Bowen Yin
YOU?
Author Swipe
View article: Exploring Salient Object Detection with Adder Neural Networks
Exploring Salient Object Detection with Adder Neural Networks Open
In this paper, we explore how to develop salient object detection models using adder neural networks (ANNs), which are more energy efficient than convolutional neural networks (CNNs), especially for real-world applications. Based on our em…
View article: Deformable multi-level feature network applied to nucleus segmentation
Deformable multi-level feature network applied to nucleus segmentation Open
Introduction The nucleus plays a crucial role in medical diagnosis, and accurate nucleus segmentation is essential for disease assessment. However, existing methods have limitations in handling the diversity of nuclei and differences in st…
View article: Multi-Token Enhancing for Vision Representation Learning
Multi-Token Enhancing for Vision Representation Learning Open
Vision representation learning, especially self-supervised learning, is pivotal for various vision applications. Ensemble learning has also succeeded in enhancing the performance and robustness of the vision models. However, traditional en…
View article: Injectable Thermo-Responsive Peptide Hydrogels and Its Enzyme Triggered Dynamic Self-Assembly
Injectable Thermo-Responsive Peptide Hydrogels and Its Enzyme Triggered Dynamic Self-Assembly Open
Endogenous stimuli-responsive injectable hydrogels hold significant promise for practical applications due to their spatio-temporal controllable drug delivery. Herein, we report a facile strategy to construct a series of in situ formation …
View article: TeMO: Towards Text-Driven 3D Stylization for Multi-Object Meshes
TeMO: Towards Text-Driven 3D Stylization for Multi-Object Meshes Open
Recent progress in the text-driven 3D stylization of a single object has been considerably promoted by CLIP-based methods. However, the stylization of multi-object 3D scenes is still impeded in that the image-text pairs used for pre-traini…
View article: Enhancing Representations through Heterogeneous Self-Supervised Learning
Enhancing Representations through Heterogeneous Self-Supervised Learning Open
Incorporating heterogeneous representations from different architectures has facilitated various vision tasks, e.g., some hybrid networks combine transformers and convolutions. However, complementarity between such heterogeneous architectu…
View article: DFormer: Rethinking RGBD Representation Learning for Semantic Segmentation
DFormer: Rethinking RGBD Representation Learning for Semantic Segmentation Open
We present DFormer, a novel RGB-D pretraining framework to learn transferable representations for RGB-D segmentation tasks. DFormer has two new key innovations: 1) Unlike previous works that encode RGB-D information with RGB pretrained bac…
View article: Microstructure and Compressive Properties of Cellular Ti-Mo-based Alloys for Hard Tissue Prostheses
Microstructure and Compressive Properties of Cellular Ti-Mo-based Alloys for Hard Tissue Prostheses Open
Demands for substituting or repairing hard tissues are surging with the increase in aging populations around the world. This paper introduces the preparation, the microstructure, Young’s moduli, as well as the compression strength of cellu…
View article: Referring Camouflaged Object Detection
Referring Camouflaged Object Detection Open
We consider the problem of referring camouflaged object detection (Ref-COD), a new task that aims to segment specified camouflaged objects based on a small set of referring images with salient target objects. We first assemble a large-scal…
View article: CamoFormer: Masked Separable Attention for Camouflaged Object Detection
CamoFormer: Masked Separable Attention for Camouflaged Object Detection Open
How to identify and segment camouflaged objects from the background is challenging. Inspired by the multi-head self-attention in Transformers, we present a simple masked separable attention (MSA) for camouflaged object detection. We first …
View article: Life Prediction of the Gear Transmission System with Multicharacteristics
Life Prediction of the Gear Transmission System with Multicharacteristics Open
This study obtains and predicts multifault data in the key transmission and connection systems with gears. Model building is based on the multikernel extreme learning machine with the method of maximum correlation kurtosis deconvolution an…