in this paper. We develop a deep neural network, which consists of the annotation network (A-Net) and the transfer network (T-Net). First, given user scribbles on a frame, A-Net yields a segmentation result based on the encoder-decoder architecture. Second, T-Net transfers the segmentation result bidirectionally to the other frames, by employing the global and local transfer modules. The global transfer module conveys the segmentation information in an annotated frame to …
CVIT（计算机视觉与智能系统中心）；Kohli Center on Intelligent Systems (KCIS)（科利智能系统中心）；IIIT Hyderabad（海得拉巴国际信息技术学院）
Radiance Fields (RF) are popular to represent casually-captured scenes for new view synthesis and several applications beyond it. Mixed reality on personal spaces needs understanding and manipulating scenes represented as RFs, with semantic segmentation of objects as an important step. Prior segmentation efforts show promise but don't scale to complex objects with diverse appearance. We present the ISRF method to interactively segment objects with fine structure and appearance. Nearest neighbor feature matching using distilled semantic features identifies high-confidence seed regions. Bilatera…
ETH Zurich（苏黎世联邦理工学院）；Beijing Institute of Technology（北京理工大学）
Despite recent progress of automatic medical image segmentation techniques, fully automatic results usually fail to meet the clinical use and typically require further refinement. In this work, we propose a quality-aware memory network for interactive segmentation of 3D medical images. Provided by user guidance on an arbitrary slice, an interaction network is firstly employed to obtain an initial 2D segmentation. The quality-aware memory network subsequently propagates the initial segmentation estimation bidirectionally over the entire volume. Subsequent refinement based on additional user gui…
University of Electronic Science and Technology of China（电子科技大学）；SenseTime Research（商汤科技研究院）；Shanghai Jiao Tong University（上海交通大学）；University Hospitals Leuven（鲁汶大学医院）；University College London（伦敦大学学院）；King’s College London（伦敦国王学院）
Segmentation of organs or lesions from medical images plays an essential role in many clinical applications such as diagnosis and treatment planning. Though Convolutional Neural Networks (CNN) have achieved the state-of-the-art performance for automatic segmentation, they are often limited by the lack of clinically acceptable accuracy and robustness in complex cases. Therefore, interactive segmentation is a practical alternative to these methods. However, traditional interactive segmentation methods require a large amount of user interactions, and recently proposed CNN-based interactive segmen…
Farsee2 Technology（Farsee2科技）；Wuhan University（武汉大学）；Huazhong University of Science and Technology（华中科技大学）；University of South Carolina（南卡罗来纳大学）
Binary image segmentation plays an important role in computer vision and has been widely used in many applications such as image and video editing, object extraction, and photo composition. In this paper, we propose a novel interactive binary image segmentation method based on the Markov Random Field (MRF) framework and the fast bilateral solver (FBS) technique. Specifically, we employ the geodesic distance component to build the unary term. To ensure both computation efficiency and effective responsiveness for interactive segmentation, superpixels are used in computing geodesic distances inst…
Deep learning techniques have successfully been employed in numerous computer vision tasks including image segmentation. The techniques have also been applied to medical image segmentation, one of the most critical tasks in computer-aided diagnosis. Compared with natural images, the medical image is a gray-scale image with low-contrast (even with some invisible parts). Because some organs have similar intensity and texture with neighboring organs, there is usually a need to refine automatic segmentation results. In this paper, we propose an interactive deep refinement framework to improve the …
Interactive segmentation enables users to extract masks by providing simple annotations to indicate the target, such as boxes, clicks, or scribbles. Among these interaction formats, scribbles are the most flexible as they can be of arbitrary shapes and sizes. This enables scribbles to provide more indications of the target object. However, previous works mainly focus on click-based configuration, and the scribble-based setting is rarely explored. In this work, we attempt to formulate a standard protocol for scribble-based interactive segmentation. Basically, we design diversified strategies to…
Deep neural networks have become a mainstream approach to interactive segmentation. As we show in our experiments, while for some images a trained network provides accurate segmentation result with just a few clicks, for some unknown objects it cannot achieve satisfactory result even with a large amount of user input. Recently proposed backpropagating refinement (BRS) scheme introduces an optimization problem for interactive segmentation that results in significantly better performance for the hard cases. At the same time, BRS requires running forward and backward pass through a deep network s…
SLIP: Segmentation with Low-latency Interactive Prompting for 3D Medical Images
IRCAD France（法国国际消化道疾病研究中心）；Université de Strasbourg, CNRS, ICube（斯特拉斯堡大学、法国国家科学研究中心、ICube实验室）；IRCCS Humanitas Research Hospital（圣心研究医院）；Humanitas University（圣心大学）；Fondazione Policlinico Universitario A. Gemelli, Istituto di Ricovero e Cura a Carattere Scientifico (IRCCS)（圣心综合大学医院）
CellPilot: A unified approach to automatic and interactive segmentation in histopathology
School of Computation and Information Technology, Technical University of Munich（慕尼黑工业大学计算与信息技术学院）；Helmholtz Zentrum München - German Research Center for Environmental Health（亥姆霍兹慕尼黑中心——德国环境健康研究中心）；School of Biomedical Engineering and Imaging Sciences, King’s College London（伦敦国王学院生物医学工程与影像科学学院）
University of South Carolina（南卡罗来纳大学）；Zhejiang University（浙江大学）；Utah State University（犹他州立大学）
One popular approach to interactively segment the foreground object of interest from an image is to annotate a bounding box that covers the foreground object. Then, a binary labeling is performed to achieve a refined segmentation. One major issue of the existing algorithms for such interactive image segmentation is their preference of an input bounding box that tightly encloses the foreground object. This increases the annotation burden, and prevents these algorithms from utilizing automatically detected bounding boxes. In this paper, we develop a new LooseCut algorithm that can handle cases w…
Interactive image segmentation aims at segmenting a target region through a way of human-computer interaction. Recent works based on deep learning have achieved excellent performance, while most of them focus on improving the accuracy of the training set and ignore potential improvement on the test set. In the inference phase, they tend to have a good performance on similar domains to the training set, and lack adaptability to domain shift, so they require more user efforts to obtain satisfactory results. In this work, we propose RAIS, a robust and accurate architecture for interactive segment…
Institute of Computer Science II（计算机科学第二研究所）；University of Bonn, Germany（德国波恩大学）；School of Computing（计算机学院）；National University of Singapore（新加坡国立大学）
In current interactive instance segmentation works, the user is granted a free hand when providing clicks to segment an object; clicks are allowed on background pixels and other object instances far from the target object. This form of interaction is highly inconsistent with the end goal of efficiently isolating objects of interest. In our work, we propose a clicking scheme wherein user interactions are restricted to the proximity of the object. In addition, we propose a novel transformation of the user-provided clicks to generate a weak localization prior on the object which is consistent wit…
Shanghai Jiao Tong University（上海交通大学）；Shanghai AI Laboratory（上海人工智能实验室）
The goal of this paper is to interactively refine the automatic segmentation on challenging structures that fall behind human performance, either due to the scarcity of available annotations or the difficulty nature of the problem itself, for example, on segmenting cancer or small organs. Specifically, we propose a novel Transformer-based architecture for Interactive Segmentation (TIS), that treats the refinement task as a procedure for grouping pixels with similar features to those clicks given by the end users. Our proposed architecture is composed of Transformer Decoder variants, which natu…
