English
Related papers

Related papers: MeSa: Masked, Geometric, and Supervised Pre-traini…

200 papers

Self-supervised learning (SSL) on 3D point clouds has the potential to learn feature representations that can transfer to diverse sensors and multiple downstream perception tasks. However, recent SSL approaches fail to define pretext tasks…

Computer Vision and Pattern Recognition · Computer Science 2025-03-19 Barza Nisar , Steven L. Waslander

Self-supervised learning (SSL) has demonstrated significant potential in pre-training robust models with limited labeled data, making it particularly valuable for remote sensing (RS) tasks. A common assumption is that pre-training on…

Computer Vision and Pattern Recognition · Computer Science 2025-02-18 Saad Lahrichi , Zion Sheng , Shufan Xia , Kyle Bradbury , Jordan Malof

Self-supervised pretraining is the method of choice for natural language processing models and is rapidly gaining popularity in many vision tasks. Recently, self-supervised pretraining has shown to outperform supervised pretraining for many…

Computer Vision and Pattern Recognition · Computer Science 2021-12-01 Sara Atito , Muhammad Awais , Ammarah Farooq , Zhenhua Feng , Josef Kittler

Magnetic Resonance Imaging (MRI) represents an important diagnostic modality; however, its inherently slow acquisition process poses challenges in obtaining fully-sampled $k$-space data under motion. In the absence of fully-sampled…

Image and Video Processing · Electrical Eng. & Systems 2024-12-23 George Yiasemis , Nikita Moriakov , Clara I. Sánchez , Jan-Jakob Sonke , Jonas Teuwen

Self-supervised monocular depth estimation (SSMDE) aims to predict the dense depth map of a monocular image, by learning depth from RGB image sequences, eliminating the need for ground-truth depth labels. Although this approach simplifies…

Computer Vision and Pattern Recognition · Computer Science 2025-02-21 Wonhyeok Choi , Kyumin Hwang , Wei Peng , Minwoo Choi , Sunghoon Im

Most existing public face datasets, such as MS-Celeb-1M and VGGFace2, provide abundant information in both breadth (large number of IDs) and depth (sufficient number of samples) for training. However, in many real-world scenarios of face…

Computer Vision and Pattern Recognition · Computer Science 2020-07-17 Hang Du , Hailin Shi , Yuchi Liu , Jun Wang , Zhen Lei , Dan Zeng , Tao Mei

Previous monocular depth estimation methods take a single view and directly regress the expected results. Though recent advances are made by applying geometrically inspired loss functions during training, the inference procedure does not…

Computer Vision and Pattern Recognition · Computer Science 2018-03-12 Yue Luo , Jimmy Ren , Mude Lin , Jiahao Pang , Wenxiu Sun , Hongsheng Li , Liang Lin

Self-supervised learning is an efficient pre-training method for medical image analysis. However, current research is mostly confined to specific-modality data pre-training, consuming considerable time and resources without achieving…

Computer Vision and Pattern Recognition · Computer Science 2023-12-01 Yiwen Ye , Yutong Xie , Jianpeng Zhang , Ziyang Chen , Qi Wu , Yong Xia

Video-based pretraining offers immense potential for learning strong visual representations on an unprecedented scale. Recently, masked video modeling methods have shown promising scalability, yet fall short in capturing higher-level…

Computer Vision and Pattern Recognition · Computer Science 2024-07-23 Mohammadreza Salehi , Michael Dorkenwald , Fida Mohammad Thoker , Efstratios Gavves , Cees G. M. Snoek , Yuki M. Asano

Self-supervised landmark estimation is a challenging task that demands the formation of locally distinct feature representations to identify sparse facial landmarks in the absence of annotated data. To tackle this task, existing…

Computer Vision and Pattern Recognition · Computer Science 2024-05-29 Kejia Yin , Varshanth R. Rao , Ruowei Jiang , Xudong Liu , Parham Aarabi , David B. Lindell

Depth estimation is critical for any robotic system. In the past years estimation of depth from monocular images have shown great improvement, however, in the underwater environment results are still lagging behind due to appearance changes…

Computer Vision and Pattern Recognition · Computer Science 2022-10-10 Shlomi Amitai , Itzik Klein , Tali Treibitz

Semantic segmentation of satellite imagery is crucial for Earth observation applications, but remains constrained by limited labelled training data. While self-supervised pretraining methods like Masked Autoencoders (MAE) have shown…

Computer Vision and Pattern Recognition · Computer Science 2025-07-17 John Waithaka , Moise Busogi

Supervised deep learning often suffers from the lack of sufficient training data. Specifically in the context of monocular depth map prediction, it is barely possible to determine dense ground truth depth images in realistic dynamic outdoor…

Computer Vision and Pattern Recognition · Computer Science 2017-05-15 Yevhen Kuznietsov , Jörg Stückler , Bastian Leibe

Majority of state-of-the-art monocular depth estimation methods are supervised learning approaches. The success of such approaches heavily depends on the high-quality depth labels which are expensive to obtain. Some recent methods try to…

Computer Vision and Pattern Recognition · Computer Science 2019-11-27 Yipeng Mou , Mingming Gong , Huan Fu , Kayhan Batmanghelich , Kun Zhang , Dacheng Tao

Self-supervised monocular depth estimation has shown impressive results in static scenes. It relies on the multi-view consistency assumption for training networks, however, that is violated in dynamic object regions and occlusions.…

Computer Vision and Pattern Recognition · Computer Science 2023-10-06 Libo Sun , Jia-Wang Bian , Huangying Zhan , Wei Yin , Ian Reid , Chunhua Shen

Strong gravitational lensing can reveal the influence of dark-matter substructure in galaxies, but analyzing these effects from noisy, low-resolution images poses a significant challenge. In this work, we propose a masked autoencoder (MAE)…

Depth estimation from a single image is an active research topic in computer vision. The most accurate approaches are based on fully supervised learning models, which rely on a large amount of dense and high-resolution (HR) ground-truth…

Computer Vision and Pattern Recognition · Computer Science 2021-09-27 Jialei Xu , Yuanchao Bai , Xianming Liu , Junjun Jiang , Xiangyang Ji

Deep Neural Networks are powerful tools for understanding complex patterns and making decisions. However, their black-box nature impedes a complete understanding of their inner workings. Saliency-Guided Training (SGT) methods try to…

Computer Vision and Pattern Recognition · Computer Science 2023-10-12 Ali Karkehabadi , Houman Homayoun , Avesta Sasan

Few-shot learning (FSL) is a central problem in meta-learning, where learners must efficiently learn from few labeled examples. Within FSL, feature pre-training has recently become an increasingly popular strategy to significantly improve…

Machine Learning · Computer Science 2023-11-07 Ruohan Wang , Isak Falk , Massimiliano Pontil , Carlo Ciliberto

This paper tackles the challenges of self-supervised monocular depth estimation in indoor scenes caused by large rotation between frames and low texture. We ease the learning process by obtaining coarse camera poses from monocular sequences…

Computer Vision and Pattern Recognition · Computer Science 2023-09-29 Chaoqiang Zhao , Matteo Poggi , Fabio Tosi , Lei Zhou , Qiyu Sun , Yang Tang , Stefano Mattoccia