English
Related papers

Related papers: Rethinking Skip Connections in Encoder-decoder Net…

200 papers

Conformer-based attention models have become the de facto backbone model for Automatic Speech Recognition tasks. A blank symbol is usually introduced to align the input and output sequences for CTC or RNN-T models. Unfortunately, the long…

Computation and Language · Computer Science 2024-05-22 Wenjing Zhu , Sining Sun , Changhao Shan , Peng Fan , Qing Yang

Recently, many methods have been proposed for object detection. They cannot detect objects by semantic features, adaptively. In this work, according to channel and spatial attention mechanisms, we mainly analyze that different methods…

Computer Vision and Pattern Recognition · Computer Science 2020-09-30 Qian Li , Nan Guo , Xiaochun Ye , Dongrui Fan , Zhimin Tang

Monocular depth estimation is known as an ill-posed task in which objects in a 2D image usually do not contain sufficient information to predict their depth. Thus, it acts differently from other tasks (e.g., classification and segmentation)…

Computer Vision and Pattern Recognition · Computer Science 2023-08-11 Wencheng Han , Junbo Yin , Jianbing Shen

Multi-frame depth estimation improves over single-frame approaches by also leveraging geometric relationships between images via feature matching, in addition to learning appearance-based features. In this paper we revisit feature matching…

Computer Vision and Pattern Recognition · Computer Science 2022-06-14 Vitor Guizilini , Rares Ambrus , Dian Chen , Sergey Zakharov , Adrien Gaidon

Deep convolutional networks (CNNs) have exhibited their potential in image inpainting for producing plausible results. However, in most existing methods, e.g., context encoder, the missing parts are predicted by propagating the surrounding…

Computer Vision and Pattern Recognition · Computer Science 2018-04-16 Zhaoyi Yan , Xiaoming Li , Mu Li , Wangmeng Zuo , Shiguang Shan

Many approaches to transform classification problems from non-linear to linear by feature transformation have been recently presented in the literature. These notably include sparse coding methods and deep neural networks. However, many of…

Machine Learning · Computer Science 2015-07-08 Alessandro Montalto , Giovanni Tessitore , Roberto Prevete

Semantic segmentation in high resolution remote sensing images is a fundamental and challenging task. Convolutional neural networks (CNNs), such as fully convolutional network (FCN) and SegNet, have shown outstanding performance in many…

Computer Vision and Pattern Recognition · Computer Science 2018-05-08 Lichao Mou , Xiao Xiang Zhu

Monocular depth estimation and defocus estimation are two fundamental tasks in computer vision. Most existing methods treat depth estimation and defocus estimation as two separate tasks, ignoring the strong connection between them. In this…

Computer Vision and Pattern Recognition · Computer Science 2022-08-23 Renzhi He , Hualin Hong , Boya Fu , Fei Liu

The encoder-decoder networks are commonly used in medical image segmentation due to their remarkable performance in hierarchical feature fusion. However, the expanding path for feature decoding and spatial recovery does not consider the…

Image and Video Processing · Electrical Eng. & Systems 2019-11-22 Ying Wen , Kai Xie , Lianghua He

Without ground truth supervision, self-supervised depth estimation can be trapped in a local minimum due to the gradient-locality issue of the photometric loss. In this paper, we present a framework to enhance depth by leveraging semantic…

Computer Vision and Pattern Recognition · Computer Science 2023-04-03 Shan Lin , Yuheng Zhi , Michael C. Yip

We present GraphDepth, a monocular depth estimation architecture that synergistically integrates Graph Neural Networks (GNNs) within a convolutional encoder-decoder framework. Our approach embeds efficient GraphSAGE layers at multiple…

Computer Vision and Pattern Recognition · Computer Science 2026-05-12 Ishan Narayan

Monocular depth prediction is an important task in scene understanding. It aims to predict the dense depth of a single RGB image. With the development of deep learning, the performance of this task has made great improvements. However, two…

Computer Vision and Pattern Recognition · Computer Science 2021-04-14 Feng Xue , Junfeng Cao , Yu Zhou , Fei Sheng , Yankai Wang , Anlong Ming

Recent years have witnessed great success of convolutional neural network (CNN) for various problems both in low and high level visions. Especially noteworthy is the residual network which was originally proposed to handle high-level vision…

Computer Vision and Pattern Recognition · Computer Science 2017-12-07 Yudong Liang , Ze Yang , Kai Zhang , Yihui He , Jinjun Wang , Nanning Zheng

Convolutional neural networks (CNNs) have become a powerful technique to decode EEG and have become the benchmark for motor imagery EEG Brain-Computer-Interface (BCI) decoding. However, it is still challenging to train CNNs on multiple…

Machine Learning · Computer Science 2021-03-10 Xiaoxi Wei , Pablo Ortega , A. Aldo Faisal

We analyze the regression accuracy of convolutional neural networks assembled from encoders, decoders and skip connections and trained with multifidelity data. Besides requiring significantly less trainable parameters than equivalent fully…

Machine Learning · Computer Science 2022-10-26 Lauren Partin , Gianluca Geraci , Ahmad Rushdi , Michael S. Eldred , Daniele E. Schiavazzi

Deep convolutional neural networks (DCNNs) have achieved great success in monocular depth estimation (MDE). However, few existing works take the contributions for MDE of different levels feature maps into account, leading to inaccurate…

Computer Vision and Pattern Recognition · Computer Science 2024-03-05 Yifang Xu , Chenglei Peng , Ming Li , Yang Li , Sidan Du

Medical image segmentation commonly relies on U-shaped encoder-decoder architectures such as U-Net, where skip connections preserve fine spatial detail by injecting high-resolution encoder features into the decoder. However, these skip…

Computer Vision and Pattern Recognition · Computer Science 2026-03-05 Chun-Wun Cheng , Yanqi Cheng , Peiyuan Jing , Guang Yang , Javier A. Montoya-Zegarra , Carola-Bibiane Schönlieb , Angelica I. Aviles-Rivero

Monocular depth estimation is a crucial task to measure distance relative to a camera, which is important for applications, such as robot navigation and self-driving. Traditional frame-based methods suffer from performance drops due to the…

Computer Vision and Pattern Recognition · Computer Science 2024-07-25 Tianbo Pan , Zidong Cao , Lin Wang

Collaborative Intelligence (CI) has emerged as a promising framework for deploying Artificial Intelligence (AI) models on resource-constrained edge devices. In CI, the AI model is partitioned between the edge device and the cloud, with…

Signal Processing · Electrical Eng. & Systems 2024-11-26 Mengyang Wang , Jiahui Li , Mengyao Ma , Xiaopeng Fan

Recent advances in end-to-end unsupervised learning has significantly improved the performance of monocular depth prediction and alleviated the requirement of ground truth depth. Although a plethora of work has been done in enforcing…

Computer Vision and Pattern Recognition · Computer Science 2020-05-19 Vinay Kaushik , Brejesh Lall