Study of mechanical degradation of freestanding ALD Al 2 O 3 by a hygrothermal environment and a facile protective method for environmentally stable Al 2 O 3 …
Al2O3 deposited via atomic layer deposition (ALD) has been used as an insulating and
barrier film for thin-film transistors, organic electronics, and microelectromechanical systems …
barrier film for thin-film transistors, organic electronics, and microelectromechanical systems …
Neural clustering based visual representation learning
We investigate a fundamental aspect of machine vision: the measurement of features by
revisiting clustering one of the most classic approaches in machine learning and data …
revisiting clustering one of the most classic approaches in machine learning and data …
Robust domain adaptive object detection with unified multi-granularity alignment
Domain adaptive detection aims to improve the generalization of detectors on target domain.
To reduce discrepancy in feature distributions between two domains, recent approaches …
To reduce discrepancy in feature distributions between two domains, recent approaches …
ISTR: Mask-Embedding-Based Instance Segmentation Transformer
Transformer-based instance-level recognition has attracted increasing research attention
recently due to the superior performance. However, although attempts have been made to …
recently due to the superior performance. However, although attempts have been made to …
Diabetic retinopathy detection and severity classification using optimized deep learning with explainable AI technique
B Lalithadevi, S Krishnaveni - Multimedia Tools and Applications, 2024 - Springer
Diabetic Retinopathy (DR) is a serious consequence of prolonged diabetic patients that
causes vision threatening issues and irreversible blindness problem. In the beginning stage …
causes vision threatening issues and irreversible blindness problem. In the beginning stage …
Exploring Prototype-Anchor Contrast for Semantic Segmentation
Pixel-wise contrastive learning recently offers a new training paradigm in semantic
segmentation by directly shaping the pixel embedding space. Compared with pixel-pixel …
segmentation by directly shaping the pixel embedding space. Compared with pixel-pixel …
[HTML][HTML] NUNI-Waste: novel semi-supervised semantic segmentation waste classification with non-uniform data augmentation
Waste categorization and recycling are critical approaches for converting waste into
valuable and functional materials, thereby significantly aiding in land preservation, reducing …
valuable and functional materials, thereby significantly aiding in land preservation, reducing …
CS-UNet: A generalizable and flexible segmentation algorithm
This study introduces a novel U-shaped image-segmentation algorithm, CS-UNet, which
contains parallel CNN and Transformer encoders. This algorithm leverages the relative …
contains parallel CNN and Transformer encoders. This algorithm leverages the relative …
Prototypical Transformer as Unified Motion Learners
In this work, we introduce the Prototypical Transformer (ProtoFormer), a general and unified
framework that approaches various motion tasks from a prototype perspective. ProtoFormer …
framework that approaches various motion tasks from a prototype perspective. ProtoFormer …
Interactive Spectral-Spatial Transformer for Hyperspectral Image Classification
The abundant spectral signatures and spatial contexts are effectively utilized as the key to
hyperspectral image (HSI) classification. Existing convolutional neural networks (CNNs) …
hyperspectral image (HSI) classification. Existing convolutional neural networks (CNNs) …