Panoptic Segmentation Research Articles

Hybrid AI for panoptic segmentation: An informed deep learning approach with integration of prior spatial relationships knowledge

Panoptic segmentation is a computer vision task that aims to identify and analyze all objects present in an image. While semantic segmentation focuses on labeling each pixel in an image with a category label, panoptic segmentation goes further by not only assigning semantic labels but also identifying and distinguishing individual instance of objects. This task is valuable for various applications, such as robotics, surveillance systems or autonomous vehicle navigation. In this work, we propose a new informed deep learning approach that combines the strengths of deep neural networks for panoptic segmentation with additional knowledge about spatial relationships between objects. This is particularly important as spatial relationships can provide useful cues for resolving ambiguities, distinguishing between overlapping or similar object instances, and capturing the holistic structure of the scene. We propose a novel training methodology that integrates knowledge directly into the deep neural network optimization process. Our approach includes a process for extracting and representing spatial relationships knowledge, which is incorporated into the training using a specially designed loss function. The effectiveness of the proposed method is evaluated and validated on various challenging datasets, namely CityScapes, KITTI, IDD and COCO datasets.

Panoptic Segmentation with Convex Object Representation

Abstract The accurate representation of objects holds pivotal significance in the realm of panoptic segmentation. Presently, prevalent object representation methodologies, including box-based, keypoint-based and query-based techniques, encounter a challenge known as the ‘representation confusion’ issue in specific scenarios, often resulting in the mislabeling of instances. In response, this paper introduces Convex Object Representation (COR), a straightforward yet highly effective approach to address this problem. COR leverages a CNN-based Euclidean Distance Transform to convert the target instance into a convex heatmap. Simultaneously, it offers a parallel embedding method for encoding the object. Subsequently, COR characterizes objects based on the distinctive embedding vectors of their convex vertices. This paper seamlessly integrates COR into a state-of-the-art query-based panoptic segmentation framework. Experimental findings validate that COR successfully mitigates the representation confusion predicament, enhancing segmentation accuracy. The COR-augmented methods exhibit notable improvements of +1.3 and +0.7 points in PQ on the Cityscapes validation and MS COCO panoptic 2017 validation datasets, respectively.

TOWARDS ACCURATE INSTANCE SEGMENTATION IN LARGE-SCALE LIDAR POINT CLOUDS

Abstract. Panoptic segmentation is the combination of semantic and instance segmentation: assign the points in a 3D point cloud to semantic categories and partition them into distinct object instances. It has many obvious applications for outdoor scene understanding, from city mapping to forest management. Existing methods struggle to segment nearby instances of the same semantic category, like adjacent pieces of street furniture or neighbouring trees, which limits their usability for inventory- or management-type applications that rely on object instances. This study explores the steps of the panoptic segmentation pipeline concerned with clustering points into object instances, with the goal to alleviate that bottleneck. We find that a carefully designed clustering strategy, which leverages multiple types of learned point embeddings, significantly improves instance segmentation. Experiments on the NPM3D urban mobile mapping dataset and the FOR-instance forest dataset demonstrate the effectiveness and versatility of the proposed strategy.

Center-Guided Transformer for Panoptic Segmentation

A panoptic segmentation network to predict masks and classes for things and stuff in images is proposed in this work. Recently, panoptic segmentation has been advanced through the combination of the query-based learning and end-to-end learning approaches. Current research focuses on learning queries without distinguishing between thing and stuff classes. We present decoupling query learning to generate effective thing and stuff queries for panoptic segmentation. For this purpose, we adopt different workflows for thing and stuff queries. We design center-guided query selection for thing queries, which focuses on the center regions of individual instances in images, while we set stuff queries as randomly initialized embeddings. Also, we apply a decoupling mask to the self-attention of query features to prevent interactions between things and stuff. In the query selection process, we generate a center heatmap that guides thing query selection. Experimental results demonstrate that the proposed panoptic segmentation network outperforms the state of the art on two panoptic segmentation datasets.

Correlating Deep Learning-Based Automated Reference Kidney Histomorphometry with Patient Demographics and Creatinine.

Reference histomorphometric data of healthy human kidneys are largely lacking due to laborious quantitation requirements. Correlating histomorphometric features with clinical parameters through machine learning approaches can provide valuable information about natural population variance. To this end, we leveraged deep learning, computational image analysis, and feature analysis to associate the relationship of histomorphometry with patient age, sex, serum creatinine (SCr), and estimated glomerular filtration rate (eGFR) in a multinational set of reference kidney tissue sections. A panoptic segmentation neural network was developed and used to segment viable and sclerotic glomeruli, cortical and medullary interstitia, tubules, and arteries/arterioles in the digitized images of 79 periodic acid-Schiff-stained human nephrectomy sections showing minimal pathologic changes. Simple morphometrics (e.g., area, radius, density) were quantified from the segmented classes. Regression analysis aided in determining the association of histomorphometric parameters with age, sex, SCr, and eGFR. Our deep-learning model achieved high segmentation performance for all test compartments. The size and density of glomeruli, tubules, and arteries/arterioles varied significantly among healthy humans, with potentially large differences between geographically diverse patients. Glomerular size was significantly correlated with SCr and eGFR. Slight, albeit significant, differences in renal vasculature were observed between sexes. Glomerulosclerosis percentage increased and cortical density of arteries/arterioles decreased, as a function of increasing age. Using deep learning, we automated precise measurements of kidney histomorphometric features. In the reference kidney tissue, several histomorphometric features demonstrated significant correlation to patient demographics, SCr, and eGFR. Deep learning tools can increase the efficiency and rigor of histomorphometric analysis.

PiGLET: Pixel-Level Grounding of Language Expressions With Transformers.

This paper proposes Panoptic Narrative Grounding, a spatially fine and general formulation of the natural language visual grounding problem. We establish an experimental framework for the study of this new task, including new ground truth and metrics. We propose PiGLET, a novel multi-modal Transformer architecture to tackle the Panoptic Narrative Grounding task, and to serve as a stepping stone for future work. We exploit the intrinsic semantic richness in an image by including panoptic categories, and we approach visual grounding at a fine-grained level using segmentations. In terms of ground truth, we propose an algorithm to automatically transfer Localized Narratives annotations to specific regions in the panoptic segmentations of the MS COCO dataset. PiGLET achieves a performance of 63.2 absolute Average Recall points. By leveraging the rich language information on the Panoptic Narrative Grounding benchmark on MS COCO, PiGLET obtains an improvement of 0.4 Panoptic Quality points over its base method on the panoptic segmentation task. Finally, we demonstrate the generalizability of our method to other natural language visual grounding problems such as Referring Expression Segmentation. PiGLET is competitive with previous state-of-the-art in RefCOCO, RefCOCO+ and RefCOCOg.

Dense Semantic Forecasting in Video by Joint Regression of Features and Feature Motion.

Dense semantic forecasting anticipates future events in the video by inferring pixel-level semantics of an unobserved future image. We present a novel approach that is applicable to various single-frame architectures and tasks. Our approach consists of two modules. The feature-to-motion (F2M) module forecasts a dense deformation field that warps past features into their future positions. The feature-to-feature (F2F) module regresses the future features directly and is, therefore, able to account for emergent scenery. The compound F2MF model decouples the effects of motion from the effects of novelty in a task-agnostic manner. We aim to apply F2MF forecasting to the most subsampled and the most abstract representation of the desired single-frame model. Our design takes advantage of deformable convolutions and spatial correlation coefficients across neighboring time instants. We perform experiments on three dense prediction tasks: semantic segmentation, instance-level segmentation, and panoptic segmentation. The results reveal state-of-the-art forecasting accuracy across three dense prediction tasks.

A Survey on Label-Efficient Deep Image Segmentation: Bridging the Gap Between Weak Supervision and Dense Prediction.

The rapid development of deep learning has made a great progress in image segmentation, one of the fundamental tasks of computer vision. However, the current segmentation algorithms mostly rely on the availability of pixel-level annotations, which are often expensive, tedious, and laborious. To alleviate this burden, the past years have witnessed an increasing attention in building label-efficient, deep-learning-based image segmentation algorithms. This paper offers a comprehensive review on label-efficient image segmentation methods. To this end, we first develop a taxonomy to organize these methods according to the supervision provided by different types of weak labels (including no supervision, inexact supervision, incomplete supervision and inaccurate supervision) and supplemented by the types of segmentation problems (including semantic segmentation, instance segmentation and panoptic segmentation). Next, we summarize the existing label-efficient image segmentation methods from a unified perspective that discusses an important question: how to bridge the gap between weak supervision and dense prediction - the current methods are mostly based on heuristic priors, such as cross-pixel similarity, cross-label constraint, cross-view consistency, and cross-image relation. Finally, we share our opinions about the future research directions for label-efficient deep image segmentation.

Visual attention network

While originally designed for natural language processing tasks, the self-attention mechanism has recently taken various computer vision areas by storm. However, the 2D nature of images brings three challenges for applying self-attention in computer vision: (1) treating images as 1D sequences neglects their 2D structures; (2) the quadratic complexity is too expensive for high-resolution images; (3) it only captures spatial adaptability but ignores channel adaptability. In this paper, we propose a novel linear attention named large kernel attention (LKA) to enable self-adaptive and long-range correlations in self-attention while avoiding its shortcomings. Furthermore, we present a neural network based on LKA, namely Visual Attention Network (VAN). While extremely simple, VAN achieves comparable results with similar size convolutional neural networks (CNNs) and vision transformers (ViTs) in various tasks, including image classification, object detection, semantic segmentation, panoptic segmentation, pose estimation, etc. For example, VAN-B6 achieves 87.8% accuracy on ImageNet benchmark, and sets new state-of-the-art performance (58.2 PQ) for panoptic segmentation. Besides, VAN-B2 surpasses Swin-T 4 mIoU (50.1 vs. 46.1) for semantic segmentation on ADE20K benchmark, 2.6 AP (48.8 vs. 46.2) for object detection on COCO dataset. It provides a novel method and a simple yet strong baseline for the community. The code is available at https://github.com/Visual-Attention-Network.

Route Planning for Emergency Evacuation Using Graph Traversal Algorithms

The automatic identification of various design elements in a floor-plan image has gained increasing attention in recent research. Emergency-evacuation applications can benefit greatly from automated floor-plan solutions, as they allow for the development of horizontal solutions instead of vertical solutions targeting a specific audience. In addition to that, current evacuation plans rely on static signs without taking into account the dynamic characteristics of each emergency case. This work aims to extract information from a floor-plan image and transform it into a graph that is used for pathfinding in an emergency evacuation. First, the basic elements of the floor-plan image, i.e., walls, rooms and doors, are identified. This is achieved using Panoptic-DeepLab, which is a state-of-the-art deep neural network for the panoptic segmentation of images, and it is available from DeepLab2, an image segmentation library. The neural network was trained using CubiCasa5K, a large-scale floor-plan image dataset containing 5000 samples, annotated into over 80 floor-plan object categories. Then, using the prediction of each pixel, a graph that shows how rooms and doors are connected is created. An application that presents this information in a user-friendly manner and provides graph editing capabilities was developed. Finally, the exits are set, and the optimal path for evacuation is calculated from each node using Dijkstra’s algorithm.

Synthetic image data generation using BIM and computer graphics for building scene understanding

Vision-based building scene understanding (BSU) is essential to many applications such as indoor navigation and 3D reconstruction. Deep learning excels in various BSU tasks but its training relies heavily on large-scale datasets, which are often burdensome and costly to obtain. This study proposes a universal and automated approach to generate synthetic building images with comprehensive annotations that support twelve BSU tasks, including camera pose estimation, scene recognition, depth estimation, 2D/3D object and object part detection, object and material semantic segmentation, object and object part instance segmentation, and panoptic segmentation. This approach captures and renders perspective views of indoor BIM model scenes to generate photorealistic images. Required annotations are computed by a ray tracing-based algorithm accelerated by two-tier axis-aligned bounding box tree indexing. The approach was validated by efficiently producing annotated synthetic images from various BIM models, and preliminary experiments demonstrated the promising efficacy of the synthetic images for deep learning model training.

PUPS: Point Cloud Unified Panoptic Segmentation

Point cloud panoptic segmentation is a challenging task that seeks a holistic solution for both semantic and instance segmentation to predict groupings of coherent points. Previous approaches treat semantic and instance segmentation as surrogate tasks, and they either use clustering methods or bounding boxes to gather instance groupings with costly computation and hand-craft designs in the instance segmentation task. In this paper, we propose a simple but effective point cloud unified panoptic segmentation (PUPS) framework, which use a set of point-level classifiers to directly predict semantic and instance groupings in an end-to-end manner. To realize PUPS, we introduce bipartite matching to our training pipeline so that our classifiers are able to exclusively predict groupings of instances, getting rid of hand-crafted designs, e.g. anchors and Non-Maximum Suppression (NMS). In order to achieve better grouping results, we utilize a transformer decoder to iteratively refine the point classifiers and develop a context-aware CutMix augmentation to overcome the class imbalance problem. As a result, PUPS achieves 1st place on the leader board of SemanticKITTI panoptic segmentation task and state-of-the-art results on nuScenes.

LidarMultiNet: Towards a Unified Multi-Task Network for LiDAR Perception

LiDAR-based 3D object detection, semantic segmentation, and panoptic segmentation are usually implemented in specialized networks with distinctive architectures that are difficult to adapt to each other. This paper presents LidarMultiNet, a LiDAR-based multi-task network that unifies these three major LiDAR perception tasks. Among its many benefits, a multi-task network can reduce the overall cost by sharing weights and computation among multiple tasks. However, it typically underperforms compared to independently combined single-task models. The proposed LidarMultiNet aims to bridge the performance gap between the multi-task network and multiple single-task networks. At the core of LidarMultiNet is a strong 3D voxel-based encoder-decoder architecture with a Global Context Pooling (GCP) module extracting global contextual features from a LiDAR frame. Task-specific heads are added on top of the network to perform the three LiDAR perception tasks. More tasks can be implemented simply by adding new task-specific heads while introducing little additional cost. A second stage is also proposed to refine the first-stage segmentation and generate accurate panoptic segmentation results. LidarMultiNet is extensively tested on both Waymo Open Dataset and nuScenes dataset, demonstrating for the first time that major LiDAR perception tasks can be unified in a single strong network that is trained end-to-end and achieves state-of-the-art performance. Notably, LidarMultiNet reaches the official 1 place in the Waymo Open Dataset 3D semantic segmentation challenge 2022 with the highest mIoU and the best accuracy for most of the 22 classes on the test set, using only LiDAR points as input. It also sets the new state-of-the-art for a single model on the Waymo 3D object detection benchmark and three nuScenes benchmarks.

Deep learning‐based panoptic segmentation: Recent advances and perspectives

AbstractIn recent years, panoptic segmentation has drawn increasing amounts of attention, leading to the rapid emergence of numerous related algorithms. A variety of deep neural networks have been used more frequently for panoptic segmentation, which is motivated by the significant success of deep learning methods in other tasks. This article presents a comprehensive exploration of panoptic segmentation, focusing on the analysis and understanding of RGB image data. Initially, the authors introduce the background of panoptic segmentation, including deep learning models and image segmentation. Then, the authors thoroughly cover a variety of panoptic segmentation‐related topics, such as datasets connected to the field, evaluation metrics, panoptic segmentation models, and derived subfields based on panoptic segmentation. Finally, the authors examine the difficulties and possibilities in this area and identify its future paths.

Panoptic quality should be avoided as a metric for assessing cell nuclei segmentation and classification in digital pathology

Panoptic Quality (PQ), designed for the task of “Panoptic Segmentation” (PS), has been used in several digital pathology challenges and publications on cell nucleus instance segmentation and classification (ISC) since its introduction in 2019. Its purpose is to encompass the detection and the segmentation aspects of the task in a single measure, so that algorithms can be ranked according to their overall performance. A careful analysis of the properties of the metric, its application to ISC and the characteristics of nucleus ISC datasets, shows that is not suitable for this purpose and should be avoided. Through a theoretical analysis we demonstrate that PS and ISC, despite their similarities, have some fundamental differences that make PQ unsuitable. We also show that the use of the Intersection over Union as a matching rule and as a segmentation quality measure within PQ is not adapted for such small objects as nuclei. We illustrate these findings with examples taken from the NuCLS and MoNuSAC datasets. The code for replicating our results is available on GitHub (https://github.com/adfoucart/panoptic-quality-suppl).

Uncertainty-Aware Panoptic Segmentation

Reliable scene understanding is indispensable for modern autonomous systems. Current learning-based methods typically try to maximize their performance based on segmentation metrics that only consider the quality of the segmentation. However, for the safe operation of a system in the real world it is crucial to consider the uncertainty in the prediction as well. In this work, we introduce the novel task of uncertainty-aware panoptic segmentation, which aims to predict per-pixel semantic and instance segmentations, together with per-pixel uncertainty estimates. We define two novel metrics to facilitate its quantitative analysis, the uncertainty-aware Panoptic Quality (uPQ) and the panoptic Expected Calibration Error (pECE). We further propose the novel top-down Evidential Panoptic Segmentation Network (EvPSNet) to solve this task. Our architecture employs a simple yet effective panoptic fusion module that leverages the predicted uncertainties. Furthermore, we provide several strong baselines combining state-of-the-art panoptic segmentation networks with sampling-free uncertainty estimation techniques. Extensive evaluations show that our EvPSNet achieves the new state-of-the-art for the standard Panoptic Quality (PQ), as well as for our uncertainty-aware panoptic metrics. We make the code available at: <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/kshitij3112/EvPSNet</uri>

Bridging Multi-Scale Context-Aware Representation for Object Detection

Feature Pyramid Network (FPN) exploits multi-scale fusion representation to deal with scale variances in object detection. However, it ignores the context information gap across different levels. In this paper, we develop a plug-and-play detector, the multi-scale context-aware feature pyramid network to unleash the power of feature pyramid representation. Based on the dilated feature map at the highest level of the backbone, we propose the cross-scale context aggregation block to make full use of context information in the feature pyramid. Moreover, we extract discriminative features among different levels by the adaptive context aggregation block for robust object detection. Comprehensive experiments on MS-COCO demonstrate the effectiveness and efficiency of the proposed network, where about 1.0 ~ 3.0 AP improvements are achieved compared with existing FPN-based methods. In addition, we also conduct extensive experiments on pixel-level prediction tasks, <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">i.e</i> ., instance segmentation, semantic segmentation, and panoptic segmentation, which further verify the effectiveness of the proposed method.

Automated Reference Kidney Histomorphometry using a Panoptic Segmentation Neural Network Correlates to Patient Demographics and Creatinine.

Reference histomorphometric data of healthy human kidneys are lacking due to laborious quantitation requirements. We leveraged deep learning to investigate the relationship of histomorphometry with patient age, sex, and serum creatinine in a multinational set of reference kidney tissue sections. A panoptic segmentation neural network was developed and used to segment viable and sclerotic glomeruli, cortical and medullary interstitia, tubules, and arteries/arterioles in digitized images of 79 periodic acid-Schiff (PAS)-stained human nephrectomy sections showing minimal pathologic changes. Simple morphometrics (e.g., area, radius, density) were measured from the segmented classes. Regression analysis was used to determine the relationship of histomorphometric parameters with age, sex, and serum creatinine. The model achieved high segmentation performance for all test compartments. We found that the size and density of nephrons, arteries/arterioles, and the baseline level of interstitium vary significantly among healthy humans, with potentially large differences between subjects from different geographic locations. Nephron size in any region of the kidney was significantly dependent on patient creatinine. Slight differences in renal vasculature and interstitium were observed between sexes. Finally, glomerulosclerosis percentage increased and cortical density of arteries/arterioles decreased as a function of age. We show that precise measurements of kidney histomorphometric parameters can be automated. Even in reference kidney tissue sections with minimal pathologic changes, several histomorphometric parameters demonstrated significant correlation to patient demographics and serum creatinine. These robust tools support the feasibility of deep learning to increase efficiency and rigor in histomorphometric analysis and pave the way for future large-scale studies.

Panoptic SwiftNet: Pyramidal Fusion for Real-Time Panoptic Segmentation

Dense panoptic prediction is a key ingredient in many existing applications such as autonomous driving, automated warehouses, or remote sensing. Many of these applications require fast inference over large input resolutions on affordable or even embedded hardware. We proposed to achieve this goal by trading off backbone capacity for multi-scale feature extraction. In comparison with contemporaneous approaches to panoptic segmentation, the main novelties of our method are efficient scale-equivariant feature extraction, cross-scale upsampling through pyramidal fusion and boundary-aware learning of pixel-to-instance assignment. The proposed method is very well suited for remote sensing imagery due to the huge number of pixels in typical city-wide and region-wide datasets. We present panoptic experiments on Cityscapes, Vistas, COCO, and the BSB-Aerial dataset. Our models outperformed the state-of-the-art on the BSB-Aerial dataset while being able to process more than a hundred 1MPx images per second on an RTX3090 GPU with FP16 precision and TensorRT optimization.

Multimodal deep learning for point cloud panoptic segmentation of railway environments

The demand for transportation asset digitalisation has significantly increased over the years. For this purpose, mobile mapping systems (MMSs) are among the most popular technologies that allow capturing high precision three-dimensional point clouds of the infrastructure. In this paper, a multimodal deep learning methodology is presented for panoptic segmentation of the railway infrastructure. The methodology takes advantage of image rasterisation of the point clouds to perform a rough segmentation and discard more than 80% of points that are not relevant to the infrastructure. With this approach, the computational requirements for processing the remaining point cloud are highly reduced, allowing the process of dense point clouds in short periods of time. A 90 km-long railway scenario was used for training and testing. The proposed methodology is two times faster than the current state-of-the-art for the same point cloud density, and pole-like object segmentation metrics are improved.