Multiple-surface segmentation in Optical Coherence Tomography (OCT) images is a challenge problem, further complicated by the frequent presence of weak image boundaries. Recently, many deep learning (DL) based methods have been developed for this task and yield remarkable performance. Unfortunately, due to the scarcity of training data in medical imaging, it is challenging for DL networks to learn the global structure of the target surfaces, including surface smoothness. To bridge this gap, this study proposes to seamlessly unify a U-Net for feature learning with a constrained differentiable dynamic programming module to achieve an end-to-end learning for retina OCT surface segmentation to explicitly enforce surface smoothness. It effectively utilizes the feedback from the downstream model optimization module to guide feature learning, yielding a better enforcement of global structures of the target surfaces. Experiments on Duke AMD (age-related macular degeneration) and JHU MS (multiple sclerosis) OCT datasets for retinal layer segmentation demonstrated very promising segmentation accuracy.
The quality of cardiac magnetic resonance (CMR) imaging is susceptible to respiratory motion artifacts. The model robustness of automated segmentation techniques in face of real-world respiratory motion artifacts is unclear. This manuscript describes the design of extreme cardiac MRI analysis challenge under respiratory motion (CMRxMotion Challenge). The challenge aims to establish a public benchmark dataset to assess the effects of respiratory motion on image quality and examine the robustness of segmentation models. The challenge recruited 40 healthy volunteers to perform different breath-hold behaviors during one imaging visit, obtaining paired cine imaging with artifacts. Radiologists assessed the image quality and annotated the level of respiratory motion artifacts. For those images with diagnostic quality, radiologists further segmented the left ventricle, left ventricle myocardium and right ventricle. The images of training set (20 volunteers) along with the annotations are released to the challenge participants, to develop an automated image quality assessment model (Task 1) and an automated segmentation model (Task 2). The images of validation set (5 volunteers) are released to the challenge participants but the annotations are withheld for online evaluation of submitted predictions. Both the images and annotations of the test set (15 volunteers) were withheld and only used for offline evaluation of submitted containerized dockers. The image quality assessment task is quantitatively evaluated by the Cohen's kappa statistics and the segmentation task is evaluated by the Dice scores and Hausdorff distances.
Amodal Instance Segmentation (AIS) aims to segment the region of both visible and possible occluded parts of an object instance. While Mask R-CNN-based AIS approaches have shown promising results, they are unable to model high-level features coherence due to the limited receptive field. The most recent transformer-based models show impressive performance on vision tasks, even better than Convolution Neural Networks (CNN). In this work, we present AISFormer, an AIS framework, with a Transformer-based mask head. AISFormer explicitly models the complex coherence between occluder, visible, amodal, and invisible masks within an object's regions of interest by treating them as learnable queries. Specifically, AISFormer contains four modules: (i) feature encoding: extract ROI and learn both short-range and long-range visual features. (ii) mask transformer decoding: generate the occluder, visible, and amodal mask query embeddings by a transformer decoder (iii) invisible mask embedding: model the coherence between the amodal and visible masks, and (iv) mask predicting: estimate output masks including occluder, visible, amodal and invisible. We conduct extensive experiments and ablation studies on three challenging benchmarks i.e. KINS, D2SA, and COCOA-cls to evaluate the effectiveness of AISFormer. The code is available at: https://github.com/UARK-AICV/AISFormer
We investigate the task of unsupervised domain adaptation in aerial semantic segmentation and discover that the current state-of-the-art algorithms designed for autonomous driving based on domain mixing do not translate well to the aerial setting. This is due to two factors: (i) a large disparity in the extension of the semantic categories, which causes a domain imbalance in the mixed image, and (ii) a weaker structural consistency in aerial scenes than in driving scenes since the same scene might be viewed from different perspectives and there is no well-defined and repeatable structure of the semantic elements in the images. Our solution to these problems is composed of: (i) a new mixing strategy for aerial segmentation across domains called Hierarchical Instance Mixing (HIMix), which extracts a set of connected components from each semantic mask and mixes them according to a semantic hierarchy and, (ii) a twin-head architecture in which two separate segmentation heads are fed with variations of the same images in a contrastive fashion to produce finer segmentation maps. We conduct extensive experiments on the LoveDA benchmark, where our solution outperforms the current state-of-the-art.
Intraoral 3D scans analysis is a fundamental aspect of Computer-Aided Dentistry (CAD) systems, playing a crucial role in various dental applications, including teeth segmentation, detection, labeling, and dental landmark identification. Accurate analysis of 3D dental scans is essential for orthodontic and prosthetic treatment planning, as it enables automated processing and reduces the need for manual adjustments by dental professionals. However, developing robust automated tools for these tasks remains a significant challenge due to the limited availability of high-quality public datasets and benchmarks. This article introduces Teeth3DS+, the first comprehensive public benchmark designed to advance the field of intraoral 3D scan analysis. Developed as part of the 3DTeethSeg 2022 and 3DTeethLand 2024 MICCAI challenges, Teeth3DS+ aims to drive research in teeth identification, segmentation, labeling, 3D modeling, and dental landmarks identification. The dataset includes at least 1,800 intraoral scans (containing 23,999 annotated teeth) collected from 900 patients, covering both upper and lower jaws separately. All data have been acquired and validated by experienced orthodontists and dental surgeons with over five years of expertise. Detailed instructions for accessing the dataset are available at https://crns-smartvision.github.io/teeth3ds
We present a deep reinforcement learning method of progressive view inpainting for colored semantic point cloud scene completion under volume guidance, achieving high-quality scene reconstruction from only a single RGB-D image with severe occlusion. Our approach is end-to-end, consisting of three modules: 3D scene volume reconstruction, 2D RGB-D and segmentation image inpainting, and multi-view selection for completion. Given a single RGB-D image, our method first predicts its semantic segmentation map and goes through the 3D volume branch to obtain a volumetric scene reconstruction as a guide to the next view inpainting step, which attempts to make up the missing information; the third step involves projecting the volume under the same view of the input, concatenating them to complete the current view RGB-D and segmentation map, and integrating all RGB-D and segmentation maps into the point cloud. Since the occluded areas are unavailable, we resort to a A3C network to glance around and pick the next best view for large hole completion progressively until a scene is adequately reconstructed while guaranteeing validity. All steps are learned jointly to achieve robust and consistent results. We perform qualitative and quantitative evaluations with extensive experiments on the 3D-FUTURE data, obtaining better results than state-of-the-arts.
Large-scale point cloud semantic segmentation is an important task in 3D computer vision, which is widely applied in autonomous driving, robotics, and virtual reality. Current large-scale point cloud semantic segmentation methods usually use down-sampling operations to improve computation efficiency and acquire point clouds with multi-resolution. However, this may cause the problem of missing local information. Meanwhile, it is difficult for networks to capture global information in large-scale distributed contexts. To capture local and global information effectively, we propose an end-to-end deep neural network called LACV-Net for large-scale point cloud semantic segmentation. The proposed network contains three main components: 1) a local adaptive feature augmentation module (LAFA) to adaptively learn the similarity of centroids and neighboring points to augment the local context; 2) a comprehensive VLAD module (C-VLAD) that fuses local features with multi-layer, multi-scale, and multi-resolution to represent a comprehensive global description vector; and 3) an aggregation loss function to effectively optimize the segmentation boundaries by constraining the adaptive weight from the LAFA module. Compared to state-of-the-art networks on several large-scale benchmark datasets, including S3DIS, Toronto3D, and SensatUrban, we demonstrated the effectiveness of the proposed network.
Livestream videos have become a significant part of online learning, where design, digital marketing, creative painting, and other skills are taught by experienced experts in the sessions, making them valuable materials. However, Livestream tutorial videos are usually hours long, recorded, and uploaded to the Internet directly after the live sessions, making it hard for other people to catch up quickly. An outline will be a beneficial solution, which requires the video to be temporally segmented according to topics. In this work, we introduced a large Livestream video dataset named MultiLive, and formulated the temporal segmentation of the long Livestream videos (TSLLV) task. We propose LiveSeg, an unsupervised Livestream video temporal Segmentation solution, which takes advantage of multimodal features from different domains. Our method achieved a $16.8\%$ F1-score performance improvement compared with the state-of-the-art method.
Panoptic segmentation assigns semantic and instance ID labels to every pixel of an image. As permutations of instance IDs are also valid solutions, the task requires learning of high-dimensional one-to-many mapping. As a result, state-of-the-art approaches use customized architectures and task-specific loss functions. We formulate panoptic segmentation as a discrete data generation problem, without relying on inductive bias of the task. A diffusion model is proposed to model panoptic masks, with a simple architecture and generic loss function. By simply adding past predictions as a conditioning signal, our method is capable of modeling video (in a streaming setting) and thereby learns to track object instances automatically. With extensive experiments, we demonstrate that our simple approach can perform competitively to state-of-the-art specialist methods in similar settings.
We explore the capability of plain Vision Transformers (ViTs) for semantic segmentation and propose the SegVit. Previous ViT-based segmentation networks usually learn a pixel-level representation from the output of the ViT. Differently, we make use of the fundamental component -- attention mechanism, to generate masks for semantic segmentation. Specifically, we propose the Attention-to-Mask (ATM) module, in which the similarity maps between a set of learnable class tokens and the spatial feature maps are transferred to the segmentation masks. Experiments show that our proposed SegVit using the ATM module outperforms its counterparts using the plain ViT backbone on the ADE20K dataset and achieves new state-of-the-art performance on COCO-Stuff-10K and PASCAL-Context datasets. Furthermore, to reduce the computational cost of the ViT backbone, we propose query-based down-sampling (QD) and query-based up-sampling (QU) to build a Shrunk structure. With the proposed Shrunk structure, the model can save up to $40\%$ computations while maintaining competitive performance.
Ensemble approaches for deep-learning-based semantic segmentation remain insufficiently explored despite the proliferation of competitive benchmarks and downstream applications. In this work, we explore and benchmark the popular ensembling approach of combining predictions of multiple, independently-trained, state-of-the-art models at test time on popular datasets. Furthermore, we propose a novel method inspired by boosting to sequentially ensemble networks that significantly outperforms the naive ensemble baseline. Our approach trains a cascade of models conditioned on class probabilities predicted by the previous model as an additional input. A key benefit of this approach is that it allows for dynamic computation offloading, which helps deploy models on mobile devices. Our proposed novel ADaptive modulatiON (ADON) block allows spatial feature modulation at various layers using previous-stage probabilities. Our approach does not require sophisticated sample selection strategies during training and works with multiple neural architectures. We significantly improve over the naive ensemble baseline on challenging datasets such as Cityscapes, ADE-20K, COCO-Stuff, and PASCAL-Context and set a new state-of-the-art.
We propose CLIP-Fields, an implicit scene model that can be used for a variety of tasks, such as segmentation, instance identification, semantic search over space, and view localization. CLIP-Fields learns a mapping from spatial locations to semantic embedding vectors. Importantly, we show that this mapping can be trained with supervision coming only from web-image and web-text trained models such as CLIP, Detic, and Sentence-BERT; and thus uses no direct human supervision. When compared to baselines like Mask-RCNN, our method outperforms on few-shot instance identification or semantic segmentation on the HM3D dataset with only a fraction of the examples. Finally, we show that using CLIP-Fields as a scene memory, robots can perform semantic navigation in real-world environments. Our code and demonstration videos are available here: https://mahis.life/clip-fields
Recent semantic segmentation models perform well under standard weather conditions and sufficient illumination but struggle with adverse weather conditions and nighttime. Collecting and annotating training data under these conditions is expensive, time-consuming, error-prone, and not always practical. Usually, synthetic data is used as a feasible data source to increase the amount of training data. However, just directly using synthetic data may actually harm the model's performance under normal weather conditions while getting only small gains in adverse situations. Therefore, we present a novel architecture specifically designed for using synthetic training data for domain adaptation. We propose a simple yet powerful addition to DeepLabV3+ by using weather and time-of-the-day supervisors trained with multi-task learning, making it both weather and nighttime aware, which improves its mIoU accuracy by $14$ percentage points on the ACDC dataset while maintaining a score of $75\%$ mIoU on the Cityscapes dataset. Our code is available at https://github.com/lsmcolab/Semantic-Segmentation-under-Adverse-Conditions.
This paper studies semi-supervised video object segmentation through boosting intra-frame interaction. Recent memory network-based methods focus on exploiting inter-frame temporal reference while paying little attention to intra-frame spatial dependency. Specifically, these segmentation model tends to be susceptible to interference from unrelated nontarget objects in a certain frame. To this end, we propose Global Spectral Filter Memory network (GSFM), which improves intra-frame interaction through learning long-term spatial dependencies in the spectral domain. The key components of GSFM is 2D (inverse) discrete Fourier transform for spatial information mixing. Besides, we empirically find low frequency feature should be enhanced in encoder (backbone) while high frequency for decoder (segmentation head). We attribute this to semantic information extracting role for encoder and fine-grained details highlighting role for decoder. Thus, Low (High) Frequency Module is proposed to fit this circumstance. Extensive experiments on the popular DAVIS and YouTube-VOS benchmarks demonstrate that GSFM noticeably outperforms the baseline method and achieves state-of-the-art performance. Besides, extensive analysis shows that the proposed modules are reasonable and of great generalization ability. Our source code is available at https://github.com/workforai/GSFM.
Semantic segmentation is a fundamental topic in computer vision. Several deep learning methods have been proposed for semantic segmentation with outstanding results. However, these models require a lot of densely annotated images. To address this problem, we propose a new algorithm that uses HyperGraph Convolutional Networks for Weakly-supervised Semantic Segmentation (HyperGCN-WSS). Our algorithm constructs spatial and k-Nearest Neighbor (k-NN) graphs from the images in the dataset to generate the hypergraphs. Then, we train a specialized HyperGraph Convolutional Network (HyperGCN) architecture using some weak signals. The outputs of the HyperGCN are denominated pseudo-labels, which are later used to train a DeepLab model for semantic segmentation. HyperGCN-WSS is evaluated on the PASCAL VOC 2012 dataset for semantic segmentation, using scribbles or clicks as weak signals. Our algorithm shows competitive performance against previous methods.
Due to the few annotated labels of 3D point clouds, how to learn discriminative features of point clouds to segment object instances is a challenging problem. In this paper, we propose a simple yet effective 3D instance segmentation framework that can achieve good performance by annotating only one point for each instance. Specifically, to tackle extremely few labels for instance segmentation, we first oversegment the point cloud into superpoints in an unsupervised manner and extend the point-level annotations to the superpoint level. Then, based on the superpoint graph, we propose an inter-superpoint affinity mining module that considers the semantic and spatial relations to adaptively learn inter-superpoint affinity to generate high-quality pseudo labels via semantic-aware random walk. Finally, we propose a volume-aware instance refinement module to segment high-quality instances by applying volume constraints of objects in clustering on the superpoint graph. Extensive experiments on the ScanNet-v2 and S3DIS datasets demonstrate that our method achieves state-of-the-art performance in the weakly supervised point cloud instance segmentation task, and even outperforms some fully supervised methods.
Image segmentation is a historic and significant computer vision task. With the help of deep learning techniques, image semantic segmentation has made great progresses. Over recent years, based on guidance of attention mechanism compared with CNN which overcomes the problems of lacking of interaction between different channels, and effective capturing and aggregating contextual information. However, the massive operations generated by the attention mechanism lead to its extremely high complexity and high demand for GPU memory. For this purpose, we propose a lightweight and flexible neural network named Dual Pool Attention Network(DPANet). The most important is that all modules in DPANet generate \textbf{0} parameters. The first component is spatial pool attention module, we formulate an easy and powerful method densely to extract contextual characteristics and reduce the amount of calculation and complexity dramatically.Meanwhile, it demonstrates the power of even and large kernel size. The second component is channel pool attention module. It is known that the computation process of CNN incorporates the information of spatial and channel dimensions. So, the aim of this module is stripping them out, in order to construct relationship of all channels and heighten different channels semantic information selectively. Moreover, we experiments on segmentation datasets, which shows our method simple and effective with low parameters and calculation complexity.
Applications in the field of augmented reality or robotics often require joint localisation and 6D pose estimation of multiple objects. However, most algorithms need one network per object class to be trained in order to provide the best results. Analysing all visible objects demands multiple inferences, which is memory and time-consuming. We present a new single-stage architecture called CASAPose that determines 2D-3D correspondences for pose estimation of multiple different objects in RGB images in one pass. It is fast and memory efficient, and achieves high accuracy for multiple objects by exploiting the output of a semantic segmentation decoder as control input to a keypoint recognition decoder via local class-adaptive normalisation. Our new differentiable regression of keypoint locations significantly contributes to a faster closing of the domain gap between real test and synthetic training data. We apply segmentation-aware convolutions and upsampling operations to increase the focus inside the object mask and to reduce mutual interference of occluding objects. For each inserted object, the network grows by only one output segmentation map and a negligible number of parameters. We outperform state-of-the-art approaches in challenging multi-object scenes with inter-object occlusion and synthetic training.
Transformer models achieve state-of-the-art results for image segmentation. However, achieving long-range attention, necessary to capture global context, with high-resolution 3D images is a fundamental challenge. This paper introduces the Full resolutIoN mEmory (FINE) transformer to overcome this issue. The core idea behind FINE is to learn memory tokens to indirectly model full range interactions while scaling well in both memory and computational costs. FINE introduces memory tokens at two levels: the first one allows full interaction between voxels within local image regions (patches), the second one allows full interactions between all regions of the 3D volume. Combined, they allow full attention over high resolution images, e.g. 512 x 512 x 256 voxels and above. Experiments on the BCV image segmentation dataset shows better performances than state-of-the-art CNN and transformer baselines, highlighting the superiority of our full attention mechanism compared to recent transformer baselines, e.g. CoTr, and nnFormer.
Automatic human matting is highly desired for many real applications. We investigate recent human matting methods and show that common bad cases happen when semantic human segmentation fails. This indicates that semantic understanding is crucial for robust human matting. From this, we develop a fast yet accurate human matting framework, named Semantic Guided Human Matting (SGHM). It builds on a semantic human segmentation network and introduces a light-weight matting module with only marginal computational cost. Unlike previous works, our framework is data efficient, which requires a small amount of matting ground-truth to learn to estimate high quality object mattes. Our experiments show that trained with merely 200 matting images, our method can generalize well to real-world datasets, and outperform recent methods on multiple benchmarks, while remaining efficient. Considering the unbearable labeling cost of matting data and widely available segmentation data, our method becomes a practical and effective solution for the task of human matting. Source code is available at https://github.com/cxgincsu/SemanticGuidedHumanMatting.