Graph contrastive learning (GCL) is a promising direction toward alleviating the label dependence, poor generalization and weak robustness of graph neural networks, learning representations with invariance, and discriminability by solving pretasks. The pretasks are mainly built on mutual information estimation, which requires data augmentation to construct positive samples with similar semantics to learn invariant signals and negative samples with dissimilar semantics to empower representation discriminability. However, an appropriate data augmentation configuration depends heavily on lots of empirical trials such as choosing the compositions of data augmentation techniques and the corresponding hyperparameter settings. We propose an augmentation-free GCL method, invariant-discriminative GCL (iGCL), that does not intrinsically require negative samples. iGCL designs the invariant-discriminative loss (ID loss) to learn invariant and discriminative representations. On the one hand, ID loss learns invariant signals by directly minimizing the mean square error (MSE) between the target samples and positive samples in the representation space. On the other hand, ID loss ensures that the representations are discriminative by an orthonormal constraint forcing the different dimensions of representations to be independent of each other. This prevents representations from collapsing to a point or subspace. Our theoretical analysis explains the effectiveness of ID loss from the perspectives of the redundancy reduction criterion, canonical correlation analysis (CCA), and information bottleneck (IB) principle. The experimental results demonstrate that iGCL outperforms all baselines on five node classification benchmark datasets. iGCL also shows superior performance for different label ratios and is capable of resisting graph attacks, which indicates that iGCL has excellent generalization and robustness. The source code is available at https://github.com/lehaifeng/ T-GCN/tree/master/iGCL.

The increase in self-supervised learning (SSL), especially contrastive learning, has enabled one to train deep neural network models with unlabeled data for remote sensing image (RSI) scene classification. Nevertheless, it still suffers from the following issues: 1) the performance of the contrastive learning method is significantly impacted by the hard negative sample (HNS) issue, since the RSI scenario is complex in semantics and rich in surface features; 2) the multiscale characteristic of RSI is missed in the existing contrastive learning methods; and 3) as the backbone of a deep learning model, especially in the case of limited annotation, a convolutional neural network (CNN) does not include the adequate receptive field of convolutional kernels to capture the broad contextual information of RSI. In this regard, we propose label-free self-distillation contrastive learning with a transformer architecture (LaST). We introduce the self-distillation contrastive learning mechanism to address the HNS issue. Specifically, the LaST architecture comprises two modules: scale alignment with a multicrop module and a long-range dependence capture backbone module. In the former, we present global–local crop and scale alignment to encourage local-to-global correspondence and acquire multiscale relations. Then, the distorted views are fed into a transformer as a backbone, which is good at capturing the long-range-dependent contextual information of the RSI while maintaining the spatial smoothness of the learned features. Experiments on public datasets show that in the downstream scene classification task, LaST improves the performance of the self-supervised trained model by a maximum of 2.18% compared to the HNS-impacted contrastive learning approaches, and only 1.5% of labeled data can achieve the performance of supervised training CNNs with 10% labeled data. Moreover, this letter supports the integration of a transformer architecture and self-supervised paradigms in RSI interpretation.

Self-supervised contrastive learning (SSCL) is a potential learning paradigm for learning remote sensing image (RSI)-invariant features through the label-free method. The existing SSCL of RSI is built based on constructing positive and negative sample pairs. However, due to the richness of RSI ground objects and the complexity of the RSI contextual semantics, the same RSI patches have the coexistence and imbalance of positive and negative samples, which causing the SSCL pushing negative samples far away while pushing positive samples far away, and vice versa. We call this the sample confounding issue (SCI). To solve this problem, we propose a False negAtive sampLes aware contraStive lEarning model (FALSE) for the semantic segmentation of high-resolution RSIs. Since the SSCL pretraining is unsupervised, the lack of definable criteria for false negative sample (FNS) leads to theoretical undecidability, we designed two steps to implement the FNS approximation determination: coarse determination of FNS and precise calibration of FNS. We achieve coarse determination of FNS by the FNS self-determination (FNSD) strategy and achieve calibration of FNS by the FNS confidence calibration (FNCC) loss function. Experimental results on three RSI semantic segmentation datasets demonstrated that the FALSE effectively improves the accuracy of the downstream RSI semantic segmentation task compared with the current three models, which represent three different types of SSCL models. The mean Intersection-over-Union on ISPRS Potsdam dataset is improved by 0.7% on average; on CVPR DGLC dataset is improved by 12.28% on average; and on Xiangtan dataset this is improved by 1.17% on average. This indicates that the SSCL model has the ability to self-differentiate FNS and that the FALSE effectively mitigates the SCI in self-supervised contrastive learning.

The segmentation of airborne laser scanning (ALS) point clouds remains a challenge in remote sensing and photogrammetry. Deep learning methods, such as KPCONV, have proven effective on various datasets. However, the rigid convolutional kernel strategy of KPCONV limits its potential use for 3D object segmentation due to its uniform approach. To address this issue, we propose an Integrated Point Convolution (IPCONV) based on KPCONV, which utilizes two different convolution kernel point generation strategies, one cylindrical and one a spherical cone, for more efficient learning of point cloud data features. We propose a customizable Multi-Shape Neighborhood System (MSNS) to balance the relationship between these convolution kernel point generations. Experiments on the ISPRS benchmark dataset, LASDU dataset, and DFC2019 dataset demonstrate the validity of our method.

3D Transformers have advanced point cloud understanding, but prevalent token generation methods (e.g., Farthest Point Sampling and k-Nearest Neighbors clustering) over-rely on geometric properties while neglecting semantic information. In urban scene point clouds, these methods cannot easily form semantically homogeneous neighborhoods, which forces semantic confusion in point tokens and weakening the self-attention mechanism's ability to model token similarity. Additionally, processing large-scale point clouds leads to excessive tokens, imposing high computational costs of attention calculations and reducing efficiency. Therefore, from the perspective of semantic information, this paper re-examines the point token generation problem and accordingly proposes an efficient 3D Transformer with Semantic Aggregated point Tokenizer (SAT-Former) for point cloud semantic segmentation in urban scenes. The developed tokenizer comprises two key modules: the Relation Reasoning Module (RRM) and the Feature Mapping Module (FMM). RRM captures inter-token relationships, generating semantic homogeneity guidance to effectively transmission and integrate semantic information, thereby reducing semantic confusion. FMM maps point-level features onto the semantically homogeneous guided tokens generated by RRM, enhancing token expressiveness while preserving essential details. We evaluate SAT-Former on three urban scene point cloud datasets: Hessigheim 3D (H3D), Toronto-3D (T3D), and SensatUrban, demonstrating competitive performance and up to $30\times$ faster inference efficiency than baseline methods while maintaining >95% of their accuracy. Additionally, extensive visualization experiments highlight the semantic homogeneity and feature representativeness of the generated tokens, providing insights into the model's internal mechanisms and validating its effectiveness.

Deep Neural Network (DNN)-based point cloud semantic segmentation has presented significant breakthrough using large-scale labeled aerial laser point cloud datasets. However, annotating such large-scaled point clouds is time-consuming. Self-Supervised Learning (SSL) is a promising approach to this problem by pre-training a DNN model utilizing unlabeled samples followed by a fine-tuned downstream task involving very limited labels. The traditional contrastive learning for point clouds selects the hardest negative samples by solely relying on the distance between the embedded features derived from the learning process, potentially evolving some negative samples from the same classes to reduce the contrastive learning effectiveness. This work proposes a hard-negative sample-aware self-supervised contrastive learning algorithm to pre-train the model for semantic segmentation. We designed a k-means clustering-based Absolute Positive And Negative samples (AbsPAN) strategy to filter the possible false-negative samples. Experiments on two typical ALS benchmark datasets demonstrate that the proposed method is more appealing than supervised training schemes without pre-training. Especially when the labels are severely inadequate (10% of the ISPRS training set), the results obtained by the proposed HAVANA method still exceed 94% of the supervised paradigm performance with full training set.