Scaling Efficient Masked Image Modeling on Large Remote Sensing Dataset

• URL: http://arxiv.org/abs/2406.11933v4
• Date: Fri, 06 Dec 2024 15:10:36 GMT
• Title: Scaling Efficient Masked Image Modeling on Large Remote Sensing Dataset
• Authors: Fengxiang Wang, Hongzhen Wang, Di Wang, Zonghao Guo, Zhenyu Zhong, Long Lan, Jing Zhang, Zhiyuan Liu, Maosong Sun,
• Abstract summary: We present a new pre-training pipeline for RS models, featuring the creation of a large-scale RS dataset and an efficient MIM approach. We curated a high-quality dataset named OpticalRS-13M by collecting publicly available RS datasets and processing them through exclusion, slicing, and deduplication. Experiments demonstrate that OpticalRS-13M significantly improves classification, detection, and segmentation performance, while SelectiveMAE increases training efficiency over 2 times.
• Score: 66.15872913664407
• License:
• Abstract: Masked Image Modeling (MIM) has become an essential method for building foundational visual models in remote sensing (RS). However, the limitations in size and diversity of existing RS datasets restrict the ability of MIM methods to learn generalizable representations. Additionally, conventional MIM techniques, which require reconstructing all tokens, introduce unnecessary computational overhead. To address these issues, we present a new pre-training pipeline for RS models, featuring the creation of a large-scale RS dataset and an efficient MIM approach. We curated a high-quality dataset named OpticalRS-13M by collecting publicly available RS datasets and processing them through exclusion, slicing, and deduplication. OpticalRS-13M comprises 13 million optical images covering various RS tasks, such as object detection and pixel segmentation. To enhance efficiency, we propose SelectiveMAE, a pre-training method that dynamically encodes and reconstructs semantically rich patch tokens, thereby reducing the inefficiencies of traditional MIM models caused by redundant background pixels in RS images. Extensive experiments demonstrate that OpticalRS-13M significantly improves classification, detection, and segmentation performance, while SelectiveMAE increases training efficiency over 2 times. This highlights the effectiveness and scalability of our pipeline in developing RS foundational models.

Related papers

• Cross-Scan Mamba with Masked Training for Robust Spectral Imaging [51.557804095896174]
  We propose the Cross-Scanning Mamba, named CS-Mamba, that employs a Spatial-Spectral SSM for global-local balanced context encoding. Experiment results show that our CS-Mamba achieves state-of-the-art performance and the masked training method can better reconstruct smooth features to improve the visual quality.
  arXiv  Detail & Related papers  (2024-08-01T15:14:10Z)
• Discriminative Hamiltonian Variational Autoencoder for Accurate Tumor Segmentation in Data-Scarce Regimes [2.8498944632323755]
  We propose an end-to-end hybrid architecture for medical image segmentation. We use Hamiltonian Variational Autoencoders (HVAE) and a discriminative regularization to improve the quality of generated images. Our architecture operates on a slice-by-slice basis to segment 3D volumes, capitilizing on the richly augmented dataset.
  arXiv  Detail & Related papers  (2024-06-17T15:42:08Z)
• Rotated Multi-Scale Interaction Network for Referring Remote Sensing Image Segmentation [63.15257949821558]
  Referring Remote Sensing Image (RRSIS) is a new challenge that combines computer vision and natural language processing. Traditional Referring Image (RIS) approaches have been impeded by the complex spatial scales and orientations found in aerial imagery. We introduce the Rotated Multi-Scale Interaction Network (RMSIN), an innovative approach designed for the unique demands of RRSIS.
  arXiv  Detail & Related papers  (2023-12-19T08:14:14Z)
• RingMo-lite: A Remote Sensing Multi-task Lightweight Network with CNN-Transformer Hybrid Framework [15.273362355253779]
  This paper proposes RingMo-lite, an RS multi-task lightweight network with a CNN-Transformer hybrid framework to optimize the interpretation process. The proposed RingMo-lite reduces the parameters over 60% in various RS image interpretation tasks, the average accuracy drops by less than 2% in most of the scenes and achieves SOTA performance compared to models of the similar size.
  arXiv  Detail & Related papers  (2023-09-16T14:15:59Z)
• Improving Pixel-based MIM by Reducing Wasted Modeling Capability [77.99468514275185]
  We propose a new method that explicitly utilizes low-level features from shallow layers to aid pixel reconstruction. To the best of our knowledge, we are the first to systematically investigate multi-level feature fusion for isotropic architectures. Our method yields significant performance gains, such as 1.2% on fine-tuning, 2.8% on linear probing, and 2.6% on semantic segmentation.
  arXiv  Detail & Related papers  (2023-08-01T03:44:56Z)
• Disruptive Autoencoders: Leveraging Low-level features for 3D Medical Image Pre-training [51.16994853817024]
  This work focuses on designing an effective pre-training framework for 3D radiology images. We introduce Disruptive Autoencoders, a pre-training framework that attempts to reconstruct the original image from disruptions created by a combination of local masking and low-level perturbations. The proposed pre-training framework is tested across multiple downstream tasks and achieves state-of-the-art performance.
  arXiv  Detail & Related papers  (2023-07-31T17:59:42Z)
• PixMIM: Rethinking Pixel Reconstruction in Masked Image Modeling [83.67628239775878]
  Masked Image Modeling (MIM) has achieved promising progress with the advent of Masked Autoencoders (MAE) and BEiT. This paper undertakes a fundamental analysis of MIM from the perspective of pixel reconstruction. We propose a remarkably simple and effective method, ourmethod, that entails two strategies.
  arXiv  Detail & Related papers  (2023-03-04T13:38:51Z)
• Exploring a Fine-Grained Multiscale Method for Cross-Modal Remote Sensing Image Retrieval [21.05804942940532]
  Cross-modal text-image retrieval has attracted extensive attention for its advantages of flexible input and efficient query. To cope with the problem of multi-scale scarcity and target redundancy in RS multimodal retrieval task, we come up with a novel asymmetric multimodal feature matching network (AMFMN) Our model adapts to multi-scale feature inputs, favors multi-source retrieval methods, and can dynamically filter redundant features.
  arXiv  Detail & Related papers  (2022-04-21T03:53:19Z)
• DML-GANR: Deep Metric Learning With Generative Adversarial Network Regularization for High Spatial Resolution Remote Sensing Image Retrieval [9.423185775609426]
  We develop a deep metric learning approach with generative adversarial network regularization (DML-GANR) for HSR-RSI retrieval. The experimental results on the three data sets demonstrate the superior performance of DML-GANR over state-of-the-art techniques in HSR-RSI retrieval.
  arXiv  Detail & Related papers  (2020-10-07T02:26:03Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.