Tootfinder

This https://arxiv.org/abs/2404.02282 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCV_…

Smooth Deep Saliency
In this work, we investigate methods to reduce the noise in deep saliency maps coming from convolutional downsampling, with the purpose of explaining how a deep learning model detects tumors in scanned histological tissue samples. Those methods make the investigated models more interpretable for gradient-based saliency maps, computed in hidden layers. We test our approach on different models trained for image classification on ImageNet1K, and models trained for tumor detection on Camelyon16 and…

This https://arxiv.org/abs/2404.02282 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCV_…

Smooth Deep Saliency
In this work, we investigate methods to reduce the noise in deep saliency maps coming from convolutional downsampling, with the purpose of explaining how a deep learning model detects tumors in scanned histological tissue samples. Those methods make the investigated models more interpretable for gradient-based saliency maps, computed in hidden layers. We test our approach on different models trained for image classification on ImageNet1K, and models trained for tumor detection on Camelyon16 and…

This https://arxiv.org/abs/2402.18929 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCV_…

Navigating Beyond Dropout: An Intriguing Solution Towards Generalizable Image Super Resolution
Deep learning has led to a dramatic leap on Single Image Super-Resolution (SISR) performances in recent years. %Despite the substantial advancement% While most existing work assumes a simple and fixed degradation model (e.g., bicubic downsampling), the research of Blind SR seeks to improve model generalization ability with unknown degradation. Recently, Kong et al pioneer the investigation of a more suitable training strategy for Blind SR using Dropout. Although such method indeed brings substa…

Graph-based Forecasting with Missing Data through Spatiotemporal Downsampling
Ivan Marisca, Cesare Alippi, Filippo Maria Bianchi
https://arxiv.org/abs/2402.10634

Graph-based Forecasting with Missing Data through Spatiotemporal Downsampling
Given a set of synchronous time series, each associated with a sensor-point in space and characterized by inter-series relationships, the problem of spatiotemporal forecasting consists of predicting future observations for each point. Spatiotemporal graph neural networks achieve striking results by representing the relationships across time series as a graph. Nonetheless, most existing methods rely on the often unrealistic assumption that inputs are always available and fail to capture hidden s…

Towards Efficient and Accurate CT Segmentation via Edge-Preserving Probabilistic Downsampling
Shahzad Ali, Yu Rim Lee, Soo Young Park, Won Young Tak, Soon Ki Jung
https://arxiv.org/abs/2404.03991

Towards Efficient and Accurate CT Segmentation via Edge-Preserving Probabilistic Downsampling
Downsampling images and labels, often necessitated by limited resources or to expedite network training, leads to the loss of small objects and thin boundaries. This undermines the segmentation network's capacity to interpret images accurately and predict detailed labels, resulting in diminished performance compared to processing at original resolutions. This situation exemplifies the trade-off between efficiency and accuracy, with higher downsampling factors further impairing segmentation outc…

This https://arxiv.org/abs/2311.16581 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csGR_…

GeoScaler: Geometry and Rendering-Aware Downsampling of 3D Mesh Textures
High-resolution texture maps are necessary for representing real-world objects accurately with 3D meshes. The large sizes of textures can bottleneck the real-time rendering of high-quality virtual 3D scenes on devices having low computational budgets and limited memory. Downsampling the texture maps directly addresses the issue, albeit at the cost of visual fidelity. Traditionally, downsampling of texture maps is performed using methods like bicubic interpolation and the Lanczos algorithm. Thes…

Enabling Experimental Impulse-Based Substructuring through Time Domain Deconvolution and Downsampling
Oliver Maximilian Zobel, Francesco Trainotti, Daniel J. Rixen
https://arxiv.org/abs/2404.14802

Enabling Experimental Impulse-Based Substructuring through Time Domain Deconvolution and Downsampling
Dynamic substructuring, especially the frequency-based variant (FBS) using frequency response functions (FRF), is gaining in popularity and importance, with countless successful applications, both numerically and experimentally. One drawback, however, is found when the responses to shocks are determined. Numerically, this might be especially expensive when a huge number of high-frequency modes have to be accounted for to correctly predict response amplitudes to shocks. In all cases, the initial…

Hierarchical Prior-based Super Resolution for Point Cloud Geometry Compression
Dingquan Li, Kede Ma, Jing Wang, Ge Li
https://arxiv.org/abs/2402.11250 http…

Hierarchical Prior-based Super Resolution for Point Cloud Geometry Compression
The Geometry-based Point Cloud Compression (G-PCC) has been developed by the Moving Picture Experts Group to compress point clouds. In its lossy mode, the reconstructed point cloud by G-PCC often suffers from noticeable distortions due to the naïve geometry quantization (i.e., grid downsampling). This paper proposes a hierarchical prior-based super resolution method for point cloud geometry compression. The content-dependent hierarchical prior is constructed at the encoder side, which enables …

SICRN: Advancing Speech Enhancement through State Space Model and Inplace Convolution Techniques
Changjiang Zhao, Shulin He, Xueliang Zhang
https://arxiv.org/abs/2402.14225

SICRN: Advancing Speech Enhancement through State Space Model and Inplace Convolution Techniques
Speech enhancement aims to improve speech quality and intelligibility, especially in noisy environments where background noise degrades speech signals. Currently, deep learning methods achieve great success in speech enhancement, e.g. the representative convolutional recurrent neural network (CRN) and its variants. However, CRN typically employs consecutive downsampling and upsampling convolution for frequency modeling, which destroys the inherent structure of the signal over frequency. Additio…

Dynamic U-Net: Adaptively Calibrate Features for Abdominal Multi-organ Segmentation
Jin Yang, Daniel S. Marcus, Aristeidis Sotiras
https://arxiv.org/abs/2403.07303

Dynamic U-Net: Adaptively Calibrate Features for Abdominal Multi-organ Segmentation
U-Net has been widely used for segmenting abdominal organs, achieving promising performance. However, when it is used for multi-organ segmentation, first, it may be limited in exploiting global long-range contextual information due to the implementation of standard convolutions. Second, the use of spatial-wise downsampling (e.g., max pooling or strided convolutions) in the encoding path may lead to the loss of deformable or discriminative details. Third, features upsampled from the higher level…