Semantic segmentation is important for scene understanding. To address the scenes of adverse illumination conditions of natural images, thermal infrared (TIR) images are introduced. Most existing RGB-T semantic segmentation methods follow three cross-modal fusion paradigms, i.e. encoder fusion, decoder fusion, and feature fusion. Some methods, unfortunately, ignore the properties of RGB and TIR features or the properties of features at different levels. In this paper, we propose a novel feature fusion-based network for RGB-T semantic segmentation, named \emph{LASNet}, which follows three steps of location, activation, and sharpening. The highlight of LASNet is that we fully consider the characteristics of cross-modal features at different levels, and accordingly propose three specific modules for better segmentation. Concretely, we propose a Collaborative Location Module (CLM) for high-level semantic features, aiming to locate all potential objects. We propose a Complementary Activation Module for middle-level features, aiming to activate exact regions of different objects. We propose an Edge Sharpening Module (ESM) for low-level texture features, aiming to sharpen the edges of objects. Furthermore, in the training phase, we attach a location supervision and an edge supervision after CLM and ESM, respectively, and impose two semantic supervisions in the decoder part to facilitate network convergence. Experimental results on two public datasets demonstrate that the superiority of our LASNet over relevant state-of-the-art methods. The code and results of our method are available at https://github.com/MathLee/LASNet.
The task of topical segmentation is well studied, but previous work has mostly addressed it in the context of structured, well-defined segments, such as segmentation into paragraphs, chapters, or segmenting text that originated from multiple sources. We tackle the task of segmenting running (spoken) narratives, which poses hitherto unaddressed challenges. As a test case, we address Holocaust survivor testimonies, given in English. Other than the importance of studying these testimonies for Holocaust research, we argue that they provide an interesting test case for topical segmentation, due to their unstructured surface level, relative abundance (tens of thousands of such testimonies were collected), and the relatively confined domain that they cover. We hypothesize that boundary points between segments correspond to low mutual information between the sentences proceeding and following the boundary. Based on this hypothesis, we explore a range of algorithmic approaches to the task, building on previous work on segmentation that uses generative Bayesian modeling and state-of-the-art neural machinery. Compared to manually annotated references, we find that the developed approaches show considerable improvements over previous work.
The prevailing paradigm for producing semantic segmentation training data relies on densely labelling each pixel of each image in the training set, akin to colouring-in books. This approach becomes a bottleneck when scaling up in the number of images, classes, and annotators. Here we propose instead a pointillist approach for semantic segmentation annotation, where only point-wise yes/no questions are answered. We explore design alternatives for such an active learning approach, measure the speed and consistency of human annotators on this task, show that this strategy enables training good segmentation models, and that it is suitable for evaluating models at test time. As concrete proof of the scalability of our method, we collected and released 22.6M point labels over 4,171 classes on the Open Images dataset. Our results enable to rethink the semantic segmentation pipeline of annotation, training, and evaluation from a pointillism point of view.
With the recent successful adaptation of transformers to the vision domain, particularly when trained in a self-supervised fashion, it has been shown that vision transformers can learn impressive object-reasoning-like behaviour and features expressive for the task of object segmentation in images. In this paper, we build on the self-supervision task of masked autoencoding and explore its effectiveness for explicitly learning object-centric representations with transformers. To this end, we design an object-centric autoencoder using transformers only and train it end-to-end to reconstruct full images from unmasked patches. We show that the model efficiently learns to decompose simple scenes as measured by segmentation metrics on several multi-object benchmarks.
In this paper, we propose a new approach to applying point-level annotations for weakly-supervised panoptic segmentation. Instead of the dense pixel-level labels used by fully supervised methods, point-level labels only provide a single point for each target as supervision, significantly reducing the annotation burden. We formulate the problem in an end-to-end framework by simultaneously generating panoptic pseudo-masks from point-level labels and learning from them. To tackle the core challenge, i.e., panoptic pseudo-mask generation, we propose a principled approach to parsing pixels by minimizing pixel-to-point traversing costs, which model semantic similarity, low-level texture cues, and high-level manifold knowledge to discriminate panoptic targets. We conduct experiments on the Pascal VOC and the MS COCO datasets to demonstrate the approach's effectiveness and show state-of-the-art performance in the weakly-supervised panoptic segmentation problem. Codes are available at https://github.com/BraveGroup/PSPS.git.
Colorectal cancer (CRC) is the second leading cause of cancer-related death worldwide. Excision of polyps during colonoscopy helps reduce mortality and morbidity for CRC. Powered by deep learning, computer-aided diagnosis (CAD) systems can detect regions in the colon overlooked by physicians during colonoscopy. Lacking high accuracy and real-time speed are the essential obstacles to be overcome for successful clinical integration of such systems. While literature is focused on improving accuracy, the speed parameter is often ignored. Toward this critical need, we intend to develop a novel real-time deep learning-based architecture, DilatedSegNet, to perform polyp segmentation on the fly. DilatedSegNet is an encoder-decoder network that uses pre-trained ResNet50 as the encoder from which we extract four levels of feature maps. Each of these feature maps is passed through a dilated convolution pooling (DCP) block. The outputs from the DCP blocks are concatenated and passed through a series of four decoder blocks that predicts the segmentation mask. The proposed method achieves a real-time operation speed of 33.68 frames per second with an average dice coefficient of 0.90 and mIoU of 0.83. Additionally, we also provide heatmap along with the qualitative results that shows the explanation for the polyp location, which increases the trustworthiness of the method. The results on the publicly available Kvasir-SEG and BKAI-IGH datasets suggest that DilatedSegNet can give real-time feedback while retaining a high \ac{DSC}, indicating high potential for using such models in real clinical settings in the near future. The GitHub link of the source code can be found here: \url{https://github.com/nikhilroxtomar/DilatedSegNet}.
Performance measures are an important tool for assessing and comparing different medical image segmentation algorithms. Unfortunately, the current measures have their weaknesses when it comes to assessing certain edge cases. These limitations arouse when images with a very small region of interest or without a region of interest at all are assessed. As a solution for these limitations, we propose a new medical image segmentation metric: MISm. To evaluate MISm, the popular metrics in the medical image segmentation and MISm were compared using images of magnet resonance tomography from several scenarios. In order to allow application in the community and reproducibility of experimental results, we included MISm in the publicly available evaluation framework MISeval: https://github.com/frankkramer-lab/miseval/tree/master/miseval
We consider a monopolistic seller in a market that may be segmented. The surplus of each consumer in a segment depends on the price that the seller optimally charges, which depends on the set of consumers in the segment. We study which segmentations may result from the interaction among consumers and the seller. Instead of studying the interaction as a non-cooperative game, we take a reduced-form approach and introduce a notion of stability that any resulting segmentation must satisfy. A stable segmentation is one that, for any alternative segmentation, contains a segment of consumers that prefers the original segmentation to the alternative one. Our main result characterizes stable segmentations as efficient and saturated. A segmentation is saturated if no consumers can be shifted from a segment with a high price to a segment with a low price without the seller optimally increasing the low price. We use this characterization to constructively show that stable segmentations always exist. Even though stable segmentations are efficient, they need not maximize average consumer surplus, and segmentations that maximize average consumer surplus need not be stable. Finally, we relate our notion of stability to solution concepts from cooperative game theory and show that stable segmentations satisfy many of them.
For real-life applications, it is crucial that end-to-end spoken language translation models perform well on continuous audio, without relying on human-supplied segmentation. For online spoken language translation, where models need to start translating before the full utterance is spoken, most previous work has ignored the segmentation problem. In this paper, we compare various methods for improving models' robustness towards segmentation errors and different segmentation strategies in both offline and online settings and report results on translation quality, flicker and delay. Our findings on five different language pairs show that a simple fixed-window audio segmentation can perform surprisingly well given the right conditions.
Recent mainstream weakly-supervised semantic segmentation (WSSS) approaches mainly relies on image-level classification learning, which has limited representation capacity. In this paper, we propose a novel semantic learning based framework, named SLAMs (Semantic Learning based Activation Map), for WSSS.
Medical image segmentation is an actively studied task in medical imaging, where the precision of the annotations is of utter importance towards accurate diagnosis and treatment. In recent years, the task has been approached with various deep learning systems, among the most popular models being U-Net. In this work, we propose a novel strategy to generate ensembles of different architectures for medical image segmentation, by leveraging the diversity (decorrelation) of the models forming the ensemble. More specifically, we utilize the Dice score among model pairs to estimate the correlation between the outputs of the two models forming each pair. To promote diversity, we select models with low Dice scores among each other. We carry out gastro-intestinal tract image segmentation experiments to compare our diversity-promoting ensemble (DiPE) with another strategy to create ensembles based on selecting the top scoring U-Net models. Our empirical results show that DiPE surpasses both individual models as well as the ensemble creation strategy based on selecting the top scoring models.
The Coronavirus Disease 2019 (COVID-19) pandemic has increased the public health burden and brought profound disaster to humans. For the particularity of the COVID-19 medical images with blurred boundaries, low contrast and different infection sites, some researchers have improved the accuracy by adding more complexity. Also, they overlook the complexity of lesions, which hinder their ability to capture the relationship between segmentation sites and the background, as well as the edge contours and global context. However, increasing the computational complexity, parameters and inference speed is unfavorable for model transfer from laboratory to clinic. A perfect segmentation network needs to balance the above three factors completely. To solve the above issues, this paper propose a symmetric automatic segmentation framework named MS-DCANet. We introduce Tokenized MLP block, a novel attention scheme that use a shift-window mechanism to conditionally fuse local and global features to get more continuous boundaries and spatial positioning capabilities. It has greater understanding of irregular lesions contours. MS-DCANet also uses several Dual Channel blocks and a Res-ASPP block to improve the ability to recognize small targets. On multi-modality COVID-19 tasks, MS-DCANet achieved state-of-the-art performance compared with other baselines. It can well trade off the accuracy and complexity. To prove the strong generalization ability of our proposed model, we apply it to other tasks (ISIC 2018 and BAA) and achieve satisfactory results.
Visual inspection is the predominant technique for evaluating the condition of civil infrastructure. The recent advances in unmanned aerial vehicles (UAVs) and artificial intelligence have made the visual inspections faster, safer, and more reliable. Camera-equipped UAVs are becoming the new standard in the industry by collecting massive amounts of visual data for human inspectors. Meanwhile, there has been significant research on autonomous visual inspections using deep learning algorithms, including semantic segmentation. While UAVs can capture high-resolution images of buildings' fa\c{c}ades, high-resolution segmentation is extremely challenging due to the high computational memory demands. Typically, images are uniformly downsized at the price of losing fine local details. Contrarily, breaking the images into multiple smaller patches can cause a loss of global contextual in-formation. We propose a hybrid strategy that can adapt to different inspections tasks by managing the global and local semantics trade-off. The framework comprises a compound, high-resolution deep learning architecture equipped with an attention-based segmentation model and learnable downsampler-upsampler modules designed for optimal efficiency and in-formation retention. The framework also utilizes vision transformers on a grid of image crops aiming for high precision learning without downsizing. An augmented inference technique is used to boost the performance and re-duce the possible loss of context due to grid cropping. Comprehensive experiments have been performed on 3D physics-based graphics models synthetic environments in the Quake City dataset. The proposed framework is evaluated using several metrics on three segmentation tasks: component type, component damage state, and global damage (crack, rebar, spalling).
Multi-organ segmentation enables organ evaluation, accounts the relationship between multiple organs, and facilitates accurate diagnosis and treatment decisions. However, only few models can perform segmentation accurately because of the lack of datasets and computational resources. On AMOS2022 challenge, which is a large-scale, clinical, and diverse abdominal multiorgan segmentation benchmark, we trained a 3D-UNet model with large batch and patch sizes using multi-GPU distributed training. Segmentation performance tended to increase for models with large batch and patch sizes compared with the baseline settings. The accuracy was further improved by using ensemble models that were trained with different settings. These results provide a reference for parameter selection in organ segmentation.
Cancer of the brain is deadly and requires careful surgical segmentation. The brain tumors were segmented using U-Net using a Convolutional Neural Network (CNN). When looking for overlaps of necrotic, edematous, growing, and healthy tissue, it might be hard to get relevant information from the images. The 2D U-Net network was improved and trained with the BraTS datasets to find these four areas. U-Net can set up many encoder and decoder routes that can be used to get information from images that can be used in different ways. To reduce computational time, we use image segmentation to exclude insignificant background details. Experiments on the BraTS datasets show that our proposed model for segmenting brain tumors from MRI (MRI) works well. In this study, we demonstrate that the BraTS datasets for 2017, 2018, 2019, and 2020 do not significantly differ from the BraTS 2019 dataset's attained dice scores of 0.8717 (necrotic), 0.9506 (edema), and 0.9427 (enhancing).
Accurate segmentation of organelle instances, e.g., mitochondria, is essential for electron microscopy analysis. Despite the outstanding performance of fully supervised methods, they highly rely on sufficient per-pixel annotated data and are sensitive to domain shift. Aiming to develop a highly annotation-efficient approach with competitive performance, we focus on weakly-supervised domain adaptation (WDA) with a type of extremely sparse and weak annotation demanding minimal annotation efforts, i.e., sparse point annotations on only a small subset of object instances. To reduce performance degradation arising from domain shift, we explore multi-level transferable knowledge through conducting three complementary tasks, i.e., counting, detection, and segmentation, constituting a task pyramid with different levels of domain invariance. The intuition behind this is that after investigating a related source domain, it is much easier to spot similar objects in the target domain than to delineate their fine boundaries. Specifically, we enforce counting estimation as a global constraint to the detection with sparse supervision, which further guides the segmentation. A cross-position cut-and-paste augmentation is introduced to further compensate for the annotation sparsity. Extensive validations show that our model with only 15% point annotations can achieve comparable performance as supervised models and shows robustness to annotation selection.
Iris Recognition (IR) is one of the market's most reliable and accurate biometric systems. Today, it is challenging to build NIR-capturing devices under the premise of hardware price reduction. Commercial NIR sensors are protected from modification. The process of building a new device is not trivial because it is required to start from scratch with the process of capturing images with quality, calibrating operational distances, and building lightweight software such as eyes/iris detectors and segmentation sub-systems. In light of such challenges, this work aims to develop and implement iris recognition software in an embedding system and calibrate NIR in a contactless binocular setup. We evaluate and contrast speed versus performance obtained with two embedded computers and infrared cameras. Further, a lightweight segmenter sub-system called "Unet_xxs" is proposed, which can be used for iris semantic segmentation under restricted memory resources.
U-Net and its extensions have achieved great success in medical image segmentation. However, due to the inherent local characteristics of ordinary convolution operations, U-Net encoder cannot effectively extract global context information. In addition, simple skip connections cannot capture salient features. In this work, we propose a fully convolutional segmentation network (CMU-Net) which incorporates hybrid convolutions and multi-scale attention gate. The ConvMixer module extracts global context information by mixing features at distant spatial locations. Moreover, the multi-scale attention gate emphasizes valuable features and achieves efficient skip connections. We evaluate the proposed method using both breast ultrasound datasets and a thyroid ultrasound image dataset; and CMU-Net achieves average Intersection over Union (IoU) values of 73.27% and 84.75%, and F1 scores of 84.81% and 91.71%. The code is available at https://github.com/FengheTan9/CMU-Net.
An automated segmentation and classification of nuclei is an essential task in digital pathology. The current deep learning-based approaches require a vast amount of annotated datasets by pathologists. However, the existing datasets are imbalanced among different types of nuclei in general, leading to a substantial performance degradation. In this paper, we propose a simple but effective data augmentation technique, termed GradMix, that is specifically designed for nuclei segmentation and classification. GradMix takes a pair of a major-class nucleus and a rare-class nucleus, creates a customized mixing mask, and combines them using the mask to generate a new rare-class nucleus. As it combines two nuclei, GradMix considers both nuclei and the neighboring environment by using the customized mixing mask. This allows us to generate realistic rare-class nuclei with varying environments. We employed two datasets to evaluate the effectiveness of GradMix. The experimental results suggest that GradMix is able to improve the performance of nuclei segmentation and classification in imbalanced pathology image datasets.
This report describes the winning solution to the Robust Vision Challenge (RVC) semantic segmentation track at ECCV 2022. Our method adopts the FAN-B-Hybrid model as the encoder and uses SegFormer as the segmentation framework. The model is trained on a composite dataset consisting of images from 9 datasets (ADE20K, Cityscapes, Mapillary Vistas, ScanNet, VIPER, WildDash 2, IDD, BDD, and COCO) with a simple dataset balancing strategy. All the original labels are projected to a 256-class unified label space, and the model is trained using a cross-entropy loss. Without significant hyperparameter tuning or any specific loss weighting, our solution ranks the first place on all the testing semantic segmentation benchmarks from multiple domains (ADE20K, Cityscapes, Mapillary Vistas, ScanNet, VIPER, and WildDash 2). The proposed method can serve as a strong baseline for the multi-domain segmentation task and benefit future works. Code will be available at https://github.com/lambert-x/RVC_Segmentation.