Rethinking Skip Connections in Encoder-decoder Networks for Monocular Depth Estimation
Not on the map. Why?
Abstract (arXiv)
Skip connections are fundamental units in encoder-decoder networks, which are able to improve the feature propagtion of the neural networks. However, most methods with skip connections just connected features with the same resolution in the encoder and the decoder, which ignored the information loss in the encoder with the layers going deeper. To leverage the information loss of the features in shallower layers of the encoder, we propose a full skip connection network (FSCN) for monocular depth estimation task. In addition, to fuse features within skip connections more closely, we present an adaptive concatenation module (ACM). Further more, we conduct extensive experiments on the ourdoor and indoor datasets (i.e., the KITTI dataste and the NYU Depth V2 dataset) for FSCN and FSCN gets the state-of-the-art results.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 31 of its 52 references that are in the map. First posted on arXiv 29 Aug 2022.
Builds on
31 of 52 references.
References · 31
- 2017Attention Is All You Needcited by 60,361
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
- 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
- 2016Densely Connected Convolutional Networkscited by 6,720
- 2017Squeeze-and-Excitation Networkscited by 4,789
- 2016Wide Residual Networkscited by 3,070
- 2016Aggregated Residual Transformations for Deep Neural Networkscited by 2,546
- 2014Depth Map Prediction from a Single Image using a Multi-Scale Deep Networkcited by 1,274
- 2016Unsupervised Monocular Depth Estimation with Left-Right Consistencycited by 820
- 2018Deep Ordinal Regression Network for Monocular Depth Estimationcited by 723
- 20193D Packing for Self-Supervised Monocular Depth Estimationcited by 439
19 more
- 2019From Big to Small: Multi-Scale Local Planar Guidance for Monocular Depth Estimationcited by 382
- 2019Enforcing geometric constraints of virtual normal for depth predictioncited by 234
- 2015Learning Depth from Single Monocular Images Using Deep Convolutional Neural Fieldscited by 169
- 2018Revisiting Single Image Depth Estimation: Toward Higher Resolution Maps with Accurate Object Boundariescited by 145
- 2018High Quality Monocular Depth Estimation via Transfer Learningcited by 133
- 2021Transformer-Based Attention Networks for Continuous Pixel-Wise Predictioncited by 125
- 2020Self-supervised Monocular Trained Depth Estimation using Self-attention and Discrete Disparity Volumecited by 116
- 2017Semi-Supervised Deep Learning for Monocular Depth Map Predictioncited by 109
- 2020Guiding Monocular Depth Estimation Using Depth-Attention Volumecited by 82
- 2019DepthTransfer: Depth Extraction from Video Using Non-parametric Samplingcited by 60
- 2019Structure-Aware Residual Pyramid Network for Monocular Depth Estimationcited by 49
- 2019Bilateral Cyclic Constraint and Adaptive Regularization for Unsupervised Monocular Depth Predictioncited by 44
- 2020Improved anomaly detection by training an autoencoder with skip connections on images corrupted with Stain-shaped noisecited by 39
- 2021Single Image Depth Prediction with Wavelet Decompositioncited by 34
- 2020Toward fast and accurate human pose estimation via soft-gated skip connectionscited by 22
- 2020Regularized Densely-connected Pyramid Network for Salient Instance Segmentationcited by 18
- 2020On Deep Learning Techniques to Boost Monocular Depth Estimation for Autonomous Navigationcited by 17
- 2019Dense Scale Network for Crowd Countingcited by 12
- 2019Semi-Supervised Adversarial Monocular Depth Estimationcited by 11
Built on by
Citing papers per year: 2023: 1.
1 paper.
- 2023Decoupled DETR For Few-shot Object Detectioncited by 1
- 2023Decoupled DETR For Few-shot Object Detection20 Nov 2023