PyTorchKR Papers

최신 논문

총 12,272편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2310.07781공식 코드 · Papers with Code

3D TransUNet: Advancing Medical Image Segmentation through Vision Transformers

Medical image segmentation plays a crucial role in advancing healthcare systems for disease diagnosis and treatment planning. The u-shaped architecture, popularly known as U-Net, has proven highly successful for various medical image segmentation tasks. However, U-Net's convolution-based operations inherently limit its ability to model long-range dependencies effectively. To address these limitations, researchers have turned to Transformers, renowned for their global self-attention mechanisms, as alternative architectures. One popular network is our previous TransUNet, which leverages Transformers' self-attention to complement U-Net's localized information with the global context. In this paper, we extend the 2D TransUNet architecture to a 3D network by building upon the state-of-the-art nnU-Net architecture, and fully exploring Transformers' potential in both the encoder and decoder design. We introduce two key components: 1) A Transformer encoder that tokenizes image patches from a convolution neural network (CNN) feature map, enabling the extraction of global contexts, and 2) A Transformer decoder that adaptively refines candidate regions by utilizing cross-attention between candidate proposals and U-Net features. Our investigations reveal that different medical tasks benefit from distinct architectural designs. The Transformer encoder excels in multi-organ segmentation, where the relationship among organs is crucial. On the other hand, the Transformer decoder proves more beneficial for dealing with small and challenging segmented targets such as tumor segmentation. Extensive experiments showcase the significant potential of integrating a Transformer-based encoder and decoder into the u-shaped medical image segmentation architecture. TransUNet outperforms competitors in various medical applications.

arXiv:2310.08538공식 코드 · Papers with Code

Image2PCI -- A Multitask Learning Framework for Estimating Pavement Condition Indices Directly from Images

The Pavement Condition Index (PCI) is a widely used metric for evaluating pavement performance based on the type, extent and severity of distresses detected on a pavement surface. In recent times, significant progress has been made in utilizing deep-learning approaches to automate PCI estimation process. However, the current approaches rely on at least two separate models to estimate PCI values -- one model dedicated to determining the type and extent and another for estimating their severity. This approach presents several challenges, including complexities, high computational resource demands, and maintenance burdens that necessitate careful consideration and resolution. To overcome these challenges, the current study develops a unified multi-tasking model that predicts the PCI directly from a top-down pavement image. The proposed architecture is a multi-task model composed of one encoder for feature extraction and four decoders to handle specific tasks: two detection heads, one segmentation head and one PCI estimation head. By multitasking, we are able to extract features from the detection and segmentation heads for automatically estimating the PCI directly from the images. The model performs very well on our benchmarked and open pavement distress dataset that is annotated for multitask learning (the first of its kind). To our best knowledge, this is the first work that can estimate PCI directly from an image at real time speeds while maintaining excellent accuracy on all related tasks for crack detection and segmentation.

arXiv:2310.07209

Multi-task Explainable Skin Lesion Classification

Skin cancer is one of the deadliest diseases and has a high mortality rate if left untreated. The diagnosis generally starts with visual screening and is followed by a biopsy or histopathological examination. Early detection can aid in lowering mortality rates. Visual screening can be limited by the experience of the doctor. Due to the long tail distribution of dermatological datasets and significant intra-variability between classes, automatic classification utilizing computer-aided methods becomes challenging. In this work, we propose a multitask few-shot-based approach for skin lesions that generalizes well with few labelled data to address the small sample space challenge. The proposed approach comprises a fusion of a segmentation network that acts as an attention module and classification network. The output of the segmentation network helps to focus on the most discriminatory features while making a decision by the classification network. To further enhance the classification performance, we have combined segmentation and classification loss in a weighted manner. We have also included the visualization results that explain the decisions made by the algorithm. Three dermatological datasets are used to evaluate the proposed method thoroughly. We also conducted cross-database experiments to ensure that the proposed approach is generalizable across similar datasets. Experimental results demonstrate the efficacy of the proposed work.

arXiv:2310.06848

DeepTriNet: A Tri-Level Attention Based DeepLabv3+ Architecture for Semantic Segmentation of Satellite Images

The segmentation of satellite images is crucial in remote sensing applications. Existing methods face challenges in recognizing small-scale objects in satellite images for semantic segmentation primarily due to ignoring the low-level characteristics of the underlying network and due to containing distinct amounts of information by different feature maps. Thus, in this research, a tri-level attention-based DeepLabv3+ architecture (DeepTriNet) is proposed for the semantic segmentation of satellite images. The proposed hybrid method combines squeeze-and-excitation networks (SENets) and tri-level attention units (TAUs) with the vanilla DeepLabv3+ architecture, where the TAUs are used to bridge the semantic feature gap among encoders output and the SENets used to put more weight on relevant features. The proposed DeepTriNet finds which features are the more relevant and more generalized way by its self-supervision rather we annotate them. The study showed that the proposed DeepTriNet performs better than many conventional techniques with an accuracy of 98% and 77%, IoU 80% and 58%, precision 88% and 68%, and recall of 79% and 55% on the 4-class Land-Cover.ai dataset and the 15-class GID-2 dataset respectively. The proposed method will greatly contribute to natural resource management and change detection in rural and urban regions through efficient and semantic satellite image segmentation

arXiv:2310.07573공식 코드 · Papers with Code

Relational Prior Knowledge Graphs for Detection and Instance Segmentation

Humans have a remarkable ability to perceive and reason about the world around them by understanding the relationships between objects. In this paper, we investigate the effectiveness of using such relationships for object detection and instance segmentation. To this end, we propose a Relational Prior-based Feature Enhancement Model (RP-FEM), a graph transformer that enhances object proposal features using relational priors. The proposed architecture operates on top of scene graphs obtained from initial proposals and aims to concurrently learn relational context modeling for object detection and instance segmentation. Experimental evaluations on COCO show that the utilization of scene graphs, augmented with relational priors, offer benefits for object detection and instance segmentation. RP-FEM demonstrates its capacity to suppress improbable class predictions within the image while also preventing the model from generating duplicate predictions, leading to improvements over the baseline model on which it is built.

arXiv:2310.07572

Impact of Label Types on Training SWIN Models with Overhead Imagery

Understanding the impact of data set design on model training and performance can help alleviate the costs associated with generating remote sensing and overhead labeled data. This work examined the impact of training shifted window transformers using bounding boxes and segmentation labels, where the latter are more expensive to produce. We examined classification tasks by comparing models trained with both target and backgrounds against models trained with only target pixels, extracted by segmentation labels. For object detection models, we compared performance using either label type when training. We found that the models trained on only target pixels do not show performance improvement for classification tasks, appearing to conflate background pixels in the evaluation set with target pixels. For object detection, we found that models trained with either label type showed equivalent performance across testing. We found that bounding boxes appeared to be sufficient for tasks that did not require more complex labels, such as object segmentation. Continuing work to determine consistency of this result across data types and model architectures could potentially result in substantial savings in generating remote sensing data sets for deep learning.

arXiv:2310.07522

S4C: Self-Supervised Semantic Scene Completion with Neural Fields

3D semantic scene understanding is a fundamental challenge in computer vision. It enables mobile agents to autonomously plan and navigate arbitrary environments. SSC formalizes this challenge as jointly estimating dense geometry and semantic information from sparse observations of a scene. Current methods for SSC are generally trained on 3D ground truth based on aggregated LiDAR scans. This process relies on special sensors and annotation by hand which are costly and do not scale well. To overcome this issue, our work presents the first self-supervised approach to SSC called S4C that does not rely on 3D ground truth data. Our proposed method can reconstruct a scene from a single image and only relies on videos and pseudo segmentation ground truth generated from off-the-shelf image segmentation network during training. Unlike existing methods, which use discrete voxel grids, we represent scenes as implicit semantic fields. This formulation allows querying any point within the camera frustum for occupancy and semantic class. Our architecture is trained through rendering-based self-supervised losses. Nonetheless, our method achieves performance close to fully supervised state-of-the-art methods. Additionally, our method demonstrates strong generalization capabilities and can synthesize accurate segmentation maps for far away viewpoints.

arXiv:2310.07394

CLIP for Lightweight Semantic Segmentation

The large-scale pretrained model CLIP, trained on 400 million image-text pairs, offers a promising paradigm for tackling vision tasks, albeit at the image level. Later works, such as DenseCLIP and LSeg, extend this paradigm to dense prediction, including semantic segmentation, and have achieved excellent results. However, the above methods either rely on CLIP-pretrained visual backbones or use none-pretrained but heavy backbones such as Swin, while falling ineffective when applied to lightweight backbones. The reason for this is that the lightweitht networks, feature extraction ability of which are relatively limited, meet difficulty embedding the image feature aligned with text embeddings perfectly. In this work, we present a new feature fusion module which tackles this problem and enables language-guided paradigm to be applied to lightweight networks. Specifically, the module is a parallel design of CNN and transformer with a two-way bridge in between, where CNN extracts spatial information and visual context of the feature map from the image encoder, and the transformer propagates text embeddings from the text encoder forward. The core of the module is the bidirectional fusion of visual and text feature across the bridge which prompts their proximity and alignment in embedding space. The module is model-agnostic, which can not only make language-guided lightweight semantic segmentation practical, but also fully exploit the pretrained knowledge of language priors and achieve better performance than previous SOTA work, such as DenseCLIP, whatever the vision backbone is. Extensive experiments have been conducted to demonstrate the superiority of our method.

arXiv:2310.07379공식 코드 · Papers with Code

Causal Unsupervised Semantic Segmentation

Unsupervised semantic segmentation aims to achieve high-quality semantic grouping without human-labeled annotations. With the advent of self-supervised pre-training, various frameworks utilize the pre-trained features to train prediction heads for unsupervised dense prediction. However, a significant challenge in this unsupervised setup is determining the appropriate level of clustering required for segmenting concepts. To address it, we propose a novel framework, CAusal Unsupervised Semantic sEgmentation (CAUSE), which leverages insights from causal inference. Specifically, we bridge intervention-oriented approach (i.e., frontdoor adjustment) to define suitable two-step tasks for unsupervised prediction. The first step involves constructing a concept clusterbook as a mediator, which represents possible concept prototypes at different levels of granularity in a discretized form. Then, the mediator establishes an explicit link to the subsequent concept-wise self-supervised learning for pixel-level grouping. Through extensive experiments and analyses on various datasets, we corroborate the effectiveness of CAUSE and achieve state-of-the-art performance in unsupervised semantic segmentation.

arXiv:2310.07183공식 코드 · Papers with Code

SAM-OCTA: Prompting Segment-Anything for OCTA Image Segmentation

Segmenting specific targets or biomarkers is necessary to analyze optical coherence tomography angiography (OCTA) images. Previous methods typically segment all the targets in an OCTA sample, such as retinal vessels (RVs). Although these methods perform well in accuracy and precision, OCTA analyses often focusing local information within the images which has not been fulfilled. In this paper, we propose a method called SAM-OCTA for local segmentation in OCTA images. The method fine-tunes a pre-trained segment anything model (SAM) using low-rank adaptation (LoRA) and utilizes prompt points for local RVs, arteries, and veins segmentation in OCTA. To explore the effect and mechanism of prompt points, we set up global and local segmentation modes with two prompt point generation strategies, namely random selection and special annotation. Considering practical usage, we conducted extended experiments with different model scales and analyzed the model performance before and after fine-tuning besides the general segmentation task. From comprehensive experimental results with the OCTA-500 dataset, our SAM-OCTA method has achieved state-of-the-art performance in common OCTA segmentation tasks related to RV and FAZ, and it also performs accurate segmentation of artery-vein and local vessels. The code is available at https://github.com/ShellRedia/SAM-OCTA-extend.

arXiv:2310.05990

Cross-Task Data Augmentation by Pseudo-label Generation for Region Based Coronary Artery Instance Segmentation

Coronary Artery Diseases (CADs) although preventable, are one of the leading causes of death and disability. Diagnosis of these diseases is often difficult and resource intensive. Angiographic imaging segmentation of the arteries has evolved as a tool of assistance that helps clinicians make an accurate diagnosis. However, due to the limited amount of data and the difficulty in curating a dataset, the task of segmentation has proven challenging. In this study, we introduce the use of pseudo-labels to address the issue of limited data in the angiographic dataset to enhance the performance of the baseline YOLO model. Unlike existing data augmentation techniques that improve the model constrained to a fixed dataset, we introduce the use of pseudo-labels generated on a dataset of separate related task to diversify and improve model performance. This method increases the baseline F1 score by 9% in the validation data set and by 3% in the test data set.

arXiv:2310.04442공식 코드 · Papers with Code

The Optimal use of Segmentation for Sampling Calorimeters

One of the key design choices of any sampling calorimeter is how fine to make the longitudinal and transverse segmentation. To inform this choice, we study the impact of calorimeter segmentation on energy reconstruction. To ensure that the trends are due entirely to hardware and not to a sub-optimal use of segmentation, we deploy deep neural networks to perform the reconstruction. These networks make use of all available information by representing the calorimeter as a point cloud. To demonstrate our approach, we simulate a detector similar to the forward calorimeter system intended for use in the ePIC detector, which will operate at the upcoming Electron Ion Collider. We find that for the energy estimation of isolated charged pion showers, relatively fine longitudinal segmentation is key to achieving an energy resolution that is better than 10% across the full phase space. These results provide a valuable benchmark for ongoing EIC detector optimizations and may also inform future studies involving high-granularity calorimeters in other experiments at various facilities.

arXiv:2310.06259공식 코드 · Papers with Code

Cross-modal Cognitive Consensus guided Audio-Visual Segmentation

Audio-Visual Segmentation (AVS) aims to extract the sounding object from a video frame, which is represented by a pixel-wise segmentation mask for application scenarios such as multi-modal video editing, augmented reality, and intelligent robot systems. The pioneering work conducts this task through dense feature-level audio-visual interaction, which ignores the dimension gap between different modalities. More specifically, the audio clip could only provide a Global semantic label in each sequence, but the video frame covers multiple semantic objects across different Local regions, which leads to mislocalization of the representationally similar but semantically different object. In this paper, we propose a Cross-modal Cognitive Consensus guided Network (C3N) to align the audio-visual semantics from the global dimension and progressively inject them into the local regions via an attention mechanism. Firstly, a Cross-modal Cognitive Consensus Inference Module (C3IM) is developed to extract a unified-modal label by integrating audio/visual classification confidence and similarities of modality-agnostic label embeddings. Then, we feed the unified-modal label back to the visual backbone as the explicit semantic-level guidance via a Cognitive Consensus guided Attention Module (CCAM), which highlights the local features corresponding to the interested object. Extensive experiments on the Single Sound Source Segmentation (S4) setting and Multiple Sound Source Segmentation (MS3) setting of the AVSBench dataset demonstrate the effectiveness of the proposed method, which achieves state-of-the-art performance. Code is available at https://github.com/ZhaofengSHI/AVS-C3N.

arXiv:2310.06582공식 코드 · Papers with Code

Hierarchical Mask2Former: Panoptic Segmentation of Crops, Weeds and Leaves

Advancements in machine vision that enable detailed inferences to be made from images have the potential to transform many sectors including agriculture. Precision agriculture, where data analysis enables interventions to be precisely targeted, has many possible applications. Precision spraying, for example, can limit the application of herbicide only to weeds, or limit the application of fertiliser only to undernourished crops, instead of spraying the entire field. The approach promises to maximise yields, whilst minimising resource use and harms to the surrounding environment. To this end, we propose a hierarchical panoptic segmentation method to simultaneously identify indicators of plant growth and locate weeds within an image. We adapt Mask2Former, a state-of-the-art architecture for panoptic segmentation, to predict crop, weed and leaf masks. We achieve a PQ{\dag} of 75.99. Additionally, we explore approaches to make the architecture more compact and therefore more suitable for time and compute constrained applications. With our more compact architecture, inference is up to 60% faster and the reduction in PQ{\dag} is less than 1%.

arXiv:2310.06162

Empirical Evaluation of the Segment Anything Model (SAM) for Brain Tumor Segmentation

Brain tumor segmentation presents a formidable challenge in the field of Medical Image Segmentation. While deep-learning models have been useful, human expert segmentation remains the most accurate method. The recently released Segment Anything Model (SAM) has opened up the opportunity to apply foundation models to this difficult task. However, SAM was primarily trained on diverse natural images. This makes applying SAM to biomedical segmentation, such as brain tumors with less defined boundaries, challenging. In this paper, we enhanced SAM's mask decoder using transfer learning with the Decathlon brain tumor dataset. We developed three methods to encapsulate the four-dimensional data into three dimensions for SAM. An on-the-fly data augmentation approach has been used with a combination of rotations and elastic deformations to increase the size of the training dataset. Two key metrics: the Dice Similarity Coefficient (DSC) and the Hausdorff Distance 95th Percentile (HD95), have been applied to assess the performance of our segmentation models. These metrics provided valuable insights into the quality of the segmentation results. In our evaluation, we compared this improved model to two benchmarks: the pretrained SAM and the widely used model, nnUNetv2. We find that the improved SAM shows considerable improvement over the pretrained SAM, while nnUNetv2 outperformed the improved SAM in terms of overall segmentation accuracy. Nevertheless, the improved SAM demonstrated slightly more consistent results than nnUNetv2, especially on challenging cases that can lead to larger Hausdorff distances. In the future, more advanced techniques can be applied in order to further improve the performance of SAM on brain tumor segmentation.

arXiv:2310.05393

Hierarchical Side-Tuning for Vision Transformers

Fine-tuning pre-trained Vision Transformers (ViTs) has showcased significant promise in enhancing visual recognition tasks. Yet, the demand for individualized and comprehensive fine-tuning processes for each task entails substantial computational and memory costs, posing a considerable challenge. Recent advancements in Parameter-Efficient Transfer Learning (PETL) have shown potential for achieving high performance with fewer parameter updates compared to full fine-tuning. However, their effectiveness is primarily observed in simple tasks like image classification, while they encounter challenges with more complex vision tasks like dense prediction. To address this gap, this study aims to identify an effective tuning method that caters to a wider range of visual tasks. In this paper, we introduce Hierarchical Side-Tuning (HST), an innovative PETL method facilitating the transfer of ViT models to diverse downstream tasks. Diverging from existing methods that focus solely on fine-tuning parameters within specific input spaces or modules, HST employs a lightweight Hierarchical Side Network (HSN). This network leverages intermediate activations from the ViT backbone to model multi-scale features, enhancing prediction capabilities. To evaluate HST, we conducted comprehensive experiments across a range of visual tasks, including classification, object detection, instance segmentation, and semantic segmentation. Remarkably, HST achieved state-of-the-art performance in 13 out of the 19 tasks on the VTAB-1K benchmark, with the highest average Top-1 accuracy of 76.1%, while fine-tuning a mere 0.78M parameters. When applied to object detection and semantic segmentation tasks on the COCO and ADE20K testdev benchmarks, HST outperformed existing PETL methods and even surpassed full fine-tuning.

arXiv:2310.05371

Enhancing Prostate Cancer Diagnosis with Deep Learning: A Study using mpMRI Segmentation and Classification

Prostate cancer (PCa) is a severe disease among men globally. It is important to identify PCa early and make a precise diagnosis for effective treatment. For PCa diagnosis, Multi-parametric magnetic resonance imaging (mpMRI) emerged as an invaluable imaging modality that offers a precise anatomical view of the prostate gland and its tissue structure. Deep learning (DL) models can enhance existing clinical systems and improve patient care by locating regions of interest for physicians. Recently, DL techniques have been employed to develop a pipeline for segmenting and classifying different cancer types. These studies show that DL can be used to increase diagnostic precision and give objective results without variability. This work uses well-known DL models for the classification and segmentation of mpMRI images to detect PCa. Our implementation involves four pipelines; Semantic DeepSegNet with ResNet50, DeepSegNet with recurrent neural network (RNN), U-Net with RNN, and U-Net with a long short-term memory (LSTM). Each segmentation model is paired with a different classifier to evaluate the performance using different metrics. The results of our experiments show that the pipeline that uses the combination of U-Net and the LSTM model outperforms all other combinations, excelling in both segmentation and classification tasks.

arXiv:2310.05262

Structure-Preserving Instance Segmentation via Skeleton-Aware Distance Transform

Objects with complex structures pose significant challenges to existing instance segmentation methods that rely on boundary or affinity maps, which are vulnerable to small errors around contacting pixels that cause noticeable connectivity change. While the distance transform (DT) makes instance interiors and boundaries more distinguishable, it tends to overlook the intra-object connectivity for instances with varying width and result in over-segmentation. To address these challenges, we propose a skeleton-aware distance transform (SDT) that combines the merits of object skeleton in preserving connectivity and DT in modeling geometric arrangement to represent instances with arbitrary structures. Comprehensive experiments on histopathology image segmentation demonstrate that SDT achieves state-of-the-art performance.

arXiv:2310.05133

Geometry Aware Field-to-field Transformations for 3D Semantic Segmentation

We present a novel approach to perform 3D semantic segmentation solely from 2D supervision by leveraging Neural Radiance Fields (NeRFs). By extracting features along a surface point cloud, we achieve a compact representation of the scene which is sample-efficient and conducive to 3D reasoning. Learning this feature space in an unsupervised manner via masked autoencoding enables few-shot segmentation. Our method is agnostic to the scene parameterization, working on scenes fit with any type of NeRF.

arXiv:2310.05026공식 코드 · Papers with Code

Low-Resolution Self-Attention for Semantic Segmentation

Semantic segmentation tasks naturally require high-resolution information for pixel-wise segmentation and global context information for class prediction. While existing vision transformers demonstrate promising performance, they often utilize high-resolution context modeling, resulting in a computational bottleneck. In this work, we challenge conventional wisdom and introduce the Low-Resolution Self-Attention (LRSA) mechanism to capture global context at a significantly reduced computational cost, i.e., FLOPs. Our approach involves computing self-attention in a fixed low-resolution space regardless of the input image's resolution, with additional 3x3 depth-wise convolutions to capture fine details in the high-resolution space. We demonstrate the effectiveness of our LRSA approach by building the LRFormer, a vision transformer with an encoder-decoder structure. Extensive experiments on the ADE20K, COCO-Stuff, and Cityscapes datasets demonstrate that LRFormer outperforms state-of-the-art models. he code is available at https://github.com/yuhuan-wu/LRFormer.