English
Related papers

Related papers: A Data-Centric Revisit of Pre-Trained Vision Model…

200 papers

The Vision Transformer (ViT) has demonstrated remarkable performance in Self-Supervised Learning (SSL) for 3D medical image analysis. Masked AutoEncoder (MAE) for feature pre-training can further unleash the potential of ViT on various…

Computer Vision and Pattern Recognition · Computer Science 2025-01-13 Jiaxin Zhuang , Linshan Wu , Qiong Wang , Peng Fei , Varut Vardhanabhuti , Lin Luo , Hao Chen

In recent years, a number of models that learn the relations between vision and language from large datasets have been released. These models perform a variety of tasks, such as answering questions about images, retrieving sentences that…

Robotics · Computer Science 2024-03-19 Kento Kawaharazuka , Yoshiki Obinata , Naoaki Kanazawa , Kei Okada , Masayuki Inaba

We present OrbiSim, a novel robotic simulation paradigm that redefines world models as a fully differentiable physics engine for embodied intelligence. Unlike prior world models that focus on unconstrained imagination in latent or visual…

Robotics · Computer Science 2026-05-19 Jiajian Li , Jingyuan Huang , Junru Gong , Qi Wang , Xiaokang Yang , Yunbo Wang

Self-supervised learning (SSL) has attracted much interest in remote sensing and earth observation due to its ability to learn task-agnostic representations without human annotation. While most of the existing SSL works in remote sensing…

Computer Vision and Pattern Recognition · Computer Science 2022-06-15 Yi Wang , Conrad M Albrecht , Xiao Xiang Zhu

Recent years have seen significant advancements in foundation models through generative pre-training, yet algorithmic innovation in this space has largely stagnated around autoregressive models for discrete signals and diffusion models for…

Machine Learning · Computer Science 2025-03-12 Jiaming Song , Linqi Zhou

We introduce UViM, a unified approach capable of modeling a wide range of computer vision tasks. In contrast to previous models, UViM has the same functional form for all tasks; it requires no task-specific modifications which require…

Computer Vision and Pattern Recognition · Computer Science 2022-10-17 Alexander Kolesnikov , André Susano Pinto , Lucas Beyer , Xiaohua Zhai , Jeremiah Harmsen , Neil Houlsby

Vision-centric autonomous driving has recently raised wide attention due to its lower cost. Pre-training is essential for extracting a universal representation. However, current vision-centric pre-training typically relies on either 2D or…

Computer Vision and Pattern Recognition · Computer Science 2024-05-08 Chen Min , Dawei Zhao , Liang Xiao , Jian Zhao , Xinli Xu , Zheng Zhu , Lei Jin , Jianshu Li , Yulan Guo , Junliang Xing , Liping Jing , Yiming Nie , Bin Dai

Mobile service robots are increasingly prevalent in human-centric, real-world domains, operating autonomously in unconstrained indoor environments. In such a context, robotic vision plays a central role in enabling service robots to…

Robotics · Computer Science 2025-10-20 Michele Antonazzi , Matteo Luperto , N. Alberto Borghese , Nicola Basilico

In this paper, we introduce a novel self-supervised learning (SSL) loss for image representation learning. There is a growing belief that generalization in deep neural networks is linked to their ability to discriminate object shapes. Since…

Computer Vision and Pattern Recognition · Computer Science 2023-03-14 Sepehr Sameni , Simon Jenni , Paolo Favaro

Recent studies have explored pretrained (foundation) models for vision-based robotic navigation, aiming to achieve generalizable navigation and positive transfer across diverse environments while enhancing zero-shot performance in unseen…

Autoregressive language modeling (ALM) have been successfully used in self-supervised pre-training in Natural language processing (NLP). However, this paradigm has not achieved comparable results with other self-supervised approach in…

Computer Vision and Pattern Recognition · Computer Science 2022-12-06 Yu Qi , Fan Yang , Yousong Zhu , Yufei Liu , Liwei Wu , Rui Zhao , Wei Li

In this paper, we present a comparative analysis of various self-supervised Vision Transformers (ViTs), focusing on their local representative power. Inspired by large language models, we examine the abilities of ViTs to perform various…

Computer Vision and Pattern Recognition · Computer Science 2024-03-22 Ani Vanyan , Alvard Barseghyan , Hakob Tamazyan , Vahan Huroyan , Hrant Khachatrian , Martin Danelljan

Masked Image Modeling (MIM) is a technique in self-supervised learning that focuses on acquiring detailed visual representations from unlabeled images by estimating the missing pixels in randomly masked sections. It has proven to be a…

Computer Vision and Pattern Recognition · Computer Science 2024-12-16 Khanh-Binh Nguyen , Chae Jung Park

Recent self-supervised learning models simulate the development of semantic object representations by training on visual experience similar to that of toddlers. However, these models ignore the foveated nature of human vision with high/low…

Computer Vision and Pattern Recognition · Computer Science 2025-09-22 Zhengyang Yu , Arthur Aubret , Chen Yu , Jochen Triesch

Embodied learning for object-centric robotic manipulation is a rapidly developing and challenging area in embodied AI. It is crucial for advancing next-generation intelligent robots and has garnered significant interest recently. Unlike…

Robotics · Computer Science 2025-01-15 Ying Zheng , Lei Yao , Yuejiao Su , Yi Zhang , Yi Wang , Sicheng Zhao , Yiyi Zhang , Lap-Pui Chau

The ability to predict future outcomes given control actions is fundamental for physical reasoning. However, such predictive models, often called world models, remains challenging to learn and are typically developed for task-specific…

Robotics · Computer Science 2025-02-04 Gaoyue Zhou , Hengkai Pan , Yann LeCun , Lerrel Pinto

Recently, masked image modeling (MIM) has become a promising direction for visual pre-training. In the context of vision transformers, MIM learns effective visual representation by aligning the token-level features with a pre-defined space…

Computer Vision and Pattern Recognition · Computer Science 2022-03-11 Longhui Wei , Lingxi Xie , Wengang Zhou , Houqiang Li , Qi Tian

Predictive models have been at the core of many robotic systems, from quadrotors to walking robots. However, it has been challenging to develop and apply such models to practical robotic manipulation due to high-dimensional sensory…

Robotics · Computer Science 2020-09-14 Lucas Manuelli , Yunzhu Li , Pete Florence , Russ Tedrake

The visual world offers a critical axis for advancing foundation models beyond language. Despite growing interest in this direction, the design space for native multimodal models remains opaque. We provide empirical clarity through…

Masked Image Modeling (MIM) techniques have redefined the landscape of computer vision, enabling pre-trained models to achieve exceptional performance across a broad spectrum of tasks. Despite their success, the full potential of MIM-based…

Computer Vision and Pattern Recognition · Computer Science 2024-09-05 Sumin Son , Hyesong Choi , Dongbo Min