Learning Panoptic Segmentation from Instance Contours

Instance segmentation and panoptic segmentation is being paid more and more attention in recent years. In comparison with bounding box based object detection and semantic segmentation, instance segmentation can provide more analytical results at pixel level. Given the insight that pixels belonging to one instance have one or more common attributes of current instance, we bring up an one-stage instance segmentation network named Common Attribute Support Network (CASNet), which realizes instance segmentation by predicting and clustering common attributes. CASNet is designed in the manner of fully convolutional and can implement training and inference from end to end. And CASNet manages predicting the instance without overlaps and holes, which problem exists in most of current instance segmentation algorithms. Furthermore, it can be easily extended to panoptic segmentation through minor modifications with little computation overhead. CASNet builds a bridge between semantic and instance segmentation from finding pixel class ID to obtaining class and instance ID by operations on common attribute. Through experiment for instance and panoptic segmentation, CASNet gets mAP 32.8% and PQ 59.0% on Cityscapes validation dataset by joint training, and mAP 36.3% and PQ 66.1% by separated training mode. For panoptic segmentation, CASNet gets state-of-the-art performance on the Cityscapes validation dataset.

In recent years, with the rapid development of deep learning technology and its wide application in the field of computer vision, various image understanding tasks including semantic segmentation and instance segmentation have made great progress, and people's further demand for image understanding has spawned a more comprehensive task image panoptic segmentation. Image panoptic segmentation can be seen as the combination of semantic segmentation and instance segmentation. For uncountable object categories (called stuff), the pixel category is distinguished. For countable object categories (called things), not only the semantic category of the target is recognized, but also each instance is distinguished. This task can provide more comprehensive scene information, and can be widely used in the understanding of various natural scenes. This paper investigate the commonly used panoptic segmentation methods, including the basic shared feature extraction method, the information combination method between semantic segmentation and instance segmentation sub-tasks, and the learnable method to remove the overlap between instances. This paper also summarize the commonly used panoptic segmentation datasets and the evaluation metrics, then the experimental performance evaluation results of various methods on commonly used datasets are showed. Finally, this paper summarize the general direction of panoptic segmentation, and predict the future research direction.

Accurate organ-level segmentation is essential for achieving high-throughput, non-destructive, and automated plant phenotyping. To address the challenge of intelligent acquisition of phenotypic parameters in tomato plants, we propose TSINet, an end-to-end dual-task segmentation network designed for effective and precise semantic labeling and instance recognition of tomato point clouds, based on the Pheno4D dataset. TSINet adopts an encoder–decoder architecture, where a shared encoder incorporates four Geometry-Aware Adaptive Feature Extraction Blocks (GAFEBs) to effectively capture local structures and geometric relationships in raw point clouds. Two parallel decoder branches are employed to independently decode shared high-level features for the respective segmentation tasks. Additionally, a Dual Attention-Based Feature Enhancement Module (DAFEM) is introduced to further enrich feature representations. The experimental results demonstrate that TSINet achieves superior performance in both semantic and instance segmentation, particularly excelling in challenging categories such as stems and large-scale instances. Specifically, TSINet achieves 97.00% mean precision, 96.17% recall, 96.57% F1-score, and 93.43% IoU in semantic segmentation and 81.54% mPrec, 81.69% mRec, 81.60% mCov, and 86.40% mWCov in instance segmentation. Compared with state-of-the-art methods, TSINet achieves balanced improvements across all metrics, significantly reducing false positives and false negatives while enhancing spatial completeness and segmentation accuracy. Furthermore, we conducted ablation studies and generalization tests to systematically validate the effectiveness of each TSINet component and the overall robustness of the model. This study provides an effective technological approach for high-throughput automated phenotyping of tomato plants, contributing to the advancement of intelligent agricultural management.

Robot perception involves recognizing the surrounding environment, particularly in indoor spaces like kitchens, classrooms, and dining areas. This recognition is crucial for tasks such as object identification. Objects in indoor environments can be categorized into "things," with fixed and countable shapes (e.g., tables, chairs), and "stuff," which lack a fixed shape and cannot be counted (e.g., sky, walls). Object detection and instance segmentation methods excel in identifying "things," with instance segmentation providing more detailed representations than object detection. However, semantic segmentation can identify both "things" and "stuff" but lacks segmentation at the object level. Panoptic segmentation, a fusion of both methods, offers comprehensive object and stuff identification and object-level segmentation. Considerations need to be made regarding the variabilities of room conditions in contrast to implementing panoptic segmentation indoors. High or low contrast in the room potentially reduces the clarity of the shape of an object, thus affecting the segmentation results of that object. We experimented with how contrast varieties impact the panoptic segmentation performance using the MaskDINO model, the first on the panoptic quality (PQ) leaderboard. We then improved the model generalization on the various contrasts by re-optimizing it using a contrast-augmented dataset.

Instance segmentation in high-resolution (HR) remote sensing imagery is one of the most challenging tasks and is more difficult than object detection and semantic segmentation tasks. It aims to predict class labels and pixel-wise instance masks to locate instances in an image. However, there are rare methods currently suitable for instance segmentation in the HR remote sensing images. Meanwhile, it is more difficult to implement instance segmentation due to the complex background of remote sensing images. In this article, a novel instance segmentation approach of HR remote sensing imagery based on Cascade Mask R-CNN is proposed, which is called a high-quality instance segmentation network (HQ-ISNet). In this scheme, the HQ-ISNet exploits a HR feature pyramid network (HRFPN) to fully utilize multi-level feature maps and maintain HR feature maps for remote sensing images’ instance segmentation. Next, to refine mask information flow between mask branches, the instance segmentation network version 2 (ISNetV2) is proposed to promote further improvements in mask prediction accuracy. Then, we construct a new, more challenging dataset based on the synthetic aperture radar (SAR) ship detection dataset (SSDD) and the Northwestern Polytechnical University very-high-resolution 10-class geospatial object detection dataset (NWPU VHR-10) for remote sensing images instance segmentation which can be used as a benchmark for evaluating instance segmentation algorithms in the high-resolution remote sensing images. Finally, extensive experimental analyses and comparisons on the SSDD and the NWPU VHR-10 dataset show that (1) the HRFPN makes the predicted instance masks more accurate, which can effectively enhance the instance segmentation performance of the high-resolution remote sensing imagery; (2) the ISNetV2 is effective and promotes further improvements in mask prediction accuracy; (3) our proposed framework HQ-ISNet is effective and more accurate for instance segmentation in the remote sensing imagery than the existing algorithms.

Chapter 12 - Semantic scene segmentation for robotics

In this study, we propose a segmentation model based on convolutional neural networks (CNNs) to address image segmentation challenges in computer vision. Prior to designing the model, the activation function and other modules of the convolutional neural network were optimized to meet specific requirements. The segmentation task was transformed into binary classification problem to simplify network calculations and improve efficiency. Additionally, the model utilized a mask map obtained from the semantic segmentation model to aid in instance segmentation. Class activation technology was introduced to extract feature mapping maps. The corresponding thermal maps were obtained to achieve target instance segmentation. To further validate the effectiveness of the segmentation model, simulation experiments were conducted on semantic segmentation and instance segmentation respectively. The results show that the accuracy of the basic semantic segmentation model reached 87.58%, while the average accuracy of the entire class of the optimized instance segmentation model reached 97.9%. Therefore, the research and design of image segmentation models demonstrate high accuracy and good robustness.

Advanced Driver Assistance System (ADAS) is a very important part of an up to date vehicle. For achieving highlevel objectives in such ADAS functionality like LKA (lane keeping assistance), LDW (lane departure warning system), FCW (forward collision warning) the quality of the algorithms under the hood must be extremely high. In the last few years, it is common that these algorithms are based on DNNs (deep neural networks) applied to the tasks of semantic and instance segmentation, 2D/3D object detection and visual object tracking. Recent state-of-the-art DNN models as usual solve only one single task from the listed above and running several neural networks is rather computationally expensive and even impossible due to the lack of the GPU memory. One of the approaches used to overcome such a problem is a shared backbone (also called feature extractor or encoder). The backbone consumes most of the computing resources thus the model with a shared backbone achieves better inference performance. Unfortunately, the training procedure for a shared backbone model has several difficulties. The first one is the lack of datasets with all the required and uniform annotation types. The second problem is a more sophisticated backpropagation procedure. In this paper, we consider several methods for multi-task neural network training and present the results of such training procedures on several public datasets with dissimilar annotation types. The shared backbone is applied to the following three tasks performed simultaneously on the road scene: semantic segmentation, 2D object detection and 3D object detection. While the performance of the DNNs with shared backbone increased significantly, we obtained the quality evaluation results, which are quite close to the original separate state-of-the-art DNNs and even outperforms them in some evaluation indices.

<title>Abstract</title> We propose a novel end-to-end convolutional network designed for the instance segmentation of burn regions. Building on the foundational principles of fully convolutional networks (FCNs) for semantic segmentation and instance-level mask generation, the method is tailored to address the unique challenges of burn injury assessment. This approach jointly detects and delineates burn areas while maintaining semantic consistency across the region. By incorporating position-sensitive features, such as inside/outside score maps, the network enables precise segmentation, effectively capturing the boundaries and details of burn regions. The architecture ensures shared convolutional representations for both the semantic and instance segmentation tasks, optimizing performance and computational efficiency. This method is highly integrated and demonstrates superior capability in accurately identifying and segmenting burn regions in medical imaging, offering significant potential for clinical applications.

In this work, we propose a single deep neural network for panoptic segmentation, for which the goal is to provide each individual pixel of an input image with a class label, as in semantic segmentation, as well as a unique identifier for specific objects in an image, following instance segmentation. Our network makes joint semantic and instance segmentation predictions and combines these to form an output in the panoptic format. This has two main benefits: firstly, the entire panoptic prediction is made in one pass, reducing the required computation time and resources; secondly, by learning the tasks jointly, information is shared between the two tasks, thereby improving performance. Our network is evaluated on two street scene datasets: Cityscapes and Mapillary Vistas. By leveraging information exchange and improving the merging heuristics, we increase the performance of the single network, and achieve a score of 23.9 on the Panoptic Quality (PQ) metric on Mapillary Vistas validation, with an input resolution of 640 x 900 pixels. On Cityscapes validation, our method achieves a PQ score of 45.9 with an input resolution of 512 x 1024 pixels. Moreover, our method decreases the prediction time by a factor of 2 with respect to separate networks.

Weakly supervised semantic instance segmentation with only image-level supervision, instead of relying on expensive pixel-wise masks or bounding box annotations, is an important problem to alleviate the data-hungry nature of deep learning. In this article, we tackle this challenging problem by aggregating the image-level information of all training images into a large knowledge graph and exploiting semantic relationships from this graph. Specifically, our effort starts with some generic segment-based object proposals (SOP) without category priors. We propose a multiple instance learning (MIL) framework, which can be trained in an end-to-end manner using training images with image-level labels. For each proposal, this MIL framework can simultaneously compute probability distributions and category-aware semantic features, with which we can formulate a large undirected graph. The category of background is also included in this graph to remove the massive noisy object proposals. An optimal multi-way cut of this graph can thus assign a reliable category label to each proposal. The denoised SOP with assigned category labels can be viewed as pseudo instance segmentation of training images, which are used to train fully supervised models. The proposed approach achieves state-of-the-art performance for both weakly supervised instance segmentation and semantic segmentation. The code is available at https://github.com/yun-liu/LIID.

Medical image analysis is critical yet challenged by the need of jointly segmenting organs or tissues, and numerous instances for anatomical structures and tumor microenvironment analysis. Existing studies typically formulated different segmentation tasks in isolation, which overlooks the fundamental interdependencies between these tasks, leading to suboptimal segmentation performance and insufficient medical image understanding. To address this issue, we propose a Co-Seg++ framework for versatile medical segmentation. Specifically, we introduce a novel co-segmentation paradigm, allowing semantic and instance segmentation tasks to mutually enhance each other. We first devise a spatio-sequential prompt encoder (SSP-Encoder) to capture long-range spatial and sequential relationships between segmentation regions and image embeddings as prior spatial constraints. Moreover, we devise a multi-task collaborative decoder (MTC-Decoder) that leverages cross-guidance to strengthen the contextual consistency of both tasks, jointly computing semantic and instance segmentation masks. Extensive experiments on diverse CT and histopathology datasets demonstrate that the proposed Co-Seg++ outperforms state-of-the-arts in the semantic, instance, and panoptic segmentation of dental anatomical structures, histopathology tissues, and nuclei instances. The source code is available at https://github.com/xq141839/Co-Seg-Plus.

Abstract. Semantic instance segmentation from scenes, serving as a crucial role for 3D modelling and scene understanding. Conducting semantic segmentation before grouping instances is adopted by the existing state-of-the-art methods. However, without additional refinement, semantic errors will fully propagate into the grouping stage, resulting in low overlap with the ground truth instance. Furthermore, the proposed methods focused on indoor level scenes, which are limited when directly applied to large-scale outdoor Airborne Laser Scanning (ALS) point clouds. Numerous instances, significant object density and scale variations make ALS point clouds distinct from indoor data. In order to address the problems, we proposed a geometric characterization-aware semantic instance segmentation network, which utilized both semantic and objectness score to select potential points for grouping. And in point cloud feature learning stage, hand-craft geometry features are taken as input for geometric characterization awareness. Moreover, to address errors propagated from previous modules after grouping, we have additionally designed a per-instance refinement module. To assess semantic instance segmentation, we conducted experiments on an open-source dataset. Additionally, we performed semantic segmentation experiments to evaluate the performance of our proposed point cloud feature learning method.

Instance segmentation in medical imaging plays a crucial role in clinical diagnostic tasks, and have shown promising performance in practical applications. In this paper, we discuss a more fine-grained instance segmentation task: dental structured instance segmentation based on panoramic radiographs. However, direct segmentation of tooth structures encounters inherent challenges. Traditional instance segmentation networks often fall short in capturing intricate internal features, and exacerbated by the frequent blurring found in medical imaging, which can result in the deficiency of anatomical details. To deal with these problems, we propose a novel framework called DSISDPR, which combines a dental structured instance segmentation (DSIS) network with an enhanced diffusion prior refinement (DPR) method. Specifically, our innovatively designed structureaware network leverages fine-grained feature fusion, acquiring a richer representation of internal anatomical structures. With the integration of adversarial learning, the model is primed to deliver holistic and subtle predictions of tooth structures. Furthermore, taking inspiration from dentists’ inherent ability to utilize prior knowledge, such as understanding dental structures to label invisible anatomical structures, we propose a diffusion inpainting to refine the results of DSIS without additional annotations. Equipped with built-in structure learning, DPR is capable of modifying anomalies within each predicted segmentation, resulting in a more robust and complete structured segmentation result. Meanwhile, we ensure rigorous oversight over the reconstruction of areas affected by abnormalities, ensuring that any introduced adjustments minimally disrupt the wellpredicted structured segmentation results. Extensive experiments have demonstrated that our DSIS-DPR outperforms all existing classical instance segmentation networks. The collected dataset is available: <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/Zzz512/TSD</uri> .

Feature upsampling is an essential operation in constructing deep convolutional neural networks. However, existing upsamplers either lack specific feature guidance or necessitate the utilization of high-resolution feature maps, resulting in a loss of performance and flexibility. In this paper, we find that the local self-attention naturally has the feature guidance capability, and its computational paradigm aligns closely with the essence of feature upsampling (i.e. feature reassembly of neighboring points). Therefore, we introduce local self-attention into the upsampling task and demonstrate that the majority of existing upsamplers can be regarded as special cases of upsamplers based on local self-attention. Considering the potential semantic gap between upsampled points and their neighboring points, we further introduce the deformation mechanism into the upsampler based on local self-attention, thereby proposing LDA-AQU. As a novel dynamic kernel-based upsampler, LDA-AQU utilizes the feature of queries to guide the model in adaptively adjusting the position and aggregation weight of neighboring points, thereby meeting the upsampling requirements across various complex scenarios. In addition, LDA-AQU is lightweight and can be easily integrated into various model architectures. We evaluate the effectiveness of LDA-AQU across four dense prediction tasks: object detection, instance segmentation, panoptic segmentation, and semantic segmentation. LDA-AQU consistently outperforms previous state-of-the-art upsamplers, achieving performance enhancements of 1.7 AP, 1.5 AP, 2.0 PQ, and 2.5 mIoU compared to the baseline models in the aforementioned four tasks, respectively.