Papers Read on AI

This paper presents a transformer-based Siamese network architecture (abbreviated by ChangeFormer) for Change Detection (CD) from a pair of co-registered remote sensing images. Different from recent CD frameworks, which are based on fully convolutional networks (ConvNets), the proposed method unifies hierarchically structured transformer encoder with Multi-Layer Perception (MLP) decoder in a Siamese network architecture to efficiently render multi-scale long-range details required for accurate CD.

2022: W. G. C. Bandara, Vishal M. Patel

https://arxiv.org/pdf/2201.01293v1.pdf

This paper presents a transformer-based Siamese network architecture (abbreviated by ChangeFormer) for Change Detection (CD) from a pair of co-registered remote sensing images. Different from recent CD frameworks, which are based on fully convolutional networks (ConvNets), the proposed method unifies hierarchically structured transformer encoder with Multi-Layer Perception (MLP) decoder in a Siamese network architecture to efficiently render multi-scale long-range details required for accurate CD.

2022: W. G. C. Bandara, Vishal M. Patel

https://arxiv.org/pdf/2201.01293v1.pdf

This paper presents a transformer-based Siamese network architecture (abbreviated by ChangeFormer) for Change Detection (CD) from a pair of co-registered remote sensing images. Different from recent CD frameworks, which are based on fully convolutional networks (ConvNets), the proposed method unifies hierarchically structured transformer encoder with Multi-Layer Perception (MLP) decoder in a Siamese network architecture to efficiently render multi-scale long-range details required for accurate CD.

2022: W. G. C. Bandara, Vishal M. Patel

https://arxiv.org/pdf/2201.01293v1.pdf

This paper presents a transformer-based Siamese network architecture (abbreviated by ChangeFormer) for Change Detection (CD) from a pair of co-registered remote sensing images. Different from recent CD frameworks, which are based on fully convolutional networks (ConvNets), the proposed method unifies hierarchically structured transformer encoder with Multi-Layer Perception (MLP) decoder in a Siamese network architecture to efficiently render multi-scale long-range details required for accurate CD.

2022: W. G. C. Bandara, Vishal M. Patel

https://arxiv.org/pdf/2201.01293v1.pdf

Multi-scale representations are crucial for semantic segmentation. The community has witnessed the flourish of semantic segmentation convolutional neural networks (CNN) exploiting multi-scale contextual information. Motivated by that the vision transformer (ViT) is powerful in image classification, some semantic segmentation ViTs are recently proposed, most of them attaining impressive results but at a cost of computational economy. In this paper, we succeed in introducing multi-scale representations into semantic segmentation ViT via window attention mechanism and further improves the performance and efficiency.

2022: Haotian Yan, Chuang Zhang, Ming Wu

https://arxiv.org/pdf/2201.01615v1.pdf

We propose a novel LiDAR-InertialVisual sensor fusion framework termed RLIVE, which takes advantage of measurement of LiDAR, inertial, and visual sensors to achieve robust and accurate state estimation. RLIVE is contained of two subsystems, the LiDAR-inertial odometry (LIO) and visual-inertial odometry (VIO).

2021: Jiarong Lin, Fu Zhang

https://arxiv.org/pdf/2109.07982v1.pdf

This paper presents a transformer-based Siamese network architecture (abbreviated by ChangeFormer) for Change Detection (CD) from a pair of co-registered remote sensing images. Different from recent CD frameworks, which are based on fully convolutional networks (ConvNets), the proposed method unifies hierarchically structured transformer encoder with Multi-Layer Perception (MLP) decoder in a Siamese network architecture to efficiently render multi-scale long-range details required for accurate CD.

2022: W. G. C. Bandara, Vishal M. Patel

https://arxiv.org/pdf/2201.01293v1.pdf

Audio-based automatic speech recognition (ASR) degrades significantly in noisy environments and is particularly vulnerable to interfering speech, as the model cannot determine which speaker to transcribe. Audio-visual speech recognition (AVSR) systems improve robustness by complementing the audio stream with the visual information that is invariant to noise and helps the model focus on the desired speaker.

2022: Bowen Shi, Wei-Ning Hsu, Abdelrahman Mohamed

https://arxiv.org/pdf/2201.01763v1.pdf

Knowledge distillation is an effective approach to leverage a well-trained network or an ensemble of them, named as the teacher, to guide the training of a student network. The outputs from the teacher network are used as soft labels for supervising the training of a new network. Recent studies (Müller et al., 2019; Yuan et al., 2020) revealed an intriguing property of the soft labels that making labels soft serves as a good regularization to the student network.

2021: Helong Zhou, Liangchen Song, Jiajie Chen, Ye Zhou, Guoli Wang, Junsong Yuan, Qian Zhang

https://arxiv.org/pdf/2102.00650v1.pdf

Recently, the Vision Transformer (ViT), which applied the transformer structure to the image classification task, has outperformed convolutional neural networks. However, the high performance of the ViT results from pre-training using a large-size dataset such as JFT-300M, and its dependence on a large dataset is interpreted as due to low locality inductive bias. This paper proposes Shifted Patch Tokenization (SPT) and Locality Self-Attention (LSA), which effectively solve the lack of locality inductive bias and enable it to learn from scratch even on small-size datasets.

2021: Seung Hoon Lee, Seunghyun Lee, Byung Cheol Song

https://arxiv.org/pdf/2112.13492v1.pdf