中文
相关论文

相关论文: ViT-VS: On the Applicability of Pretrained Vision …

200 篇论文

Autonomy in robot-assisted minimally invasive surgery has the potential to reduce surgeon cognitive and task load, thereby increasing procedural efficiency. However, implementing accurate autonomous control can be difficult due to poor…

机器人学 · 计算机科学 2026-03-18 Shuyuan Yang , Zonghe Chua

This paper proposes a new approach to achieve direct visual servoing (DVS) based on discrete orthogonal moments (DOMs). DVS is performed in such a way that the extraction of geometric primitives, matching, and tracking steps in the…

机器人学 · 计算机科学 2024-02-14 Yuhan Chen , Max Q. -H. Meng , Li Liu

We study a crucial yet often overlooked issue inherent to Vision Transformers (ViTs): feature maps of these models exhibit grid-like artifacts, which hurt the performance of ViTs in downstream dense prediction tasks such as semantic…

计算机视觉与模式识别 · 计算机科学 2024-07-23 Jiawei Yang , Katie Z Luo , Jiefeng Li , Congyue Deng , Leonidas Guibas , Dilip Krishnan , Kilian Q Weinberger , Yonglong Tian , Yue Wang

One of the central challenges preventing robots from acquiring complex manipulation skills is the prohibitive cost of collecting large-scale robot demonstrations. In contrast, humans are able to learn efficiently by watching others interact…

机器人学 · 计算机科学 2025-11-13 Changhe Chen , Quantao Yang , Xiaohao Xu , Nima Fazeli , Olov Andersson

Learning general-purpose models from diverse datasets has achieved great success in machine learning. In robotics, however, existing methods in multi-task learning are typically constrained to a single robot and workspace, while recent work…

机器人学 · 计算机科学 2024-10-15 Xinyu Zhang , Yuhan Liu , Haonan Chang , Abdeslam Boularias

We present a method for semantically transferring the visual appearance of one natural image to another. Specifically, our goal is to generate an image in which objects in a source structure image are "painted" with the visual appearance of…

计算机视觉与模式识别 · 计算机科学 2022-01-04 Narek Tumanyan , Omer Bar-Tal , Shai Bagon , Tali Dekel

This work presents a simple vision transformer design as a strong baseline for object localization and instance segmentation tasks. Transformers recently demonstrate competitive performance in image classification tasks. To adopt ViT to…

计算机视觉与模式识别 · 计算机科学 2022-10-04 Wuyang Chen , Xianzhi Du , Fan Yang , Lucas Beyer , Xiaohua Zhai , Tsung-Yi Lin , Huizhong Chen , Jing Li , Xiaodan Song , Zhangyang Wang , Denny Zhou

We apply pre-trained Vision Transformers (ViTs), originally developed for image recognition, to the analysis of astronomical spectral data. By converting traditional one-dimensional spectra into two-dimensional image representations, we…

天体物理仪器与方法 · 物理学 2026-05-13 Luis Felipe Strano Moraes , Ignacio Becker , Pavlos Protopapas , Guillermo Cabrera-Vives

This paper presents a detailed study of improving visual representations for vision language (VL) tasks and develops an improved object detection model to provide object-centric representations of images. Compared to the most widely used…

计算机视觉与模式识别 · 计算机科学 2021-03-11 Pengchuan Zhang , Xiujun Li , Xiaowei Hu , Jianwei Yang , Lei Zhang , Lijuan Wang , Yejin Choi , Jianfeng Gao

In order to autonomously learn wide repertoires of complex skills, robots must be able to learn from their own autonomously collected data, without human supervision. One learning signal that is always available for autonomously collected…

机器人学 · 计算机科学 2017-10-18 Frederik Ebert , Chelsea Finn , Alex X. Lee , Sergey Levine

Transformer design is the de facto standard for natural language processing tasks. The success of the transformer design in natural language processing has lately piqued the interest of researchers in the domain of computer vision. When…

计算机视觉与模式识别 · 计算机科学 2024-02-29 Md Sohag Mia , Abu Bakor Hayat Arnob , Abdu Naim , Abdullah Al Bary Voban , Md Shariful Islam

In recent years, vision transformers (ViTs) have emerged as powerful and promising techniques for computer vision tasks such as image classification, object detection, and segmentation. Unlike convolutional neural networks (CNNs), which…

计算机视觉与模式识别 · 计算机科学 2025-05-20 Shaibal Saha , Lanyu Xu

The current popular methods for video object segmentation (VOS) implement feature matching through several hand-crafted modules that separately perform feature extraction and matching. However, the above hand-crafted designs empirically…

计算机视觉与模式识别 · 计算机科学 2023-08-22 Qiangqiang Wu , Tianyu Yang , Wei WU , Antoni Chan

Imitation learning has proven to be highly effective in teaching robots dexterous manipulation skills. However, it typically relies on large amounts of human demonstration data, which limits its scalability and applicability in dynamic,…

机器人学 · 计算机科学 2025-03-03 Minjie Zhu , Yichen Zhu , Jinming Li , Zhongyi Zhou , Junjie Wen , Xiaoyu Liu , Chaomin Shen , Yaxin Peng , Feifei Feng

Vision transformers have demonstrated remarkable success in classification by leveraging global self-attention to capture long-range dependencies. However, this same mechanism can obscure fine-grained spatial details crucial for tasks such…

计算机视觉与模式识别 · 计算机科学 2026-03-06 Sina Hajimiri , Farzad Beizaee , Fereshteh Shakeri , Christian Desrosiers , Ismail Ben Ayed , Jose Dolz

Recently, end-to-end robotic manipulation models have gained significant attention for their generalizability and scalability. However, they often suffer from limited robustness to camera viewpoint changes when training with a fixed camera.…

机器人学 · 计算机科学 2026-04-24 Songen Gu , Yuhang Zheng , Weize Li , Yupeng Zheng , Yating Feng , Xiang Li , Yilun Chen , Pengfei Li , Wenchao Ding

Visual pre-training with large-scale real-world data has made great progress in recent years, showing great potential in robot learning with pixel observations. However, the recipes of visual pre-training for robot manipulation tasks are…

机器人学 · 计算机科学 2023-08-08 Ya Jing , Xuelin Zhu , Xingbin Liu , Qie Sima , Taozheng Yang , Yunhai Feng , Tao Kong

Pretrained vision foundation models (VFMs) advance robotic learning via rich visual representations, yet individual VFMs typically excel only in specific domains, limiting generality across tasks. Distilling multiple VFMs into a unified…

In this paper, we propose a transformer based approach for visual grounding. Unlike previous proposal-and-rank frameworks that rely heavily on pretrained object detectors or proposal-free frameworks that upgrade an off-the-shelf one-stage…

计算机视觉与模式识别 · 计算机科学 2022-03-15 Ye Du , Zehua Fu , Qingjie Liu , Yunhong Wang

This paper presents an adaptive visual servoing framework for robotic on-orbit servicing (OOS), specifically designed for capturing tumbling satellites. The vision-guided robotic system is capable of selecting optimal control actions in the…

机器人学 · 计算机科学 2024-09-10 Farhad Aghili