Ar-Spider: Text-to-SQL in Arabic

In Natural Language Processing (NLP), one of the most important tasks is text-to-SQL semantic parsing, which focuses on enabling users to interact with the database in a more natural manner. In recent years, text-to-SQL has made significant progress, but most were English-centric. In this paper, we introduce Ar-Spider 1, the first Arabic cross-domain text-to-SQL dataset. Due to the unique nature of the language, two major challenges have been encountered, namely schema linguistic and SQL structural challenges. In order to handle these issues and conduct the experiments, we adopt two baseline models LGESQL [4] and S2SQL [12], both of which are tested with two cross-lingual models to alleviate the effects of schema linguistic and SQL structure linking challenges. The baselines demonstrate decent single-language performance on our Arabic text-to-SQL dataset, Ar-Spider, achieving 62.48% for S2SQL and 65.57% for LGESQL, only 8.79% below the highest results achieved by the baselines when trained in English dataset. To achieve better performance on Arabic text-to-SQL, we propose the context similarity relationship (CSR) approach, which results in a significant increase in the overall performance of about 1.52% for S2SQL and 1.06% for LGESQL and closes the gap between Arabic and English languages to 7.73%.

Learning Semantic Proxies from Visual Prompts for Parameter-Efficient Fine-Tuning in Deep Metric Learning

Deep Metric Learning (DML) has long attracted the attention of the machine learning community as a key objective. Existing solutions concentrate on fine-tuning the pre-trained models on conventional image datasets. As a result of the success of recent pre-trained models trained from larger-scale datasets, it is challenging to adapt the model to the DML tasks in the local data domain while retaining the previously gained knowledge. In this paper, we investigate parameter-efficient methods for fine-tuning the pre-trained model for DML tasks. In particular, we propose a novel and effective framework based on learning Visual Prompts (VPT) in the pre-trained Vision Transformers (ViT). Based on the conventional proxy-based DML paradigm, we augment the proxy by incorporating the semantic information from the input image and the ViT, in which we optimize the visual prompts for each class. We demonstrate that our new approximations with semantic information are superior to representative capabilities, thereby improving metric learning performance. We conduct extensive experiments to demonstrate that our proposed framework is effective and efficient by evaluating popular DML benchmarks. In particular, we demonstrate that our fine-tuning method achieves comparable or even better performance than recent state-of-the-art full fine-tuning works of DML while tuning only a small percentage of total parameters.

BA-LINS: A Frame-to-Frame Bundle Adjustment for LiDAR-Inertial Navigation

Bundle Adjustment (BA) has been proven to improve the accuracy of the LiDAR mapping. However, the BA method has not been properly employed in a dead-reckoning navigation system. In this paper, we present a frame-to-frame (F2F) BA for LiDAR-inertial navigation, named BA-LINS. Based on the direct F2F point-cloud association, the same-plane points are associated among the LiDAR keyframes. Hence, the plane-point BA measurement can be constructed using the same-plane points. The LiDAR BA measurements and the inertial measurement unit (IMU)-preintegration measurements are tightly integrated under the framework of factor graph optimization. An effective adaptive covariance estimation algorithm for LiDAR BA measurements is proposed to further improve the accuracy of BA-LINS. We conduct exhaustive real-world experiments on public and private datasets to examine the proposed BA-LINS. The results demonstrate that BA-LINS yields superior accuracy to state-of-the-art methods. Compared to the baseline system FF-LINS, the absolute translation accuracy and state-estimation efficiency of BA-LINS are improved by 29.5% and 28.7%, respectively, on the private dataset. Besides, the ablation experiment results exhibit that the proposed adaptive covariance estimation algorithm can notably improve the accuracy and robustness of BA-LINS.

Towards Improved Proxy-based Deep Metric Learning via Data-Augmented Domain Adaptation

Deep Metric Learning (DML) plays an important role in modern computer vision research, where we learn a distance metric for a set of image representations. Recent DML techniques utilize the proxy to interact with the corresponding image samples in the embedding space. However, existing proxy-based DML methods focus on learning individual proxy-to-sample distance while the overall distribution of samples and proxies lacks attention. In this paper, we present a novel proxy-based DML framework that focuses on aligning the sample and proxy distributions to improve the efficiency of proxy-based DML losses. Specifically, we propose the Data-Augmented Domain Adaptation (DADA) method to adapt the domain gap between the group of samples and proxies. To the best of our knowledge, we are the first to leverage domain adaptation to boost the performance of proxy-based DML. We show that our method can be easily plugged into existing proxy-based DML losses. Our experiments on benchmarks, including the popular CUB-200-2011, CARS196, Stanford Online Products, and In-Shop Clothes Retrieval, show that our learning algorithm significantly improves the existing proxy losses and achieves superior results compared to the existing methods.

SE-LIO: Semantics-enhanced Solid-State-LiDAR-Inertial Odometry for Tree-rich Environments

In this letter, we propose a semantics-enhanced solid-state-LiDAR-inertial odometry (SE-LIO) in tree-rich environments. Multiple LiDAR frames are first merged and compensated with the inertial navigation system (INS) to increase the point-cloud coverage, thus improving the accuracy of semantic segmentation. The unstructured point clouds, such as tree leaves and dynamic objects, are then removed with the semantic information. Furthermore, the pole-like point clouds, primarily tree trunks, are modeled as cylinders to improve positioning accuracy. An adaptive piecewise cylinder-fitting method is proposed to accommodate environments with a high prevalence of curved tree trunks. Finally, the iterated error-state Kalman filter (IESKF) is employed for state estimation. Point-to-cylinder and point-to-plane constraints are tightly coupled with the prior constraints provided by the INS to obtain the maximum a posteriori estimation. Targeted experiments are conducted in complex campus and park environments to evaluate the performance of SE-LIO. The proposed methods, including removing the unstructured point clouds and the adaptive cylinder fitting, yield improved accuracy. Specifically, the positioning accuracy of the proposed SE-LIO is improved by 43.1% compared to the plane-based LIO.

Multi-modal Domain Adaptation for REG via Relation Transfer

Domain adaptation, which aims to transfer knowledge between domains, has been well studied in many areas such as image classification and object detection. However, for multi-modal tasks, conventional approaches rely on large-scale pre-training. But due to the difficulty of acquiring multi-modal data, large-scale pre-training is often impractical. Therefore, domain adaptation, which can efficiently utilize the knowledge from different datasets (domains), is crucial for multi-modal tasks. In this paper, we focus on the Referring Expression Grounding (REG) task, which is to localize an image region described by a natural language expression. Specifically, we propose a novel approach to effectively transfer multi-modal knowledge through a specially relation-tailored approach for the REG problem. Our approach tackles the multi-modal domain adaptation problem by simultaneously enriching inter-domain relations and transferring relations between domains. Experiments show that our proposed approach significantly improves the transferability of multi-modal domains and enhances adaptation performance in the REG problem.

FF-LINS: A Consistent Frame-to-Frame Solid-State-LiDAR-Inertial State Estimator

Most of the existing LiDAR-inertial navigation systems are based on frame-to-map registrations, leading to inconsistency in state estimation. The newest solid-state LiDAR with a non-repetitive scanning pattern makes it possible to achieve a consistent LiDAR-inertial estimator by employing a frame-to-frame data association. In this letter, we propose a robust and consistent frame-to-frame LiDAR-inertial navigation system (FF-LINS) for solid-state LiDARs. With the INS-centric LiDAR frame processing, the keyframe point-cloud map is built using the accumulated point clouds to construct the frame-to-frame data association. The LiDAR frame-to-frame and the inertial measurement unit (IMU) preintegration measurements are tightly integrated using the factor graph optimization, with online calibration of the LiDAR-IMU extrinsic and time-delay parameters. The experiments on the public and private datasets demonstrate that the proposed FF-LINS achieves superior accuracy and robustness than the state-of-the-art systems. Besides, the LiDAR-IMU extrinsic and time-delay parameters are estimated effectively, and the online calibration notably improves the pose accuracy. The proposed FF-LINS and the employed datasets are open-sourced on GitHub (https://github.com/i2Nav-WHU/FF-LINS).

PO-VINS: An Efficient Pose-Only LiDAR-Enhanced Visual-Inertial State Estimator

The pose-only (PO) visual representation has been proven to be equivalent to the classical multiple-view geometry, while significantly improving computational efficiency. However, its applicability for real-world navigation in large-scale complex environments has not yet been demonstrated. In this study, we present an efficient pose-only LiDAR-enhanced visual-inertial navigation system (PO-VINS) to enhance the real-time performance of the state estimator. In the visual-inertial state estimator (VISE), we propose a pose-only visual-reprojection measurement model that only contains the inertial measurement unit (IMU) pose and extrinsic-parameter states. We further integrated the LiDAR-enhanced method to construct a pose-only LiDAR-depth measurement model. Real-world experiments were conducted in large-scale complex environments, demonstrating that the proposed PO-VISE and LiDAR-enhanced PO-VISE reduce computational complexity by more than 50% and over 20%, respectively. Additionally, the PO-VINS yields the same accuracy as conventional methods. These results indicate that the pose-only solution is efficient and applicable for real-time visual-inertial state estimation.

On Calibrating Semantic Segmentation Models: Analysis and An Algorithm

We study the problem of semantic segmentation calibration. For image classification, lots of existing solutions are proposed to alleviate model miscalibration of confidence. However, to date, confidence calibration research on semantic segmentation is still limited. We provide a systematic study on the calibration of semantic segmentation models and propose a simple yet effective approach. First, we find that model capacity, crop size, multi-scale testing, and prediction correctness have impact on calibration. Among them, prediction correctness, especially misprediction, is more important to miscalibration due to over-confidence. Next, we propose a simple, unifying, and effective approach, namely selective scaling, by separating correct/incorrect prediction for scaling and more focusing on misprediction logit smoothing. Then, we study popular existing calibration methods and compare them with selective scaling on semantic segmentation calibration. We conduct extensive experiments with a variety of benchmarks on both in-domain and domain-shift calibration, and show that selective scaling consistently outperforms other methods.

CTIN: Robust Contextual Transformer Network for Inertial Navigation

Recently, data-driven inertial navigation approaches have demonstrated their capability of using well-trained neural networks to obtain accurate position estimates from inertial measurement units (IMU) measurements. In this paper, we propose a novel robust Contextual Transformer-based network for Inertial Navigation~(CTIN) to accurately predict velocity and trajectory. To this end, we first design a ResNet-based encoder enhanced by local and global multi-head self-attention to capture spatial contextual information from IMU measurements. Then we fuse these spatial representations with temporal knowledge by leveraging multi-head attention in the Transformer decoder. Finally, multi-task learning with uncertainty reduction is leveraged to improve learning efficiency and prediction accuracy of velocity and trajectory. Through extensive experiments over a wide range of inertial datasets~(e.g. RIDI, OxIOD, RoNIN, IDOL, and our own), CTIN is very robust and outperforms state-of-the-art models.