English
Related papers

Related papers: A Light Touch Approach to Teaching Transformers Mu…

200 papers

The Transformer is an extremely powerful and prominent deep learning architecture. In this work, we challenge the commonly held belief in deep learning that going deeper is better, and show an alternative design approach that is building…

Machine Learning · Computer Science 2022-11-10 Jason Ross Brown , Yiren Zhao , Ilia Shumailov , Robert D Mullins

We introduce a scalable approach for object pose estimation trained on simulated RGB views of multiple 3D models together. We learn an encoding of object views that does not only describe an implicit orientation of all objects seen during…

Computer Vision and Pattern Recognition · Computer Science 2020-04-06 Martin Sundermeyer , Maximilian Durner , En Yen Puang , Zoltan-Csaba Marton , Narunas Vaskevicius , Kai O. Arras , Rudolph Triebel

Non-prehensile manipulation is challenging due to complex contact interactions between objects, the environment, and robots. Model-based approaches can efficiently generate complex trajectories of robots and objects under contact…

Robotics · Computer Science 2025-08-07 Yuki Shirai , Kei Ota , Devesh K. Jha , Diego Romeres

Video understanding requires reasoning at multiple spatiotemporal resolutions -- from short fine-grained motions to events taking place over longer durations. Although transformer architectures have recently advanced the state-of-the-art,…

Computer Vision and Pattern Recognition · Computer Science 2022-06-01 Shen Yan , Xuehan Xiong , Anurag Arnab , Zhichao Lu , Mi Zhang , Chen Sun , Cordelia Schmid

In this work, we propose TransTrack, a simple but efficient scheme to solve the multiple object tracking problems. TransTrack leverages the transformer architecture, which is an attention-based query-key mechanism. It applies object…

Computer Vision and Pattern Recognition · Computer Science 2021-05-05 Peize Sun , Jinkun Cao , Yi Jiang , Rufeng Zhang , Enze Xie , Zehuan Yuan , Changhu Wang , Ping Luo

In-hand object reorientation has been a challenging problem in robotics due to high dimensional actuation space and the frequent change in contact state between the fingers and the objects. We present a simple model-free framework that can…

Robotics · Computer Science 2021-11-05 Tao Chen , Jie Xu , Pulkit Agrawal

The smoothness of the transformer architecture has been extensively studied in the context of generalization, training stability, and adversarial robustness. However, its role in transfer learning remains poorly understood. In this paper,…

Machine Learning · Computer Science 2026-02-10 Ambroise Odonnat , Laetitia Chapel , Romain Tavenard , Ievgen Redko

Existing generative approaches for guided image synthesis of multi-object scenes typically rely on 2D controls in the image or text space. As a result, these methods struggle to maintain and respect consistent three-dimensional geometric…

Computer Vision and Pattern Recognition · Computer Science 2025-08-05 Léopold Maillard , Tom Durand , Adrien Ramanana Rahary , Maks Ovsjanikov

Conventional wisdom suggests that pre-training Vision Transformers (ViT) improves downstream performance by learning useful representations. Is this actually true? We investigate this question and find that the features and representations…

Machine Learning · Computer Science 2024-11-15 Alexander C. Li , Yuandong Tian , Beidi Chen , Deepak Pathak , Xinlei Chen

It is challenging for humans -- particularly those living with physical disabilities -- to control high-dimensional, dexterous robots. Prior work explores learning embedding functions that map a human's low-dimensional inputs (e.g., via a…

Robotics · Computer Science 2021-05-04 Siddharth Karamcheti , Albert J. Zhai , Dylan P. Losey , Dorsa Sadigh

We present MVTOP, a novel transformer-based method for multi-view rigid object pose estimation. Through an early fusion of the view-specific features, our method can resolve pose ambiguities that would be impossible to solve with a single…

Computer Vision and Pattern Recognition · Computer Science 2026-03-24 Lukas Ranftl , Felix Brendel , Bertram Drost , Carsten Steger

Recurrent neural networks are effective models to process sequences. However, they are unable to learn long-term dependencies because of their inherent sequential nature. As a solution, Vaswani et al. introduced the Transformer, a model…

Machine Learning · Computer Science 2023-03-28 Quentin Fournier , Gaétan Marceau Caron , Daniel Aloise

Multiview diffusion models have rapidly emerged as a powerful tool for content creation with spatial consistency across viewpoints, offering rich visual realism without requiring explicit geometry and appearance representation. However,…

Computer Vision and Pattern Recognition · Computer Science 2025-12-11 Hubert Kompanowski , Varun Jampani , Aaryaman Vasishta , Binh-Son Hua

Currently, manipulation tasks for deformable objects often focus on activities like folding clothes, handling ropes, and manipulating bags. However, research on contact-rich tasks involving deformable objects remains relatively…

Robotics · Computer Science 2026-03-06 Yuhang Zhang , Jinming Ma , Feng Wu

In many automation tasks involving manipulation of rigid objects, the poses of the objects must be acquired. Vision-based pose estimation using a single RGB or RGB-D sensor is especially popular due to its broad applicability. However,…

Computer Vision and Pattern Recognition · Computer Science 2023-03-24 Rasmus Laurvig Haugaard , Thorbjørn Mosekjær Iversen

6D object pose estimation is a crucial prerequisite for autonomous robot manipulation applications. The state-of-the-art models for pose estimation are convolutional neural network (CNN)-based. Lately, Transformers, an architecture…

Computer Vision and Pattern Recognition · Computer Science 2023-07-24 Arul Selvam Periyasamy , Arash Amini , Vladimir Tsaturyan , Sven Behnke

This paper investigates the challenge of learning image manifolds, specifically pose manifolds, of 3D objects using limited training data. It proposes a DNN approach to manifold learning and for predicting images of objects for novel,…

Computer Vision and Pattern Recognition · Computer Science 2023-05-19 Shenyuan Liang , Pavan Turaga , Anuj Srivastava

Robotic manipulation tasks often rely on static cameras for perception, which can limit flexibility, particularly in scenarios like robotic surgery and cluttered environments where mounting static cameras is impractical. Ideally, robots…

Robotics · Computer Science 2025-09-18 Xiatao Sun , Francis Fan , Yinxing Chen , Daniel Rakita

For certain manipulation tasks, object pose estimation from head-mounted cameras may not be sufficiently accurate. This is at least in part due to our inability to perfectly calibrate the coordinate frames of today's high degree of freedom…

Robotics · Computer Science 2022-04-12 Patrick Lancaster , Boling Yang , Joshua R. Smith

Vision transformers (ViTs) have found only limited practical use in processing images, in spite of their state-of-the-art accuracy on certain benchmarks. The reason for their limited use include their need for larger training datasets and…

Computer Vision and Pattern Recognition · Computer Science 2022-01-26 Pranav Jeevan , Amit sethi