Semantic segmentation of pendet dance images using multires U-Net architecture

Chapter 12 - Semantic scene segmentation for robotics

Semantic segmentation is a classical task in computer vision. In this paper, we target to address the low confidence regions which traditional CNN can not solve very well in semantic segmentation task. Depending on different characteristics of low confidence regions, an adaptive and robust attention mechanism is important to focus on the informative regions but ignore the noisy parts in the image. Intuitively, one attention map only is not sufficient to model the interaction between the low confidence regions and its surrounding patches. Thus, in this paper, we propose an Attention Forest structure, a novel and robust attention mechanism, to handle the low confidence regions. Each Attention Tree structure can capture more interactions between current patches with its adjacent regions. Experiments on PASCAL VOC 2012 Dataset validate the effectiveness of our proposed algorithm.

The balance between high accuracy and high speed has always been a challenging task in semantic image segmentation. Compact segmentation networks are more widely used in the case of limited resources, while their performances are constrained. In this paper, motivated by the residual learning and global aggregation, we propose a simple yet general and effective knowledge distillation framework called double similarity distillation (DSD) to improve the classification accuracy of all existing compact networks by capturing the similarity knowledge in pixel and category dimensions, respectively. Specifically, we propose a pixel-wise similarity distillation (PSD) module that utilizes residual attention maps to capture more detailed spatial dependencies across multiple layers. Compared with exiting methods, the PSD module greatly reduces the amount of calculation and is easy to expand. Furthermore, considering the differences in characteristics between semantic segmentation task and other computer vision tasks, we propose a category-wise similarity distillation (CSD) module, which can help the compact segmentation network strengthen the global category correlation by constructing the correlation matrix. Combining these two modules, DSD framework has no extra parameters and only a minimal increase in FLOPs. Extensive experiments on four challenging datasets, including Cityscapes, CamVid, ADE20K, and Pascal VOC 2012, show that DSD outperforms current state-of-the-art methods, proving its effectiveness and generality. The code and models will be publicly available.

The field of continual deep learning is an emerging field and a lot of progress has been made. However, concurrently most of the approaches are only tested on the task of image classification, which is not relevant in the field of intelligent vehicles. Only recently approaches for class-incremental semantic segmentation were proposed. However, all of those approaches are based on some form of knowledge distillation. At the moment there are no investigations on replay-based approaches that are commonly used for object recognition in a continual setting. At the same time while unsupervised domain adaption for semantic segmentation gained a lot of traction, investigations regarding domain-incremental learning in an continual setting is not well-studied. Therefore, the goal of our work is to evaluate and adapt established solutions for continual object recognition to the task of semantic segmentation and to provide baseline methods and evaluation protocols for the task of continual semantic segmentation. We firstly introduce evaluation protocols for the class- and domain-incremental segmentation and analyze selected approaches. We show that the nature of the task of semantic segmentation changes which methods are most effective in mitigating forgetting compared to image classification. Especially, in class-incremental learning knowledge distillation proves to be a vital tool, whereas in domain-incremental learning replay methods are the most effective method.

Panoptic Segmentation aims to provide an understanding of background (stuff) and instances of objects (things) at a pixel level. It combines the separate tasks of semantic segmentation (pixel level classification) and instance segmentation to build a single unified scene understanding task. Typically, panoptic segmentation is derived by combining semantic and instance segmentation tasks that are learned separately or jointly (multi-task networks). In general, instance segmentation networks are built by adding a foreground mask estimation layer on top of object detectors or using instance clustering methods that assign a pixel to an instance center. In this work, we present a fully convolution neural network that learns instance segmentation from semantic segmentation and instance contours (boundaries of things). Instance contours along with semantic segmentation yield a boundary aware semantic segmentation of things. Connected component labeling on these results produces instance segmentation. We merge semantic and instance segmentation results to output panoptic segmentation. We evaluate our proposed method on the CityScapes dataset to demonstrate qualitative and quantitative performances along with several ablation studies. Our overview video can be accessed from https://youtu.be/wBtcxRhG3e0.

Semantic image segmentation is an interesting problem in Computer Vision with many potential applications. The DeepLab model is combined with two other networks: Resnet and Conditional Random Field networks, making the DeepLab model a fairly deep network structure to increase semantic segmentation performance. Many previous studies argued that there are some limits on the deep learning model's depth as the deep structure may lead to vanishing/exploding gradient, which the model's performance. This paper presents an experimental study to compare the effect of several ImageNet pre-trained Resnet variant models with different network layers used as feature extractor in DeepLab model to solve semantic image segmentation task. In this study, three Resnet34, Resnet50, and Resnet101 models as network extractor of DeepLabV3were explored. The experiment found that semantic image segmentation model performance measured by the best accuracy and average accuracies of DeepLabV3- Resnet34, DeepLabV3-Resnet50, and DeepLabV3-Resnet101 are (0.87, 0.86) (0.86, 0.84), and (0.92, 0.88) respectively. Based on the experiment, DeepLabV3-Resnet101 achieved the best semantic segmentation performance than the other models

Face recognition has been one of the most studied researches in computer vision, and facial feature extraction, is one of the cores of face recognition. In this paper, we focus on semantic segmentation methods for facial feature extraction. However, the structure and number of parameters of the model usually affect the accuracy of semantic segmentation tasks in facial feature extraction. High-resolution representation learning can bring better accuracy to semantic segmentation, and large convolutional kernels, which bring a larger effective receptive field and better shape feature extraction to the model, can also improve the performance of the segmentation model. In this paper, we propose a novel lightweight model, HRModel (HRM), for optimizing the accuracy and parameters of semantic segmentation tasks in face recognition. From the perspective of multi-scale fusion, large perceptual fields, and gradient segmentation using high-resolution parallel streaming networks as a framework, we use a multi-scale feature extraction module with a large convolutional kernel to reduce the number of parameters while maintaining accuracy. In the feature extraction block, we use a channel attention mechanism to aggregate feature maps of different depths and different receptive fields. At the same time, we apply depthwise separable convolution and gradient flow splitting to reuse the gradient information and hence reduce the number of parameters and computational effort of the network effectively. We compare our proposed model HRM with other single-model networks on semantic segmentation tasks for face recognition. The experimental results show that HRM significantly reduces the number of parameters and achieves an accuracy of 95.52% in the application of the CelebAMask-HQ dataset.

<p class="VARAbstract">The growing availability of three-dimensional (3D) data, such as point clouds, coming from Light Detection and Ranging (LiDAR), Mobile Mapping Systems (MMSs) or Unmanned Aerial Vehicles (UAVs), provides the opportunity to rapidly generate 3D models to support the restoration, conservation, and safeguarding activities of cultural heritage (CH). The so-called scan-to-BIM process can, in fact, benefit from such data, and they can themselves be a source for further analyses or activities on the archaeological and built heritage. There are several ways to exploit this type of data, such as Historic Building Information Modelling (HBIM), mesh creation, rasterisation, classification, and semantic segmentation. The latter, referring to point clouds, is a trending topic not only in the CH domain but also in other fields like autonomous navigation, medicine or retail. Precisely in these sectors, the task of semantic segmentation has been mainly exploited and developed with artificial intelligence techniques. In particular, machine learning (ML) algorithms, and their deep learning (DL) subset, are increasingly applied and have established a solid state-of-the-art in the last half-decade. However, applications of DL techniques on heritage point clouds are still scarce; therefore, we propose to tackle this framework within the built heritage field. Starting from some previous tests with the Dynamic Graph Convolutional Neural Network (DGCNN), in this contribution close attention is paid to: i) the investigation of fine-tuned models, used as a transfer learning technique, ii) the combination of external classifiers, such as Random Forest (RF), with the artificial neural network, and iii) the evaluation of the data augmentation results for the domain-specific ArCH dataset. Finally, after taking into account the main advantages and criticalities, considerations are made on the possibility to profit by this methodology also for non-programming or domain experts.</p><p>Highlights:</p><ul><li><p>Semantic segmentation of built heritage point clouds through deep neural networks can provide performances comparable to those of more consolidated state-of-the-art ML classifiers.</p></li><li><p>Transfer learning approaches, as fine-tuning, can considerably reduce computational time also for CH domain-specific datasets, as well as improve metrics for some challenging categories (i.e. windows or mouldings).</p></li><li><p>Data augmentation techniques do not significantly improve overall performances.</p></li></ul>

Nowadays, Intelligent Transportation System (ITS) has become one of the most popular subjects of scientific research. ITS provides innovative services to transport and traffic monitoring like vehicle segmentation and classification. Image understanding and object semantic segmentation in traffic scenes is a very important topic in the trend of autonomous driving issues, like autonomous vehicles and robotics. Actually, Deep Convolution Neural Network (CNN) architectures have given very good results and good performance in computer vision tasks such as classification, object detection, and segmentation. In this scope, we can distinguish two modes of CNN training, the pre-trained model and the training from scratch. In fact, deep neural network training without pre-trained weights and little data requires more training iterations. Besides, deeper models are more efficient than their shallow counterparts for the task of semantic segmentation. In this paper, we will make a comparative study between many deep CNNs models that can train the CNN model from scratch on small datasets, in addition, we will use data augmentation techniques. Extensive experiments were performed on the MiniCity urban scene dataset to prove the effectiveness of the used neural networks while obtaining promising results.

Vision Foundation Models (VFMs), while powerful, often struggle in Remote Sensing (RS) segmentation tasks when combined with existing Parameter-Efficient Fine-Tuning (PEFT) methods. We observe that this limitation primarily arises from their inability to effectively handle the pervasive artifacts in RS imagery. To address this, we introduce Earth-Adapter, the first PEFT method specifically designed for RS artifact mitigation. Earth-Adapter introduces a novel Frequency-Guided Mixture of Adapters (MoA) approach, structured around a ''divide and conquer" strategy. It first utilizes Discrete Fourier Transformation (DFT) to "divide" features into distinct frequency components, thereby effectively isolating artifact-related information from semantic signals. Subsequently, to ''conquer" these artifact, MoA independently optimizes features within different subspaces and dynamically assigns weights via a router to aggregate the refined representations. This enables adaptive refinement of the VFM’s representation space to mitigate the impact of artifacts. This simple yet highly effective PEFT method demonstrably mitigates artifacts and significantly enhances VFMs performance on RS segmentation tasks. Extensive experiments demonstrate Earth-Adapter's effectiveness on in-domain semantic segmentation (SS), as well as Domain Adaptive (DA) and Domain Generalized (DG) semantic segmentation tasks. Compared with the baseline Rein, Earth-Adapter significantly improves mIoU by 1.2% in SS, 9.0% in DA, and 3.1% in DG benchmarks. Our code and weights will be released soon.

Most of the current semantic segmentation approaches have achieved state-of-the-art performance relying on fully convolutional networks. However, the consecutive operations such as pooling or convolution striding lead to spatially disjointed object boundaries. We present a dense boundary regression architecture (DBRS2), which aims to use boundary cues to aid high-level semantic segmentation task. Specifically, we first propose a multilevel guided low-level boundary (MG-LB) learning method, where we exploit multilevel convolutional features as guidance for low-level boundary detection. The predicted MG-LB boundaries are used to enable consistent spatial grouping and enhance precise adherence to segment boundaries. Then, we present a significant global energy model based on boundary penalty and appearance penalty, which are respectively defined on the predicted boundaries and coarse segmentations obtained by the DeepLabv3 network. Finally, the refined segmentations are regressed by minimizing the global energy model. Extensive experiments over PASCAL VOC 2012, ADE20K, CamVid, and BSD500 datasets demonstrate that the proposed approach can obtain state-of-the-art performance on both semantic segmentation and boundary detection tasks.

In the human brain, the incoming light to the retina is transformed into meaningful representations that allow us to interact with the world. In a similar vein, the RGB pixel values are transformed by a deep neural network (DNN) into meaningful representations relevant to solving a computer vision task it was trained for. Therefore, in my research, I aim to reveal insights into the visual representations in the human visual cortex and DNNs solving vision tasks. In the previous decade, DNNs have emerged as the state-of-the-art models for predicting neural responses in the human and monkey visual cortex. Research has shown that training on a task related to a brain region’s function leads to better predictivity than a randomly initialized network. Based on this observation, we proposed that we can use DNNs trained on different computer vision tasks to identify functional mapping of the human visual cortex. To validate our proposed idea, we first investigate a brain region occipital place area (OPA) using DNNs trained on scene parsing task and scene classification task. From the previous investigations about OPA’s functions, we knew that it encodes navigational affordances that require spatial information about the scene. Therefore, we hypothesized that OPA’s representation should be closer to a scene parsing model than a scene classification model as the scene parsing task explicitly requires spatial information about the scene. Our results showed that scene parsing models had representation closer to OPA than scene classification models thus validating our approach. We then selected multiple DNNs performing a wide range of computer vision tasks ranging from low-level tasks such as edge detection, 3D tasks such as surface normals, and semantic tasks such as semantic segmentation. We compared the representations of these DNNs with all the regions in the visual cortex, thus revealing the functional representations of different regions of the visual cortex. Our results highly converged with previous investigations of these brain regions validating the feasibility of the proposed approach in finding functional representations of the human brain. Our results also provided new insights into underinvestigated brain regions that can serve as starting hypotheses and promote further investigation into those brain regions. We applied the same approach to find representational insights about the DNNs. A DNN usually consists of multiple layers with each layer performing a computation leading to the final layer that performs prediction for a given task. Training on different tasks could lead to very different representations. Therefore, we first investigate at which stage does the representation in DNNs trained on different tasks starts to differ. We further investigate if the DNNs trained on similar tasks lead to similar representations and on dissimilar tasks lead to more dissimilar representations. We selected the same set of DNNs used in the previous work that were trained on the Taskonomy dataset on a diverse range of 2D, 3D and semantic tasks. Then, given a DNN trained on a particular task, we compared the representation of multiple layers to corresponding layers in other DNNs. From this analysis, we aimed to reveal where in the network architecture task-specific representation is prominent. We found that task specificity increases as we go deeper into the DNN architecture and similar tasks start to cluster in groups. We found that the grouping we found using representational similarity was highly correlated with grouping based on transfer learning thus creating an interesting application of the approach to model selection in transfer learning. During previous works, several new measures were introduced to compare DNN representations. So, we identified the commonalities in different measures and unified different measures into a single framework referred to as duality diagram similarity. This work opens up new possibilities for similarity measures to understand DNN representations. While demonstrating a much higher correlation with transfer learning than previous state-of-the-art measures we extend it to understanding layer-wise representations of models trained on the Imagenet and Places dataset using different tasks and demonstrate its applicability to layer selection for transfer learning. In all the previous works, we used the task-specific DNN representations to understand the representations in the human visual cortex and other DNNs. We were able to interpret our findings in terms of computer vision tasks such as edge detection, semantic segmentation, depth estimation, etc. however we were not able to map the representations to human interpretable concepts. Therefore in our most recent work, we developed a new method that associates individual artificial neurons with human interpretable concepts. Overall, the works in this thesis revealed new insights into the representation of the visual cortex and DNNs...

Attention mechanism can focus on important features and suppress unnecessary features, to increase the representational power of the network, which plays an important role in visual tasks such as semantic segmentation. To this end, the UNET of Convolutional Block Attention Module (CBAM) is applied in semantic segmentation tasks to improve the performance of convolutional neural networks. The channel attention adopts maximum pooling and average pooling, and for the spatial attention, a smaller convolution kernel is proposed to reduce computation and loss of important features. Through experiments, the introduction of CBAM has a improvement in semantic segmentation tasks increasing the Validation Dice from 0.98 to 0.9871 in the Kaggle Carvana image segmentation dataset.

Improving performance of deep learning models for 3D point cloud semantic segmentation via attention mechanisms

Convolutional neural networks (CNNs) achieve prevailing results in segmentation tasks nowadays and represent the state-of-the-art for image-based analysis. However, the under- standing of the accurate decision-making process of a CNN is rather unknown. The research area of explainable artificial intelligence (xAI) primarily revolves around understanding and interpreting this black-box behavior. One way of interpreting a CNN is the use of class ac- tivation maps (CAMs) that represent heatmaps to indicate the importance of image areas for the prediction of the CNN. For classification tasks, a variety of CAM algorithms exist. But for segmentation tasks, only one CAM algorithm for the interpretation of the output of a CNN exist. We propose a transfer between existing classification- and segmentation- based methods for more detailed, explainable, and consistent results which show salient pixels in semantic segmentation tasks. The resulting Seg-HiRes-Grad CAM is an exten- sion of the segmentation-based Seg-Grad CAM with the transfer to the classification-based HiRes CAM. Our method improves the previously-mentioned existing segmentation-based method by adjusting it to recently published classification-based methods. Especially for medical image segmentation, this transfer solves existing explainability disadvantages. The code is available at <a href='https://github.com/TillmannRheude/SegHiResGrad_CAM'>https://github.com/TillmannRheude/SegHiResGrad_CAM</a>