English
Related papers

Related papers: Beyond flattening: a geometrically principled posi…

200 papers

Fourier features based positional encoding (PE) is commonly used in machine learning tasks that involve learning high-frequency features from low-dimensional inputs, such as 3D view synthesis and time series regression with neural tangent…

Machine Learning · Computer Science 2024-07-18 Chuanhao Sun , Zhihang Yuan , Kai Xu , Luo Mai , N. Siddharth , Shuo Chen , Mahesh K. Marina

Is the center position fully capable of representing a pixel? There is nothing wrong to represent pixels with their centers in a discrete image representation, but it makes more sense to consider each pixel as the aggregation of signals…

Image and Video Processing · Electrical Eng. & Systems 2021-12-14 Ying-Tian Liu , Yuan-Chen Guo , Song-Hai Zhang

In this study, we investigate the impact of positional encoding (PE) on source separation performance and the generalization ability to long sequences (length extrapolation) in Transformer-based time-frequency (TF) domain dual-path models.…

Audio and Speech Processing · Electrical Eng. & Systems 2025-06-03 Kohei Saijo , Tetsuji Ogawa

Position Embeddings (PEs), an arguably indispensable component in Vision Transformers (ViTs), have been shown to improve the performance of ViTs on many vision tasks. However, PEs have a potentially high risk of privacy leakage since the…

Computer Vision and Pattern Recognition · Computer Science 2023-05-29 Bin Ren , Yahui Liu , Yue Song , Wei Bi , Rita Cucchiara , Nicu Sebe , Wei Wang

This paper presents an investigation of vision transformer learning for multi-view geometry tasks, such as optical flow estimation, by fine-tuning video foundation models. Unlike previous methods that involve custom architectural designs…

Computer Vision and Pattern Recognition · Computer Science 2025-12-23 Huimin Wu , Kwang-Ting Cheng , Stephen Lin , Zhirong Wu

Transformer architectures rely on position encodings to model the spatial structure of input data. Rotary Position Encoding (RoPE) is a widely used method in language models that encodes relative positions through fixed, block-diagonal,…

Computer Vision and Pattern Recognition · Computer Science 2025-08-19 Sophie Ostmeier , Brian Axelrod , Maya Varma , Michael E. Moseley , Akshay Chaudhari , Curtis Langlotz

How discriminative position information is for image classification depends on the data. On the one hand, the camera position is arbitrary and objects can appear anywhere in the image, arguing for translation invariance. At the same time,…

Computer Vision and Pattern Recognition · Computer Science 2025-05-20 Robert-Jan Bruintjes , Jan van Gemert

Recent advances in Transformer models allow for unprecedented sequence lengths, due to linear space and time complexity. In the meantime, relative positional encoding (RPE) was proposed as beneficial for classical Transformers and consists…

Machine Learning · Computer Science 2021-06-11 Antoine Liutkus , Ondřej Cífka , Shih-Lun Wu , Umut Şimşekli , Yi-Hsuan Yang , Gaël Richard

Graph Transformers (GTs) facilitate the comprehension of graph-structured data by calculating the self-attention of node pairs without considering node position information. To address this limitation, we introduce an innovative and…

Machine Learning · Computer Science 2023-12-12 Kushal Bose , Swagatam Das

Detecting 3D objects accurately from multi-view 2D images is a challenging yet essential task in the field of autonomous driving. Current methods resort to integrating depth prediction to recover the spatial information for object query…

Computer Vision and Pattern Recognition · Computer Science 2025-10-20 Haisheng Su , Junjie Zhang , Feixiang Song , Sanping Zhou , Wei Wu , Nanning Zheng , Junchi Yan

While recent advances in machine learning have equipped Weather Foundation Models (WFMs) with substantial generalization capabilities across diverse downstream tasks, the escalating computational requirements associated with their expanding…

Accurately estimating the pose of an object is a crucial task in computer vision and robotics. There are two main deep learning approaches for this: geometric representation regression and iterative refinement. However, these methods have…

Computer Vision and Pattern Recognition · Computer Science 2024-01-30 Jaewoo Park , Jaeguk Kim , Nam Ik Cho

Relative position embedding has become a standard mechanism for encoding positional information in Transformers. However, existing formulations are typically limited to a fixed geometric space, namely 1D sequences or regular 2D/3D grids,…

Computer Vision and Pattern Recognition · Computer Science 2026-04-22 Yichen Xie , Depu Meng , Chensheng Peng , Yihan Hu , Quentin Herau , Masayoshi Tomizuka , Wei Zhan

Vision Transformers trained only on image classification routinely transfer to tasks that demand spatial understanding, yet they receive no spatial supervision during pretraining. We ask where and how robustly such structure is encoded.…

Computer Vision and Pattern Recognition · Computer Science 2026-04-28 Jainum Sanghavi

With the scale of vision Transformer-based models continuing to grow, finetuning these large-scale pretrained models for new tasks has become increasingly parameter-intensive. Visual prompt tuning is introduced as a parameter-efficient…

Computer Vision and Pattern Recognition · Computer Science 2024-11-19 Runjia Zeng , Cheng Han , Qifan Wang , Chunshu Wu , Tong Geng , Lifu Huang , Ying Nian Wu , Dongfang Liu

Despite the success of Transformers on language understanding, code generation, and logical reasoning, they still fail to generalize over length on basic arithmetic tasks such as addition and multiplication. A major reason behind this…

Machine Learning · Computer Science 2024-06-05 Mahdi Sabbaghi , George Pappas , Hamed Hassani , Surbhi Goel

Positional embeddings (PE) play a crucial role in Vision Transformers (ViTs) by providing spatial information otherwise lost due to the permutation invariant nature of self attention. While absolute positional embeddings (APE) have shown…

Computer Vision and Pattern Recognition · Computer Science 2026-04-14 Md Abtahi Majeed Chowdhury , Md Rifat Ur Rahman , Akil Ahmad Taki

We introduce an unsupervised technique for encoding point clouds into a canonical shape representation, by disentangling shape and pose. Our encoder is stable and consistent, meaning that the shape encoding is purely pose-invariant, while…

Computer Vision and Pattern Recognition · Computer Science 2022-04-05 Oren Katzir , Dani Lischinski , Daniel Cohen-Or

We propose position-velocity encoders (PVEs) which learn---without supervision---to encode images to positions and velocities of task-relevant objects. PVEs encode a single image into a low-dimensional position state and compute the…

Robotics · Computer Science 2017-07-25 Rico Jonschkowski , Roland Hafner , Jonathan Scholz , Martin Riedmiller

Length generalization, the ability to generalize from small training context sizes to larger ones, is a critical challenge in the development of Transformer-based language models. Positional encoding (PE) has been identified as a major…

Computation and Language · Computer Science 2023-11-08 Amirhossein Kazemnejad , Inkit Padhi , Karthikeyan Natesan Ramamurthy , Payel Das , Siva Reddy