Binarized Encoder-Decoder Network and Binarized Deconvolution Engine for Semantic Segmentation

Recent advances in convolutional neural networks have led to considerably accurate semantic segmentation tasks. However, previous works use a pre-trained backbone borrowed from image classification tasks with considerable computational complexity, resulting in large latencies. Many methods have been proposed to reduce the latency of the segmentation network without loss of accuracy. These methods have reported varying experimental results with different computing devices, acceleration techniques, and input image sizes. Although most studies claim that their results are state-of-the-art, it is necessary to reconsider whether they are being compared under the same conditions. We propose a performance evaluation method of real-time semantic segmentation models to compare the performance under the same conditions fairly. In addition, we carry out an empirical study to evaluate the performance of recent real-time semantic segmentation networks and make a comparative analysis between them. We train the segmentation models using the same input data and data augmentation method. Then, the performance of the segmentation methods is analyzed regarding accuracy and speed. In contrast to most studies that exclude the time required for the pre-processing and post-processing steps, we measured the actual processing time needed to perform semantic segmentation with a real dataset. Further, we measured the processing speed and power consumption of the segmentation models in embedded devices in which real-time segmentation is applied, unlike previous studies that measured performance on a PC. Experimental results showed that the real-time semantic segmentation methods could not run in real-time on embedded devices when considering the pre-processing and post-processing steps. By comprehensively considering the inference speed, energy consumption, and processing time of semantic segmentation models, the experimental results show that FasterSeg-S is suited for embedded devices.

With the growing demands of applications on online devices, the speed-accuracy trade-off is critical in the semantic segmentation system. Recently, the bilateral segmentation network has shown promising capacity to achieve the balance between favorable accuracy and fast speed, and has become the mainstream backbone in real-time semantic segmentation. Segmentation of target objects relies on high-level semantics, whereas it requires detailed low-level features to model specific local patterns for accurate location. However, the lightweight backbone of bilateral architecture limits the extraction of semantic context and spatial details. And the late fusion of the bilateral streams incurs the insufficient aggregation of semantic context and spatial details. In this article, we propose a densely aggregated bilateral network (DAB-Net) for real-time semantic segmentation. In the context path, a patchwise context enhancement (PCE) module is proposed to efficiently capture the local semantic contextual information from spatialwise and channelwise, respectively. Meanwhile, a context-guided spatial path (CGSP) is designed to exploit more spatial information by encoding finer details from the raw image and the transition from the context path. Finally, with multiple interactions between bilateral branches, the intertwined outputs from bilateral streams are combined in a unified decoder for a final interaction to further enhance the feature representation, which generates the final segmentation prediction. Experimental results on three public benchmarks demonstrate that our proposed method achieves higher accuracy with a limited decay in speed, which performs favorably against state-of-the-art real-time approaches and runs at 31.1 frames/s (FPS) on the high resolution of [Formula: see text] . The source code is released at https://github.com/isyangshu/DABNet.

In a previous paper, we introduced a deep learning neural network that should be able to detect the existence of very shallow periodic planetary transits in the presence of red noise. The network in that feasibility study would not provide any further details about the detected transits. The current paper completes this missing part. We present a neural network that tags samples that were obtained during transits. This is essentially similar to the task of identifying the semantic context of each pixel in an image—an important task in computer vision, called “semantic segmentation,” which is often performed by deep neural networks. The neural network we present makes use of novel deep learning concepts such as U-Nets, Generative Adversarial Networks, and adversarial loss. The resulting segmentation should allow further studies of the light curves that are tagged as containing transits. This approach toward the detection and study of very shallow transits is bound to play a significant role in future space-based transit surveys such as PLATO, which are specifically aimed to detect those extremely difficult cases of long-period shallow transits. Our segmentation network also adds to the growing toolbox of deep learning approaches that are being increasingly used in the study of exoplanets; but, so far mainly for vetting transits, rather than their initial detection.

In recent years, deep learning has achieved good results in the semantic segmentation of medical images. A typical architecture for segmentation networks is an encoder-decoder structure. However, the design of the segmentation networks is fragmented and lacks a mathematical explanation. Consequently, segmentation networks are inefficient and less generalizable across different organs. To solve these problems, we reconstructed the segmentation network based on mathematical methods. We introduced the dynamical systems view into semantic segmentation and proposed a novel segmentation network based on Runge-Kutta methods, referred to hereafter as the Runge-Kutta segmentation network (RKSeg). RKSegs were evaluated on ten organ image datasets from the Medical Segmentation Decathlon. The experimental results show that RKSegs far outperform other segmentation networks. RKSegs use few parameters and short inference time, yet they can achieve competitive or even better segmentation results compared to other models. RKSegs pioneer a new architectural design pattern for segmentation networks.

Semantic segmentation methods based on deep neural networks have achieved great success in recent years. However, training such deep neural networks relies heavily on a large number of images with accurate pixel-level labels, which requires a huge amount of human effort, especially for large-scale remote sensing images. In this paper, we propose a point-based weakly supervised learning framework called the deep bilateral filtering network (DBFNet) for the semantic segmentation of remote sensing images. Compared with pixel-level labels, point annotations are usually sparse and cannot reveal the complete structure of the objects; they also lack boundary information, thus resulting in incomplete prediction within the object and the loss of object boundaries. To address these problems, we incorporate the bilateral filtering technique into deeply learned representations in two respects. First, since a target object contains smooth regions that always belong to the same category, we perform deep bilateral filtering (DBF) to filter the deep features by a nonlinear combination of nearby feature values, which encourages the nearby and similar features to become closer, thus achieving a consistent prediction in the smooth region. In addition, the DBF can distinguish the boundary by enlarging the distance between the features on different sides of the edge, thus preserving the boundary information well. Experimental results on two widely used datasets, the ISPRS 2-D semantic labeling Potsdam and Vaihingen datasets, demonstrate that our proposed DBFNet can achieve a highly competitive performance compared with state-of-the-art fully-supervised methods. Code is available at https://github.com/Luffy03/DBFNet.

Real-time semantic segmentation is widely used in autonomous driving and robotics. Most previous networks achieved great accuracy based on a complicated model involving mass computing. The existing lightweight networks generally reduce the parameter sizes by sacrificing the segmentation accuracy. It is critical to balance the parameters and accuracy for real-time semantic segmentation. In this article, we propose a lightweight multiscale-feature-fusion network (LMFFNet) mainly composed of three types of components: split-extract-merge bottleneck (SEM-B) block, feature fusion module (FFM), and multiscale attention decoder (MAD), where the SEM-B block extracts sufficient features with fewer parameters. FFMs fuse multiscale semantic features to effectively improve the segmentation accuracy and the MAD well recovers the details of the input images through the attention mechanism. Without pretraining, LMFFNet-3-8 achieves 75.1% mean intersection over union (mIoU) with 1.4 M parameters at 118.9 frames/s using RTX 3090 GPU. More experiments are investigated extensively on various resolutions on other three datasets of CamVid, KITTI, and WildDash2. The experiments verify that the proposed LMFFNet model makes a decent tradeoff between segmentation accuracy and inference speed for real-time tasks. The source code is publicly available at https://github.com/Greak-1124/LMFFNet.

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.

Synthetic Aperture Radar (SAR) imagery have been one of the important tools to support earth observations and topographic measurements. It means SAR imagery are essentially rich in structures and some important target categories are difficult to recognize. Optical imagery contains rich and clear spectral information which has a good influence on semantic image segmentation. The success of deep neural networks for semantic segmentation heavily depends on large-scale and well-labeled data sets, which are hard to collect in practice. In this paper, we consider deep transfer learning for semantic segmentation, we propose a deep novel transfer learning method, which transfers a semantically segment model from SAR imagery to SAR and optical fusion imagery. The experimental results show that the method proposed achieves higher mean Intersection over Union (mIoU) with less training time compared with other methods.

Semantic segmentation is a fundamental capability for autonomous vehicles. With the advancements of deep learning technologies, many effective semantic segmentation networks have been proposed in recent years. However, most of them are designed using RGB images from visible cameras. The quality of RGB images is prone to be degraded under unsatisfied lighting conditions, such as darkness and glares of oncoming headlights, which imposes critical challenges for the networks that use only RGB images. Different from visible cameras, thermal imaging cameras generate images using thermal radiations. They are able to see under various lighting conditions. In order to enable robust and accurate semantic segmentation for autonomous vehicles, we take the advantage of thermal images and fuse both the RGB and thermal information in a novel deep neural network. The main innovation of this letter is the architecture of the proposed network. We adopt the encoder–decoder design concept. ResNet is employed for feature extraction and a new decoder is developed to restore the feature map resolution. The experimental results prove that our network outperforms the state of the arts.

<div class="section abstract"><div class="htmlview paragraph">Traditional Simultaneous Localization and Mapping (SLAM) methods often assume static environments. This limitation can lead to inaccurate localization or even the loss of tracking in dynamic scenes. To address this issue, we propose a novel SLAM approach specifically designed for dynamic environments. Our method integrates the real-time image semantic segmentation network BisenetV2 with inter-frame and continuous multi-frame motion feature detection. Firstly, semantic segmentation is applied to render the semantic mask, which is then used by the inter-frame motion detection module to identify potential motion features. Subsequently, these suspected motion features are evaluated by a likelihood probability model across consecutive frames. Finally, points with a high probability of motion are monitored in real-time by the Luenberger observer, which filters out motion features and re-adds static ones. Our experiments demonstrate that semantic segmentation can meet real-time requirements in various scenarios. Evaluations of the TUM-RGBD dataset and simulation experiment show that our proposed method significantly improves SLAM accuracy and robustness in dynamic scenes.</div></div>

Semantic segmentation is a crucial approach for remote sensing interpretation. High-precision semantic segmentation results are obtained at the cost of manually collecting massive pixelwise annotations. Remote sensing imagery contains complex and variable ground objects and obtaining abundant manual annotations is expensive and arduous. The semi-supervised learning (SSL) strategy can enhance the generalization capability of a model with a small number of labeled samples. In this study, a novel semi-supervised adversarial semantic segmentation network is developed for remote sensing information extraction. A multiscale input convolution module (MICM) is designed to extract sufficient local features, while a Transformer module (TM) is applied for long-range dependency modeling. These modules are integrated to construct a segmentation network with a double-branch encoder. Additionally, a double-branch discriminator network with different convolution kernel sizes is proposed. The segmentation network and discriminator network are jointly trained under the semi-supervised adversarial learning (SSAL) framework to improve its segmentation accuracy in cases with small amounts of labeled data. Taking building extraction as a case study, experiments on three datasets with different resolutions are conducted to validate the proposed network. Semi-supervised semantic segmentation models, in which DeepLabv2, the pyramid scene parsing network (PSPNet), UNet and TransUNet are taken as backbone networks, are utilized for performance comparisons. The results suggest that the approach effectively improves the accuracy of semantic segmentation. The F1 and mean intersection over union (mIoU) accuracy measures are improved by 0.82–11.83% and 0.74–7.5%, respectively, over those of other methods.

Visual semantic segmentation, which is represented by the semantic segmentation network, has been widely used in many fields, such as intelligent robots, security, and autonomous driving. However, these Convolutional Neural Network (CNN)-based networks have high requirements for computing resources and programmability for hardware platforms. For embedded platforms and terminal devices in particular, Graphics Processing Unit (GPU)-based computing platforms cannot meet these requirements in terms of size and power consumption. In contrast, the Field Programmable Gate Array (FPGA)-based hardware system not only has flexible programmability and high embeddability, but can also meet lower power consumption requirements, which make it an appropriate solution for semantic segmentation on terminal devices. In this paper, we demonstrate EDSSA—an Encoder-Decoder semantic segmentation networks accelerator architecture which can be implemented with flexible parameter configurations and hardware resources on the FPGA platforms that support Open Computing Language (OpenCL) development. We introduce the related technologies, architecture design, algorithm optimization, and hardware implementation of the Encoder-Decoder semantic segmentation network SegNet as an example, and undertake a performance evaluation. Using an Intel Arria-10 GX1150 platform for evaluation, our work achieves a throughput higher than 432.8 GOP/s with power consumption of about 20 W, which is a 1.2× times improvement the energy-efficiency ratio compared to a high-performance GPU.

Semantic segmentation is a fundamental task in remote sensing image understanding. Recently, Deep Convolutional Neural Networks (DCNNs) have considerably improved the performance of the semantic segmentation of natural scenes. However, it is still challenging for very high-resolution remote sensing images. Due to the large and complex scenes as well as the influence of illumination and imaging angle, it is particularly difficult for the existing methods to accurately obtain the category of pixels at object boundaries—the so-called boundary blur. We propose a framework called Boundary-Aware Semi-Supervised Semantic Segmentation Network (BAS <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">4</sup> Net), which obtains more accurate segmentation results without additional annotation workload, especially at the object boundaries. The Channel-weighted Multi-scale Feature (CMF) module balances semantic and spatial information, and the Boundary Attention Module (BAM) weights the features with rich semantic boundary information to alleviate the boundary blur. Additionally, to decrease the amount of difficult and tedious manual labeling of remote sensing images, a discriminator network infers pseudolabels from unlabeled images to assist semisupervised learning, and further improves the performance of the segmentation network. To validate the effectiveness of the proposed framework, extensive experiments have been performed on both the ISPRS Vaihingen dataset, and the novel remote sensing dataset AIR-SEG with more categories, and complex boundaries. The results demonstrate a significant improvement of accuracy especially on boundaries and for small objects.

Semantic segmentation is a key technique involved in automatic interpretation of high-resolution remote sensing (HRS) imagery and has drawn much attention in the remote sensing community. Deep convolutional neural networks (DCNNs) have been successfully applied to the HRS imagery semantic segmentation task due to their hierarchical representation ability. However, the heavy dependency on a large number of training data with dense annotation and the sensitiveness to the variation of data distribution severely restrict the potential application of DCNNs for the semantic segmentation of HRS imagery. This study proposes a novel unsupervised domain adaptation semantic segmentation network (MemoryAdaptNet) for the semantic segmentation of HRS imagery. MemoryAdaptNet constructs an output space adversarial learning scheme to bridge the domain distribution discrepancy between source domain and target domain and to narrow the influence of domain shift. Specifically, we embed an invariant feature memory module to store invariant domain-level context information because the features obtained from adversarial learning only tend to represent the variant feature of current limited inputs. This module is integrated by a category attention-driven invariant domain-level context aggregation module to current pseudo invariant feature for further augmenting the pixel representations. An entropy-based pseudo label filtering strategy is used to update the memory module with high-confident pseudo invariant feature of current target images. Extensive experiments under three cross-domain tasks indicate that our proposed MemoryAdaptNet is remarkably superior to the state-of-the-art methods.

Detecting oil palm plantation from high-resolution satellite images can provide the necessary information for palm oil production estimation and oil palm plantation layout planning, etc. In this paper, we proposed a novel semantic segmentation based approach for large-scale oil palm plantation detection using QuickBird images and Google Earth Images (in 0.6-m spatial resolution) in Malaysia. We manually labeled a dataset for pixel-wise semantic segmentation into four categories: oil palm plantation, other vegetation, impervious/cloud, and the others (e.g. water and uncertain pixels). We presented an end-to-end deep convolutional neural network (DCNN) for semantic segmentation followed by fully connected conditional random fields (CRF) and applied an ensemble learning method to improve the localization of boundaries. The overall accuracy and mean IoU of our proposed approach in test regions are 95.27% and 88.46%, which are greatly better than the results of the other three common semantic segmentation methods and patch-based CNN method.