We present the DeepScores dataset with the goal of advancing the state-of-the-art in small objects recognition, and by placing the question of object recognition in the context of scene understanding. DeepScores contains high quality images of musical scores, partitioned into 300,000 sheets of written music that contain symbols of different shapes and sizes. With close to a hundred millions of small objects, this makes our dataset not only unique, but also the largest public dataset. DeepScores comes with ground truth for object classification, detection and semantic segmentation. DeepScores thus poses a relevant challenge for computer vision in general, beyond the scope of optical music recognition (OMR) research. We present a detailed statistical analysis of the dataset, comparing it with other computer vision datasets like Caltech101/256, PASCAL VOC, SUN, SVHN, ImageNet, MS-COCO, smaller computer vision datasets, as well as with other OMR datasets. Finally, we provide baseline performances for object classification and give pointers to future research based on this dataset.
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…
University of California, Santa Barbara（加利福尼亚大学圣巴巴拉分校）；Las Cumbres Observatory（拉斯坎布雷斯天文台）
We introduce an interactive image segmentation and visualization framework for identifying, inspecting, and editing tiny objects (just a few pixels wide) in large multi-megapixel high-dynamic-range (HDR) images. Detecting cosmic rays (CRs) in astronomical observations is a cumbersome workflow that requires multiple tools, so we developed an interactive toolkit that unifies model inference, HDR image visualization, segmentation mask inspection and editing into a single graphical user interface. The feature set, initially designed for astronomical data, makes this work a useful research-supporti…
Systems Laboratory, Universit\' e Laval Quebec City (QC), Canada
Current object segmentation algorithms are based on the hypothesis that one has access to a very large amount of data. In this paper, we aim to segment objects using only tiny datasets. To this extent, we propose a new automatic part-based object segmentation algorithm for non-deformable and semi-deformable objects in natural backgrounds. We have developed a novel shape descriptor which models the local boundaries of an object's part. This shape descriptor is used in a bag-of-words approach for object detection. Once the detection process is performed, we use the background and foreground like…
Multi-scale learning frameworks have been regarded as a capable class of models to boost semantic segmentation. The problem nevertheless is not trivial especially for the real-world deployments, which often demand high efficiency in inference latency. In this paper, we thoroughly analyze the design of convolutional blocks (the type of convolutions and the number of channels in convolutions), and the ways of interactions across multiple scales, all from lightweight standpoint for semantic segmentation. With such in-depth comparisons, we conclude three principles, and accordingly devise Lightwei…
Tiny and Efficient Model for the Edge Detection Generalization
National University of Chimborazo（钦博拉索国立大学）；China University of Petroleum (East China)（中国石油大学（华东））；INRIA Paris（法国国家信息与自动化研究所巴黎分部）；ESPOL Polytechnic University（ESPOL理工大学）；Computer Vision Center（计算机视觉中心）
In this research, we propose a tiny image segmentation model, L^3U-net, that works on low-resource edge devices in real-time. We introduce a data folding technique that reduces inference latency by leveraging the parallel convolutional layer processing capability of the CNN accelerators. We also deploy the proposed model to such a device, MAX78000, and the results show that L^3U-net achieves more than 90% accuracy over two different segmentation datasets with 10 fps.
Inception Institute of Artificial Intelligence, UAE（阿联酋Inception人工智能研究所）；Wuhan University, China（中国武汉大学）；Huazhong University of Science and Technology, China（中国华中科技大学）
Existing Earth Vision datasets are either suitable for semantic segmentation or object detection. In this work, we introduce the first benchmark dataset for instance segmentation in aerial imagery that combines instance-level object detection and pixel-level segmentation tasks. In comparison to instance segmentation in natural scenes, aerial images present unique challenges e.g., a huge number of instances per image, large object-scale variations and abundant tiny objects. Our large-scale and densely annotated Instance Segmentation in Aerial Images Dataset (iSAID) comes with 655,451 object ins…
Cornell University（康奈尔大学）；Weill Cornell Medical College（威尔康奈尔医学院）；University of Pennsylvania（宾夕法尼亚大学）
We introduce Neural Representation of Distribution (NeRD) technique, a module for convolutional neural networks (CNNs) that can estimate the feature distribution by optimizing an underlying function mapping image coordinates to the feature distribution. Using NeRD, we propose an end-to-end deep learning model for medical image segmentation that can compensate the negative impact of feature distribution shifting issue caused by commonly used network operations such as padding and pooling. An implicit function is used to represent the parameter space of the feature distribution by querying the i…
Active learning aims to address the paucity of labeled data by finding the most informative samples. However, when applying to semantic segmentation, existing methods ignore the segmentation difficulty of different semantic areas, which leads to poor performance on those hard semantic areas such as tiny or slender objects. To deal with this problem, we propose a semantic Difficulty-awarE Active Learning (DEAL) network composed of two branches: the common segmentation branch and the semantic difficulty branch. For the latter branch, with the supervision of segmentation error between the segment…
北京天地智绘科技有限公司；China Institute of Water Resources and Hydropower Research (IWHR)（中国水利水电科学研究院）；北京治元景行科技有限公司
Until now, all single level segmentation algorithms except CNN-based ones lead to over segmentation. And CNN-based segmentation algorithms have their own problems. To avoid over segmentation, multiple thresholds of criteria are adopted in region merging process to produce hierarchical segmentation results. However, there still has extreme over segmentation in the low level of the hierarchy, and outstanding tiny objects are merged to their large adjacencies in the high level of the hierarchy. This paper proposes a region-merging-based image segmentation method that we call it Dam Burst. As a si…
Seoul National University（首尔大学）；NAVER AI Lab（NAVER AI实验室）；NAVER Clova
This paper introduces a solid state-of-the-art baseline for a class-incremental semantic segmentation (CISS) problem. While the recent CISS algorithms utilize variants of the knowledge distillation (KD) technique to tackle the problem, they failed to fully address the critical challenges in CISS causing the catastrophic forgetting; the semantic drift of the background class and the multi-label prediction issue. To better address these challenges, we propose a new method, dubbed SSUL-M (Semantic Segmentation with Unknown Label with Memory), by carefully combining techniques tailored for semanti…
Masked image modeling (MIM) performs strongly in pre-training large vision Transformers (ViTs). However, small models that are critical for real-world applications cannot or only marginally benefit from this pre-training approach. In this paper, we explore distillation techniques to transfer the success of large MIM-based pre-trained models to smaller ones. We systematically study different options in the distillation framework, including distilling targets, losses, input, network regularization, sequential distillation, etc, revealing that: 1) Distilling token relations is more effective than…
The University of Hong Kong（香港大学）；SenseTime Research（商汤科技研究院）；Shanghai AI Laboratory（上海人工智能实验室）
This paper presents a simple MLP-like architecture, CycleMLP, which is a versatile backbone for visual recognition and dense predictions. As compared to modern MLP architectures, e.g., MLP-Mixer, ResMLP, and gMLP, whose architectures are correlated to image size and thus are infeasible in object detection and segmentation, CycleMLP has two advantages compared to modern approaches. (1) It can cope with various image sizes. (2) It achieves linear computational complexity to image size by using local windows. In contrast, previous MLPs have $O(N^2)$ computations due to fully spatial connections. …
Harbin Institute of Technology（哈尔滨工业大学）；Huawei Noah’s Ark Lab（华为诺亚方舟实验室）
Existing open-world universal segmentation approaches usually leverage CLIP and pre-computed proposal masks to treat open-world segmentation tasks as proposal classification. However, 1) these works cannot handle universal segmentation in an end-to-end manner, and 2) the limited scale of panoptic datasets restricts the open-world segmentation ability on things classes. In this paper, we present Vision-Language Omni-Supervised Segmentation (VLOSS). VLOSS starts from a Mask2Former universal segmentation framework with CLIP text encoder. To improve the open-world segmentation ability, we leverage…
Zhejiang University（浙江大学）；Alibaba-Zhejiang University Joint Research Institute of Frontier Technologies（阿里巴巴-浙江大学前沿技术联合研究院）
Box-supervised instance segmentation has recently attracted lots of research efforts while little attention is received in aerial image domain. In contrast to the general object collections, aerial objects have large intra-class variances and inter-class similarity with complex background. Moreover, there are many tiny objects in the high-resolution satellite images. This makes the recent pairwise affinity modeling method inevitably to involve the noisy supervision with the inferior results. To tackle these problems, we propose a novel aerial instance segmentation approach, which drives the ne…
From diagnosing neovascular diseases to detecting white matter lesions, accurate tiny vessel segmentation in fundus images is critical. Promising results for accurate vessel segmentation have been known. However, their effectiveness in segmenting tiny vessels is still limited. In this paper, we study retinal vessel segmentation by incorporating tiny vessel segmentation into our framework for the overall accurate vessel segmentation. To achieve this, we propose a new deep convolutional neural network (CNN) which divides vessel segmentation into two separate objectives. Specifically, we consider…
Indonesia holds the second-highest-ranking country for the highest number of malaria cases in Southeast Asia. A different malaria parasite semantic segmentation technique based on a deep learning approach is an alternative to reduce the limitations of traditional methods. However, the main problem of the semantic segmentation technique is raised since large parasites are dominant, and the tiny parasites are suppressed. In addition, the amount and variance of data are important influences in establishing their models. In this study, we conduct two contributions. First, we collect 559 microscopi…
Huazhong University of Science and Technology（华中科技大学）；Tencent PCG（腾讯平台与内容事业群）；Fudan University（复旦大学）；Zhejiang University（浙江大学）
Although vision transformers (ViTs) have achieved great success in computer vision, the heavy computational cost hampers their applications to dense prediction tasks such as semantic segmentation on mobile devices. In this paper, we present a mobile-friendly architecture named \textbf{To}ken \textbf{P}yramid Vision Trans\textbf{former} (\textbf{TopFormer}). The proposed \textbf{TopFormer} takes Tokens from various scales as input to produce scale-aware semantic features, which are then injected into the corresponding tokens to augment the representation. Experimental results demonstrate that o…
Scientific Computing and Imaging Institute, University of Utah（犹他大学科学计算与成像研究所）
We introduce a novel unsupervised loss function for learning semantic segmentation with deep convolutional neural nets (ConvNet) when densely labeled training images are not available. More specifically, the proposed loss function penalizes the L1-norm of the gradient of the label probability vector image , i.e. total variation, produced by the ConvNet. This can be seen as a regularization term that promotes piecewise smoothness of the label probability vector image produced by the ConvNet during learning. The unsupervised loss function is combined with a supervised loss in a semi-supervised s…
University of North Carolina at Chapel Hill（北卡罗来纳大学教堂山分校）
Click-based interactive image segmentation aims at extracting objects with a limited user clicking. A hierarchical backbone is the de-facto architecture for current methods. Recently, the plain, non-hierarchical Vision Transformer (ViT) has emerged as a competitive backbone for dense prediction tasks. This design allows the original ViT to be a foundation model that can be finetuned for downstream tasks without redesigning a hierarchical backbone for pretraining. Although this design is simple and has been proven effective, it has not yet been explored for interactive image segmentation. To fi…
The University of Hong Kong（香港大学）；SenseTime Research（商汤科技研究院）；Shenzhen Research Institute of Big Data, The Chinese University of Hong Kong, Shenzhen（香港中文大学深圳大数据研究院）
Aggregating multi-level feature representation plays a critical role in achieving robust volumetric medical image segmentation, which is important for the auxiliary diagnosis and treatment. Unlike the recent neural architecture search (NAS) methods that typically searched the optimal operators in each network layer, but missed a good strategy to search for feature aggregations, this paper proposes a novel NAS method for 3D medical image segmentation, named UXNet, which searches both the scale-wise feature aggregation strategies as well as the block-wise operators in the encoder-decoder network…
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…
Nanyang Technological University（南洋理工大学）；National University of Singapore（新加坡国立大学）
While deep models have shown promising performance in medical image segmentation, they heavily rely on a large amount of well-annotated data, which is difficult to access, especially in clinical practice. On the other hand, high-accuracy deep models usually come in large model sizes, limiting their employment in real scenarios. In this work, we propose a novel asymmetric co-teacher framework, ACT-Net, to alleviate the burden on both expensive annotations and computational costs for semi-supervised knowledge distillation. We advance teacher-student learning with a co-teacher network to facilita…
Harmonizing output imbalance for defect segmentation on extremely-imbalanced photovoltaic module cells images
Shenzhen University（深圳大学）；Guangdong Artificial Intelligence and Digital Economy Laboratory (Shenzhen)（广东人工智能与数字经济实验室（深圳））；Shenzhen Institute of Technology（深圳技术学院）
Xi’an Jiaotong-liverpool University（西交利物浦大学）；University of Technology Sydney（悉尼科技大学）；Alibaba-Zhejiang University Joint Institute of Frontier Technologies（阿里巴巴-浙江大学前沿技术联合研究院）
Weakly supervised semantic segmentation is a challenging task as it only takes image-level information as supervision for training but produces pixel-level predictions for testing. To address such a challenging task, most recent state-of-the-art approaches propose to adopt two-step solutions, \emph{i.e. } 1) learn to generate pseudo pixel-level masks, and 2) engage FCNs to train the semantic segmentation networks with the pseudo masks. However, the two-step solutions usually employ many bells and whistles in producing high-quality pseudo masks, making this kind of methods complicated and inele…
Beijing University of Posts and Telecommunications（北京邮电大学）；AI Labs, Didi Chuxing（滴滴出行人工智能实验室）
The performance of face detectors has been largely improved with the development of convolutional neural network. However, it remains challenging for face detectors to detect tiny, occluded or blurry faces. Besides, most face detectors can't locate face's position precisely and can't achieve high Intersection-over-Union (IoU) scores. We assume that problems inside are inadequate use of supervision information and imbalance between semantics and details at all level feature maps in CNN even with Feature Pyramid Networks (FPN). In this paper, we present a novel single-shot face detection network…
Feature reassembly is an essential component in modern CNN-based segmentation approaches, which includes feature downsampling and upsampling operators. Existing operators reassemble multiple features from a small predefined region into one for each target location independently. This may result in loss of spatial information, which could vanish activations caused by tiny lesions particularly when they cluster together. In this paper, we propose a many-to-many reassembly of features (M2MRF). It reassembles features in a dimension-reduced feature space and simultaneously aggregates multiple feat…
East China Normal University（华东师范大学）；Xiamen University（厦门大学）；Shanghai Jiao Tong University（上海交通大学）
Weakly supervised point cloud semantic segmentation methods that require 1\% or fewer labels, hoping to realize almost the same performance as fully supervised approaches, which recently, have attracted extensive research attention. A typical solution in this framework is to use self-training or pseudo labeling to mine the supervision from the point cloud itself, but ignore the critical information from images. In fact, cameras widely exist in LiDAR scenarios and this complementary information seems to be greatly important for 3D applications. In this paper, we propose a novel cross-modality w…
As an essential prerequisite for developing a medical intelligent assistant system, medical image segmentation has received extensive research and concentration from the neural network community. A series of UNet-like networks with encoder-decoder architecture has achieved extraordinary success, in which UNet2+ and UNet3+ redesign skip connections, respectively proposing dense skip connection and full-scale skip connection and dramatically improving compared with UNet in medical image segmentation. However, UNet2+ lacks sufficient information explored from the full scale, which will affect the…
Scale-specific auxiliary multi-task contrastive learning for deep liver vessel segmentation
LaTIM UMR 1101（拉蒂姆UMR 1101机构）；Inserm（法国国家健康与医学研究院）；University of Western Brittany（西布列塔尼大学）；University Hospital of Brest（布雷斯特大学医院）；University Hospital of Poitiers（普瓦捷大学医院）；ICube UMR 7357（ICube UMR 7357机构）；CNRS（法国国家科学研究中心）；IMT Atlantique（大西洋电信学院）
Robustness Analysis on Foundational Segmentation Models
Center for Research in Computer Vision, University of Central Florida（中佛罗里达大学计算机视觉研究中心）；Indian Institute of Technology, Madras（马德拉斯印度理工学院）；University of Southern California（南加州大学）；Microsoft Research（微软研究院）
SimulaMet；UiT The Arctic University of Norway（挪威北极大学）；Oslo Metropolitan University（奥斯陆城市大学）；Institute of Biomedical Engineering, University of Oxford（牛津大学生物医学工程研究所）；Bærum Hospital（贝鲁姆医院）；Augere Medical AS（Augere Medical 公司）；Sahlgrenska University Hospital-Mölndal Hospital（萨尔格伦斯卡大学医院-默恩达尔医院）；Sahlgrenska Academy, University of Gothenburg（哥德堡大学萨尔格伦斯卡学院）
Deep learning in gastrointestinal endoscopy can assist to improve clinical performance and be helpful to assess lesions more accurately. To this extent, semantic segmentation methods that can perform automated real-time delineation of a region-of-interest, e.g., boundary identification of cancer or precancerous lesions, can benefit both diagnosis and interventions. However, accurate and real-time segmentation of endoscopic images is extremely challenging due to its high operator dependence and high-definition image quality. To utilize automated methods in clinical settings, it is crucial to de…
