Accurate fine-grained geospatial scene classification using remote sensing imagery is essential for a wide range of applications. However, existing approaches often rely on manually zooming remote sensing images at different scales to create typical scene samples. This approach fails to adequately support the fixed-resolution image interpretation requirements in real-world scenarios. To address this limitation, we introduce the Million-scale finE-grained geospatial scEne classification dataseT (MEET), which contains over 1.03 million zoom-free remote sensing scene samples, manually annotated into 80 fine-grained categories. In MEET, each scene sample follows a scene-inscene layout, where the central scene serves as the reference, and auxiliary scenes provide crucial spatial context for finegrained classification. Moreover, to tackle the emerging challenge of scene-in-scene classification, we present the Context-Aware Transformer (CAT), a model specifically designed for this task, which adaptively fuses spatial context to accurately classify the scene samples. CAT adaptively fuses spatial context to accurately classify the scene samples by learning attentional features that capture the relationships between the center and auxiliary scenes. Based on MEET, we establish a comprehensive benchmark for fine-grained geospatial scene classification, evaluating CAT against 11 competitive baselines. The results demonstrate that CAT significantly outperforms these baselines, achieving a 1.88% higher balanced accuracy (BA) with the Swin-Large backbone, and a notable 7.87% improvement with the Swin-Huge backbone. Further experiments validate the effectiveness of each module in CAT and show the practical applicability of CAT in the urban functional zone mapping. The source code and dataset will be publicly available at https://jerrywyn.github.io/project/MEET.html.

We aim at exploiting additional auxiliary labels from an independent (auxiliary) task to boost the primary task performance which we focus on, while preserving a single task inference cost of the primary task. While most existing auxiliary learning methods are optimization-based relying on loss weights/gradients manipulation, our method is architecture-based with a flexible asymmetric structure for the primary and auxiliary tasks, which produces different networks for training and inference. Specifically, starting from two single task networks/branches (each representing a task), we propose a novel method with evolving networks where only primary-to-auxiliary links exist as the cross-task connections after convergence. These connections can be removed during the primary task inference, resulting in a single-task inference cost. We achieve this by formulating a Neural Architecture Search (NAS) problem, where we initialize bi-directional connections in the search space and guide the NAS optimization converging to an architecture with only the single-side primary-to-auxiliary connections. Moreover, our method can be incorporated with optimization-based auxiliary learning approaches. In this paper, we tackle the practical issue of auxiliary learning, which involves improving the performance of a specific task (i.e., the primary task) while incorporating additional auxiliary labels from different tasks (i.e., the auxiliary tasks). We aim to efficiently leverage these auxiliary labels to enhance the primary task's performance while maintaining a comparable computational and parameter cost to a single-task network when evaluating the primary task.

In this research, we introduce MaeFuse, a novel autoencoder model designed for infrared and visible image fusion (IVIF). The existing approaches for image fusion often rely on training combined with downstream tasks to obtain high-level visual information, which is effective in emphasizing target objects and delivering impressive results in visual quality and task-specific applications. MaeFuse, however, deviates from the norm. Instead of being driven by downstream tasks, our model utilizes a pretrained encoder from Masked Autoencoders (MAE), which facilities the omni features extraction for low-level reconstruction and high-level vision tasks, to obtain perception friendly features with a low cost. In order to eliminate the domain gap of different modal features and the block effect caused by the MAE encoder, we further develop a guided training strategy. This strategy is meticulously crafted to ensure that the fusion layer seamlessly adjusts to the feature space of the encoder, gradually enhancing the fusion effect. It facilitates the comprehensive integration of feature vectors from both infrared and visible modalities, preserving the rich details inherent in each. MaeFuse not only introduces a novel perspective in the realm of fusion techniques but also stands out with impressive performance across various public datasets.

For a long time, due to the high heterogeneity in structure and semantics among various spatiotemporal modal data, the joint interpretation of multimodal spatiotemporal data has been an extremely challenging problem. The primary challenge resides in striking a trade-off between the cohesion and autonomy of diverse modalities, and this trade-off exhibits a progressively nonlinear nature as the number of modalities expands. We introduce the Language as Reference Framework (LaRF), a fundamental principle for constructing a multimodal unified model, aiming to strike a trade-off between the cohesion and autonomy among different modalities. We propose a multimodal spatiotemporal general artificial intelligence model, called AllSpark. Our model integrates thirteen different modalities into a unified framework, including 1D (text, code), 2D (RGB, infrared, SAR, multispectral, hyperspectral, tables, graphs, trajectory, oblique photography), and 3D (point clouds, videos) modalities. To achieve modal cohesion, AllSpark uniformly maps diverse modal features to the language modality. In addition, we design modality-specific prompts to guide multi-modal large language models in accurately perceiving multimodal data. To maintain modality autonomy, AllSpark introduces modality-specific encoders to extract the tokens of various spatiotemporal modalities. And modal bridge is employed to achieve dimensional projection from each modality to the language modality. Finally, observing a gap between the model's interpretation and downstream tasks, we designed task heads to enhance the model's generalization capability on specific downstream tasks. Experiments indicate that AllSpark achieves competitive accuracy in modalities such as RGB and trajectory compared to state-of-the-art models.

Deep-learning-based local feature extraction algorithms that combine detection and description have made significant progress in visible image matching. However, the end-to-end training of such frameworks is notoriously unstable due to the lack of strong supervision of detection and the inappropriate coupling between detection and description. The problem is magnified in cross-modal scenarios, in which most methods heavily rely on the pre-training. In this paper, we recouple independent constraints of detection and description of multimodal feature learning with a mutual weighting strategy, in which the detected probabilities of robust features are forced to peak and repeat, while features with high detection scores are emphasized during optimization. Different from previous works, those weights are detached from back propagation so that the detected probability of indistinct features would not be directly suppressed and the training would be more stable. Moreover, we propose the Super Detector, a detector that possesses a large receptive field and is equipped with learnable non-maximum suppression layers, to fulfill the harsh terms of detection. Finally, we build a benchmark that contains cross visible, infrared, near-infrared and synthetic aperture radar image pairs for evaluating the performance of features in feature matching and image registration tasks. Extensive experiments demonstrate that features trained with the recoulped detection and description, named ReDFeat, surpass previous state-of-the-arts in the benchmark, while the model can be readily trained from scratch.

Modifications on triplet loss that rescale the back-propagated gradients of special pairs have made significant progress on local descriptor learning. However, current gradient modulation strategies are mainly static so that they would suffer from changes of training phases or datasets. In this paper, we propose a dynamic gradient modulation, named SDGMNet, to improve triplet loss for local descriptor learning. The core of our method is formulating modulation functions with statistical characteristics which are estimated dynamically. Firstly, we perform deep analysis on back propagation of general triplet-based loss and introduce included angle for distance measure. On this basis, auto-focus modulation is employed to moderate the impact of statistically uncommon individual pairs in stochastic gradient descent optimization; probabilistic margin cuts off the gradients of proportional Siamese pairs that are believed to reach the optimum; power adjustment balances the total weights of negative pairs and positive pairs. Extensive experiments demonstrate that our novel descriptor surpasses previous state-of-the-arts on standard benchmarks including patch verification, matching and retrieval tasks.

In this paper, we propose a robust transformation estimation method based on manifold regularization for non-rigid point set registration. The method iteratively recovers the point correspondence and estimates the spatial transformation between two point sets. The correspondence is established based on existing local feature descriptors which typically results in a number of outliers. To achieve an accurate estimate of the transformation from such putative point correspondence, we formulate the registration problem by a mixture model with a set of latent variables introduced to identify outliers, and a prior involving manifold regularization is imposed on the transformation to capture the underlying intrinsic geometry of the input data. The non-rigid transformation is specified in a reproducing kernel Hilbert space and a sparse approximation is adopted to achieve a fast implementation. Extensive experiments on both 2D and 3D data demonstrate that our method can yield superior results compared to other state-of-the-arts, especially in case of badly degraded data.