To date, instance segmentation is dominated by twostage methods, as pioneered by Mask R-CNN. In contrast, one-stage alternatives cannot compete with Mask R-CNN in mask AP, mainly due to the difficulty of compactly representing masks, making the design of one-stage methods very challenging. In this work, we propose a simple singleshot instance segmentation framework, termed mask encoding based instance segmentation (MEInst). Instead of predicting the two-dimensional mask directly, MEInst distills it into a compact and fixed-dimensional representation vector, which allows the instance segmentation task to be incorporated into one-stage bounding-box detectors and results in a simple yet efficient instance segmentation framework. The proposed one-stage MEInst achieves 36.4% in mask AP with single-model (ResNeXt-101-FPN backbone) and single-scale testing on the MS-COCO benchmark. We show that the much simpler and flexible one-stage instance segmentation method, can also achieve competitive performance. This framework can be easily adapted for other instance-level recognition tasks. Code is available at: https://git.io/AdelaiDet
MonolithAI；Middle East Technical University（中东技术大学）；Hacettepe University（哈切特佩大学）
Just like other few-shot learning problems, few-shot segmentation aims to minimize the need for manual annotation, which is particularly costly in segmentation tasks. Even though the few-shot setting reduces this cost for novel test classes, there is still a need to annotate the training data. To alleviate this need, we propose a self-supervised training approach for learning few-shot segmentation models. We first use unsupervised saliency estimation to obtain pseudo-masks on images. We then train a simple prototype based model over different splits of pseudo masks and augmentations of images.…
MaskDiff: Modeling Mask Distribution with Diffusion Probabilistic Model for Few-Shot Instance Segmentation
University of Science, VNU-HCM（胡志明市国家大学科学大学）；Vietnam National University, Ho Chi Minh City（胡志明市国家大学）；Stony Brook University（石溪大学）；University of Dayton（代顿大学）；Monash University（莫纳什大学）；University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
Rutgers University（罗格斯大学）；The College of New Jersey（新泽西学院）；Mohamed Bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）
We study few-shot semantic segmentation that aims to segment a target object from a query image when provided with a few annotated support images of the target class. Several recent methods resort to a feature masking (FM) technique to discard irrelevant feature activations which eventually facilitates the reliable prediction of segmentation mask. A fundamental limitation of FM is the inability to preserve the fine-grained spatial details that affect the accuracy of segmentation mask, especially for small target objects. In this paper, we develop a simple, effective, and efficient approach to …
University of Southern California（南加州大学）；MEGVII Technology（旷视科技）
Emerging interests have been brought to recognize previously unseen objects given very few training examples, known as few-shot object detection (FSOD). Recent researches demonstrate that good feature embedding is the key to reach favorable few-shot learning performance. We observe object proposals with different Intersection-of-Union (IoU) scores are analogous to the intra-image augmentation used in contrastive approaches. And we exploit this analogy and incorporate supervised contrastive learning to achieve more robust objects representations in FSOD. We present Few-Shot object detection via…
HERE North America LLC（HERE北美有限责任公司）；University of South Carolina（南卡罗来纳大学）；Tianjin University（天津大学）
Region-based Convolutional Neural Networks (R-CNNs) have achieved great success in the field of object detection. The existing R-CNNs usually divide a Region-of-Interest (ROI) into grids, and then localize objects by utilizing the spatial information reflected by the relative position of each grid in the ROI. In this paper, we propose a novel feature-encoding approach, where spatial information is represented through the spatial distributions of visual patterns. In particular, we design a Mask Weight Network (MWN) to learn a set of masks and then apply channel-wise masking operations to ROI fe…
Unlike conventional zero-shot classification, zero-shot semantic segmentation predicts a class label at the pixel level instead of the image level. When solving zero-shot semantic segmentation problems, the need for pixel-level prediction with surrounding context motivates us to incorporate spatial information using positional encoding. We improve standard positional encoding by introducing the concept of Relative Positional Encoding, which integrates spatial information at the feature level and can handle arbitrary image sizes. Furthermore, while self-training is widely used in zero-shot sema…
College of Information Science & Technology, Beijing University of Chemical Technology（北京化工大学信息科学与技术学院）
Object detection and instance segmentation in remote sensing images is a fundamental and challenging task, due to the complexity of scenes and targets. The latest methods tried to take into account both the efficiency and the accuracy of instance segmentation. In order to improve both of them, in this paper, we propose a single-shot convolutional neural network structure, which is conceptually simple and straightforward, and meanwhile makes up for the problem of low accuracy of single-shot networks. Our method, termed with SSS-Net, detects targets based on the location of the object's center a…
We tackle the problem of one-shot instance segmentation: Given an example image of a novel, previously unknown object category, find and segment all objects of this category within a complex scene. To address this challenging new task, we propose Siamese Mask R-CNN. It extends Mask R-CNN by a Siamese backbone encoding both reference image and scene, allowing it to target detection and segmentation towards the reference category. We demonstrate empirical results on MS Coco highlighting challenges of the one-shot setting: while transferring knowledge about instance segmentation to novel object c…
PFENet++: Boosting Few-shot Semantic Segmentation with the Noise-filtered Context-aware Prior Mask
Chongqing University of Technology（重庆理工大学）；Chongqing University（重庆大学）；The Chinese University of Hong Kong（香港中文大学）；SmartMore（智谱AI）；University of Macau（澳门大学）
Research into Few-shot Semantic Segmentation (FSS) has attracted great attention, with the goal to segment target objects in a query image given only a few annotated support images of the target class. A key to this challenging task is to fully utilize the information in the support images by exploiting fine-grained correlations between the query and support images. However, most existing approaches either compressed the support information into a few class-wise prototypes, or used partial support information (e.g., only foreground) at the pixel level, causing non-negligible information loss. …
Few-shot semantic segmentation aims to recognize novel classes with only very few labelled data. This challenging task requires mining of the relevant relationships between the query image and the support images. Previous works have typically regarded it as a pixel-wise classification problem. Therefore, various models have been designed to explore the correlation of pixels between the query image and the support images. However, they focus only on pixel-wise correspondence and ignore the overall correlation of objects. In this paper, we introduce a mask-based classification method for address…
RUFNet: Query-Guided Support Mask Refinement and Uncertainty Fusion based on Hybrid Mamba for Few-Shot Brain Tumor Segmentation
Department of Language Science and Technology, The Hong Kong Polytechnic University（香港理工大学语言科学与技术系）；School of Artificial Intelligence, Chongqing University of Technology（重庆理工大学人工智能学院）；Affiliated Lianyungang Hospital of Xuzhou Medical University（徐州医科大学附属连云港医院）；College of Mechatronics and Control Engineering, Shenzhen University（深圳大学机电与控制工程学院）
Semantic segmentation is an important and prevalent task, but severely suffers from the high cost of pixel-level annotations when extending to more classes in wider applications. To this end, we focus on the problem named weak-shot semantic segmentation, where the novel classes are learnt from cheaper image-level labels with the support of base classes having off-the-shelf pixel-level labels. To tackle this problem, we propose SimFormer, which performs dual similarity transfer upon MaskFormer. Specifically, MaskFormer disentangles the semantic segmentation task into two sub-tasks: proposal cla…
Bridge the Points: Graph-based Few-shot Segment Anything Semantically
School of Computer Science, Beijing Institute of Technology（北京理工大学计算机学院）；School of Computer Science, University of Birmingham（伯明翰大学计算机学院）；Institute of Information Science, Beijing Jiaotong University（北京交通大学信息科学研究所）
Group-On: Boosting One-Shot Segmentation with Supportive Query
Zhejiang University（浙江大学）；University of Notre Dame（诺丁汉大学）；Zhejiang Key Laboratory of Medical Imaging Artificial Intelligence（浙江省医学影像人工智能重点实验室）；HKUST(Guangzhou)（香港科技大学（广州））
XJTLU（西交利物浦大学）；University of Liverpool（利物浦大学）；Dinnar Automation Technology（迪纳自动化技术公司）
Few-shot segmentation has been attracting a lot of attention due to its effectiveness to segment unseen object classes with a few annotated samples. Most existing approaches use masked Global Average Pooling (GAP) to encode an annotated support image to a feature vector to facilitate query image segmentation. However, this pipeline unavoidably loses some discriminative information due to the average operation. In this paper, we propose a simple but effective self-guided learning approach, where the lost critical information is mined. Specifically, through making an initial prediction for the a…
Judging from Support-set: A New Way to Utilize Few-Shot Segmentation for Segmentation Refinement Process
Brookhaven National Laboratory（布鲁赫斯国家实验室）；Roblox（Roblox公司）；Rutgers University（罗格斯大学）；Mohamed Bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）
Sun Yat-sen University（中山大学）；DarkMatter AI Research（暗物质人工智能研究院）
Resembling the rapid learning capability of human, few-shot learning empowers vision systems to understand new concepts by training with few samples. Leading approaches derived from meta-learning on images with a single visual object. Obfuscated by a complex background and multiple objects in one image, they are hard to promote the research of few-shot object detection/segmentation. In this work, we present a flexible and general methodology to achieve these tasks. Our work extends Faster /Mask R-CNN by proposing meta-learning over RoI (Region-of-Interest) features instead of a full image feat…
Video object segmentation (VOS) describes the task of segmenting a set of objects in each frame of a video. In the semi-supervised setting, the first mask of each object is provided at test time. Following the one-shot principle, fine-tuning VOS methods train a segmentation model separately on each given object mask. However, recently the VOS community has deemed such a test time optimization and its impact on the test runtime as unfeasible. To mitigate the inefficiencies of previous fine-tuning approaches, we present efficient One-Shot Video Object Segmentation (e-OSVOS). In contrast to most …
One of the key issues in facial expression recognition in the wild (FER-W) is that curating large-scale labeled facial images is challenging due to the inherent complexity and ambiguity of facial images. Therefore, in this paper, we propose a self-supervised simple facial landmark encoding (SimFLE) method that can learn effective encoding of facial landmarks, which are important features for improving the performance of FER-W, without expensive labels. Specifically, we introduce novel FaceMAE module for this purpose. FaceMAE reconstructs masked facial images with elaborately designed semantic …
Recently two-stage detectors have surged ahead of single-shot detectors in the accuracy-vs-speed trade-off. Nevertheless single-shot detectors are immensely popular in embedded vision applications. This paper brings single-shot detectors up to the same level as current two-stage techniques. We do this by improving training for the state-of-the-art single-shot detector, RetinaNet, in three ways: integrating instance mask prediction for the first time, making the loss function adaptive and more stable, and including additional hard examples in training. We call the resulting augmented network Re…
Although having achieved great success in medical image segmentation, deep convolutional neural networks usually require a large dataset with manual annotations for training and are difficult to generalize to unseen classes. Few-shot learning has the potential to address these challenges by learning new classes from only a few labeled examples. In this work, we propose a new framework for few-shot medical image segmentation based on prototypical networks. Our innovation lies in the design of two key modules: 1) a context relation encoder (CRE) that uses correlation to capture local relation fe…
Recently, removing objects from videos and filling in the erased regions using deep video inpainting (VI) algorithms has attracted considerable attention. Usually, a video sequence and object segmentation masks for all frames are required as the input for this task. However, in real-world applications, providing segmentation masks for all frames is quite difficult and inefficient. Therefore, we deal with VI in a one-shot manner, which only takes the initial frame's object mask as its input. Although we can achieve that using naive combinations of video object segmentation (VOS) and VI methods,…
Beijing Jiaotong University（北京交通大学）；University of Technology Sydney（悉尼科技大学）；Picsart AI Research (PAIR)（Picsart人工智能研究院（PAIR））
In this paper, we aim to tackle the challenging few-shot segmentation task from a new perspective. Typical methods follow the paradigm to firstly learn prototypical features from support images and then match query features in pixel-level to obtain segmentation results. However, to obtain satisfactory segments, such a paradigm needs to couple the learning of the matching operations with heavy segmentation modules, limiting the flexibility of design and increasing the learning complexity. To alleviate this issue, we propose Mask Matching Transformer (MM-Former), a new paradigm for the few-shot …
University of Electronic Science and Technology of China（电子科技大学）；University of Georgia（佐治亚大学）；University of Texas at Arlington（德克萨斯大学阿灵顿分校）；Northwestern Polytechnical University（西北工业大学）
Learning with little data is challenging but often inevitable in various application scenarios where the labeled data is limited and costly. Recently, few-shot learning (FSL) gained increasing attention because of its generalizability of prior knowledge to new tasks that contain only a few samples. However, for data-intensive models such as vision transformer (ViT), current fine-tuning based FSL approaches are inefficient in knowledge generalization and thus degenerate the downstream task performances. In this paper, we propose a novel mask-guided vision transformer (MG-ViT) to achieve an effe…
Bosch Center for Artificial Intelligence（博世人工智能中心）；University of Tübingen（图宾根大学）；University of Bonn（波恩大学）
Joint synthesis of images and segmentation masks with generative adversarial networks (GANs) is promising to reduce the effort needed for collecting image data with pixel-wise annotations. However, to learn high-fidelity image-mask synthesis, existing GAN approaches first need a pre-training phase requiring large amounts of image data, which limits their utilization in restricted image domains. In this work, we take a step to reduce this limitation, introducing the task of one-shot image-mask synthesis. We aim to generate diverse images and their segmentation masks given only a single labelled…
Key Laboratory of Multimedia Trusted Perception and Efficient Computing（多媒体可信感知与高效计算重点实验室）；Ministry of Education of China（中华人民共和国教育部）；Xiamen University（厦门大学）；VIVO
Zero-Shot Learning (ZSL) is typically achieved by resorting to a class semantic embedding space to transfer the knowledge from the seen classes to unseen ones. Capturing the common semantic characteristics between the visual modality and the class semantic modality (e.g., attributes or word vector) is a key to the success of ZSL. In this paper, we propose a novel encoder-decoder approach, namely Latent Space Encoding (LSE), to connect the semantic relations of different modalities. Instead of requiring a projection function to transfer information across different modalities like most previous…
Providing quality-constant streams can simultaneously guarantee user experience and prevent wasting bit-rate. In this paper, we propose a novel deep learning based two-pass encoder parameter prediction framework to decide rate factor (RF), with which encoder can output streams with constant quality. For each one-shot segment in a video, the proposed method firstly extracts spatial, temporal and pre-coding features by an ultra fast pre-process. Based on these features, a RF parameter is predicted by a deep neural network. Video encoder uses the RF to compress segment as the first encoding pass.…
Global Prompt Refinement with Non-Interfering Attention Masking for One-Shot Federated Learning
School of Software, Shandong University（山东大学软件学院）；AIM Lab, Faculty of Engineering, Monash University（莫纳什大学工程学院AIM实验室）；College of Computing and Data Science, Nanyang Technological University（南洋理工大学计算与数据科学学院）；Department of Electrical and Computer Engineering, University of British Columbia（不列颠哥伦比亚大学电气与计算机工程系）；Vector Institute, Canada（加拿大向量研究所）
University of Tsukuba（筑波大学）；Universi（Universi（注：原文中“Univeristy”应为“University”的拼写错误，正确机构为筑波大学））
This paper tackles a challenging problem of generating photorealistic images from semantic layouts in few-shot scenarios where annotated training pairs are hardly available but pixel-wise annotation is quite costly. We present a training strategy that performs pseudo labeling of semantic masks using the StyleGAN prior. Our key idea is to construct a simple mapping between the StyleGAN feature and each semantic class from a few examples of semantic masks. With such mappings, we can generate an unlimited number of pseudo semantic masks from random noise to train an encoder for controlling a pre-…
Harokopio University of Athens, Athens, Greece（雅典哈尔科波利欧大学）；National and Kapodistrian University of Athens, Athens, Greece（雅典国家与卡波迪斯蒂亚纳大学）；CentraleSupelec, University Paris Saclay, Paris, France（巴黎萨克雷中央苏普尔大学）；Archimedes, Athena Research Center, Athens, Greece（阿提卡研究所以及阿奇米德中心）
