English
Related papers

Related papers: MATE: Masked Autoencoders are Online 3D Test-Time …

200 papers

Recent advances in Earth Observation have focused on large-scale foundation models. However, these models are computationally expensive, limiting their accessibility and reuse for downstream tasks. In this work, we investigate compact…

Computer Vision and Pattern Recognition · Computer Science 2025-09-16 Mohanad Albughdadi

We propose Masked-Attention Transformers for Surgical Instrument Segmentation (MATIS), a two-stage, fully transformer-based method that leverages modern pixel-wise attention mechanisms for instrument segmentation. MATIS exploits the…

Computer Vision and Pattern Recognition · Computer Science 2024-01-29 Nicolás Ayobi , Alejandra Pérez-Rondón , Santiago Rodríguez , Pablo Arbeláez

The application of deep learning to 3D point clouds is challenging due to its lack of order. Inspired by the point embeddings of PointNet and the edge embeddings of DGCNNs, we propose three improvements to the task of point cloud analysis.…

Computer Vision and Pattern Recognition · Computer Science 2021-04-09 Chaitanya Kaul , Nick Pears , Suresh Manandhar

Predicting the future of surrounding agents and accordingly planning a safe, goal-directed trajectory are crucial for automated vehicles. Current methods typically rely on imitation learning to optimize metrics against the ground truth,…

Robotics · Computer Science 2025-07-15 Yangang Ren , Guojian Zhan , Chen Lv , Jun Li , Fenghua Liang , Keqiang Li

Self-supervised learning has attracted increasing attention as it learns data-driven representation from data without annotations. Vision transformer-based autoencoder (ViT-AE) by He et al. (2021) is a recent self-supervised learning…

Computer Vision and Pattern Recognition · Computer Science 2023-05-17 Chinmay Prabhakar , Hongwei Bran Li , Jiancheng Yang , Suprosana Shit , Benedikt Wiestler , Bjoern Menze

This paper studies the potential of distilling knowledge from pre-trained models, especially Masked Autoencoders. Our approach is simple: in addition to optimizing the pixel reconstruction loss on masked inputs, we minimize the distance…

Computer Vision and Pattern Recognition · Computer Science 2022-11-11 Yutong Bai , Zeyu Wang , Junfei Xiao , Chen Wei , Huiyu Wang , Alan Yuille , Yuyin Zhou , Cihang Xie

Masked Autoencoders is a simple yet powerful self-supervised learning method. However, it learns representations indirectly by reconstructing masked input patches. Several methods learn representations directly by predicting representations…

Audio and Speech Processing · Electrical Eng. & Systems 2023-03-03 Daisuke Niizumi , Daiki Takeuchi , Yasunori Ohishi , Noboru Harada , Kunio Kashino

Point clouds obtained from 3D scans are typically sparse, irregular, and noisy, and required to be consolidated. In this paper, we present the first deep learning based edge-aware technique to facilitate the consolidation of point clouds.…

Computer Vision and Pattern Recognition · Computer Science 2018-07-18 Lequan Yu , Xianzhi Li , Chi-Wing Fu , Daniel Cohen-Or , Pheng-Ann Heng

The popularity of pre-trained large models has revolutionized downstream tasks across diverse fields, such as language, vision, and multi-modality. To minimize the adaption cost for downstream tasks, many Parameter-Efficient Fine-Tuning…

Computer Vision and Pattern Recognition · Computer Science 2024-10-22 Yiwen Tang , Ray Zhang , Zoey Guo , Dong Wang , Zhigang Wang , Bin Zhao , Xuelong Li

Unsupervised domain adaptation object detection (UDAOD) research on Detection Transformer(DETR) mainly focuses on feature alignment and existing methods can be divided into two kinds, each of which has its unresolved issues. One-stage…

Computer Vision and Pattern Recognition · Computer Science 2024-01-19 Weixi Weng , Chun Yuan

In this paper, we introduce a Model-based Algorithm Turning Engine, namely MATE, where the parameters of an algorithm are represented as expressions of the features of a target optimisation problem. In contrast to most static…

Neural and Evolutionary Computing · Computer Science 2021-02-16 Mohamed El Yafrani , Marcella Scoczynski Ribeiro Martins , Inkyung Sung , Markus Wagner , Carola Doerr , Peter Nielsen

Point cloud is a fundamental 3D representation which is widely used in real world applications such as autonomous driving. As a newly-developed media format which is characterized by complexity and irregularity, point cloud creates a need…

Computer Vision and Pattern Recognition · Computer Science 2019-05-10 Wei Yan , Yiting shao , Shan Liu , Thomas H Li , Zhu Li , Ge Li

There have been recent efforts to learn more meaningful representations via fixed length codewords from mesh data, since a mesh serves as a complete model of underlying 3D shape compared to a point cloud. However, the mesh connectivity…

Computer Vision and Pattern Recognition · Computer Science 2023-08-30 Eric Lei , Muhammad Asad Lodhi , Jiahao Pang , Junghyun Ahn , Dong Tian

With the overwhelming trend of mask image modeling led by MAE, generative pre-training has shown a remarkable potential to boost the performance of fundamental models in 2D vision. However, in 3D vision, the over-reliance on…

Computer Vision and Pattern Recognition · Computer Science 2023-09-08 Ziyi Wang , Xumin Yu , Yongming Rao , Jie Zhou , Jiwen Lu

Masked auto-encoding is a popular and effective self-supervised learning approach to point cloud learning. However, most of the existing methods reconstruct only the masked points and overlook the local geometry information, which is also…

Computer Vision and Pattern Recognition · Computer Science 2022-07-08 Yabin Zhang , Jiehong Lin , Chenhang He , Yongwei Chen , Kui Jia , Lei Zhang

Nowadays, pre-training big models on large-scale datasets has become a crucial topic in deep learning. The pre-trained models with high representation ability and transferability achieve a great success and dominate many downstream tasks in…

Computer Vision and Pattern Recognition · Computer Science 2022-10-13 Ziyi Wang , Xumin Yu , Yongming Rao , Jie Zhou , Jiwen Lu

The emerging trend in computer vision emphasizes developing universal models capable of simultaneously addressing multiple diverse tasks. Such universality typically requires joint training across multi-domain datasets to ensure effective…

Computer Vision and Pattern Recognition · Computer Science 2025-05-01 Eunsoo Im , Changhyun Jee , Jung Kwon Lee

Masked point modeling methods have recently achieved great success in self-supervised learning for point cloud data. However, these methods are sensitive to rotations and often exhibit sharp performance drops when encountering rotational…

Computer Vision and Pattern Recognition · Computer Science 2024-12-30 Kunming Su , Qiuxia Wu , Panpan Cai , Xiaogang Zhu , Xuequan Lu , Zhiyong Wang , Kun Hu

Understanding the internal representations of large language models is crucial for ensuring their reliability and safety, with sparse autoencoders (SAEs) emerging as a promising interpretability approach. However, current SAE training…

Machine Learning · Computer Science 2025-10-13 T. Ed Li , Junyu Ren

Designing a single neural network architecture that performs competitively across a range of molecule property prediction tasks remains largely an open challenge, and its solution may unlock a widespread use of deep learning in the drug…

Machine Learning · Computer Science 2021-02-10 Łukasz Maziarka , Tomasz Danel , Sławomir Mucha , Krzysztof Rataj , Jacek Tabor , Stanisław Jastrzębski