Research on Patch Attentive Neural Process
Not on the map. Why?
Abstract (arXiv)
Attentive Neural Process (ANP) improves the fitting ability of Neural Process (NP) and improves its prediction accuracy, but the higher time complexity of the model imposes a limitation on the length of the input sequence. Inspired by models such as Vision Transformer (ViT) and Masked Auto-Encoder (MAE), we propose Patch Attentive Neural Process (PANP) using image patches as input and improve the structure of deterministic paths based on ANP, which allows the model to extract image features more accurately and efficiently reconstruction.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 11 of its 14 references that are in the map. First posted on arXiv 29 Jan 2022.
Builds on
11 of 14 references.
References · 11
- 2017Attention Is All You Needcited by 60,361
- 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
- 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,403
- 2013Auto-Encoding Variational Bayescited by 4,053
- 2017Non-local Neural Networkscited by 2,293
- 2018Image Transformercited by 772
- 2018Conditional Neural Processescited by 426
- 2020Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentationcited by 326
- 2018Neural Processescited by 311
- 2019On the Relationship between Self-Attention and Convolutional Layerscited by 300
- 2019Attentive Neural Processescited by 283
Built on by
Citing papers per year: 2022: 1.
1 paper.