相关论文: SatReg: Regression-based Neural Architecture Searc…

Segmentation of organs of interest in 3D medical images is necessary for accurate diagnosis and longitudinal studies. Though recent advances using deep learning have shown success for many segmentation tasks, large datasets are required for…

Medical image segmentation requires large annotated datasets, creating a significant bottleneck for clinical applications. While few-shot segmentation methods can learn from minimal examples, existing approaches demonstrate suboptimal…

Roof plane segmentation is one of the key procedures for reconstructing three-dimensional (3D) building models at levels of detail (LoD) 2 and 3 from airborne light detection and ranging (LiDAR) point clouds. The majority of current…

We tackle a novel few-shot learning challenge, which we call few-shot semantic edge detection, aiming to localize crisp boundaries of novel categories using only a few labeled samples. We also present a Class-Agnostic Few-shot Edge…

Neural networks have become popular due to their versatility and state-of-the-art results in many applications, such as image classification, natural language processing, speech recognition, forecasting, etc. These applications are also…

Adaptive inference is an effective mechanism to achieve a dynamic tradeoff between accuracy and computational cost in deep networks. Existing works mainly exploit architecture redundancy in network depth or width. In this paper, we focus on…

In recent years, analysis of remote sensing data has benefited immensely from borrowing techniques from the broader field of computer vision, such as the use of shared models pre-trained on large and diverse datasets. However, satellite…

Since its introduction, UNet has been leading a variety of medical image segmentation tasks. Although numerous follow-up studies have also been dedicated to improving the performance of standard UNet, few have conducted in-depth analyses of…

In the tasks of image aesthetic quality evaluation, it is difficult to reach both the high score area and low score area due to the normal distribution of aesthetic datasets. To reduce the error in labeling and solve the problem of normal…

Deep convolutional neural networks (DCNNs) based remote sensing (RS) image semantic segmentation technology has achieved great success used in many real-world applications such as geographic element analysis. However, strong dependency on…

This paper proposes a novel approach to few-shot semantic segmentation for machinery with multiple parts that exhibit spatial and hierarchical relationships. Our method integrates the foundation models CLIPSeg and Segment Anything Model…

To address the annotation scarcity issue in some cases of semantic segmentation, there have been a few attempts to develop the segmentation model in the few-shot learning paradigm. However, most existing methods only focus on the…

In this study, we introduce EdgeSegNet, a compact deep convolutional neural network for the task of semantic segmentation. A human-machine collaborative design strategy is leveraged to create EdgeSegNet, where principled network design…

In this study, we applied the PointRend (Point-based Rendering) method to semiconductor defect segmentation. PointRend is an iterative segmentation algorithm inspired by image rendering in computer graphics, a new image segmentation method…

We propose a highly structured neural network architecture for semantic segmentation with an extremely small model size, suitable for low-power embedded and mobile platforms. Specifically, our architecture combines i) a Haar wavelet-based…

Current NAS-based semantic segmentation methods focus on accuracy improvements rather than light-weight design. In this paper, we proposed a two-stage framework to design our NAS-based RSPNet model for light-weight semantic segmentation.…

We introduce Amortized Neural Networks (AmNets), a compute cost- and latency-aware network architecture particularly well-suited for sequence modeling tasks. We apply AmNets to the Recurrent Neural Network Transducer (RNN-T) to reduce…

Recently, deep learning has been successfully applied to the single-image super-resolution (SISR) with remarkable performance. However, most existing methods focus on building a more complex network with a large number of layers, which can…

Machine unlearning aims to remove the influence of a designated forget set from a trained model while preserving utility on the retained data. In modern deep networks, approximate unlearning frequently fails under large or adversarial…

In this research, we propose a new low-precision framework, TENT, to leverage the benefits of a tapered fixed-point numerical format in TinyML models. We introduce a tapered fixed-point quantization algorithm that matches the numerical…