实时动态环境感知对于拥挤空间的自动机器人至关重要。尽管流行的基于体素的映射方法可以有效地用任意复杂的形状代表3D障碍，但它们几乎无法区分静态和动态障碍，从而导致避免障碍物的性能有限。尽管在自动驾驶中存在大量基于学习的动态障碍检测算法，但四轮驱动器的有限计算资源无法使用这些方法实现实时性能。为了解决这些问题，我们为使用RGB-D摄像机提出了一个实时动态障碍物跟踪和映射系统，以避免四肢障碍物。拟议的系统首先利用带有占用体素图的深度图像来生成潜在的动态障碍区域作为建议。通过障碍区域建议，Kalman滤波器和我们的连续性过滤器将应用于跟踪每个动态障碍物。最后，使用追踪动态障碍的状态基于马尔可夫链提出了环境感知的轨迹预测方法。我们使用定制的四轮驱动器和导航计划者实施了建议的系统。仿真和物理实验表明，我们的方法可以成功地跟踪和代表动态环境中的障碍，并安全地避免障碍。

导航动态环境要求机器人生成无碰撞的轨迹，并积极避免移动障碍。大多数以前的作品都基于一个单个地图表示形式（例如几何，占用率或ESDF地图）设计路径计划算法。尽管他们在静态环境中表现出成功，但由于地图表示的限制，这些方法无法同时可靠地处理静态和动态障碍。为了解决该问题，本文提出了一种利用机器人在板载视觉的基于梯度的B-Spline轨迹优化算法。深度视觉使机器人能够基于体素图以几何形式跟踪和表示动态对象。拟议的优化首先采用基于圆的指南算法，以近似避免静态障碍的成本和梯度。然后，使用视觉检测的移动对象，我们的后水平距离场同时用于防止动态碰撞。最后，采用迭代重新指导策略来生成无碰撞轨迹。仿真和物理实验证明，我们的方法可以实时运行以安全地导航动态环境。

A recent study has shown a phenomenon called neural collapse in that the within-class means of features and the classifier weight vectors converge to the vertices of a simplex equiangular tight frame at the terminal phase of training for classification. In this paper, we explore the corresponding structures of the last-layer feature centers and classifiers in semantic segmentation. Based on our empirical and theoretical analysis, we point out that semantic segmentation naturally brings contextual correlation and imbalanced distribution among classes, which breaks the equiangular and maximally separated structure of neural collapse for both feature centers and classifiers. However, such a symmetric structure is beneficial to discrimination for the minor classes. To preserve these advantages, we introduce a regularizer on feature centers to encourage the network to learn features closer to the appealing structure in imbalanced semantic segmentation. Experimental results show that our method can bring significant improvements on both 2D and 3D semantic segmentation benchmarks. Moreover, our method ranks 1st and sets a new record (+6.8% mIoU) on the ScanNet200 test leaderboard. Code will be available at https://github.com/dvlab-research/Imbalanced-Learning.

In this paper, we study the problem of knowledge-intensive text-to-SQL, in which domain knowledge is necessary to parse expert questions into SQL queries over domain-specific tables. We formalize this scenario by building a new Chinese benchmark KnowSQL consisting of domain-specific questions covering various domains. We then address this problem by presenting formulaic knowledge, rather than by annotating additional data examples. More concretely, we construct a formulaic knowledge bank as a domain knowledge base and propose a framework (ReGrouP) to leverage this formulaic knowledge during parsing. Experiments using ReGrouP demonstrate a significant 28.2% improvement overall on KnowSQL.

The node-place model has been widely used to classify and evaluate transit stations, which sheds light on individual travel behaviors and supports urban planning through effectively integrating land use and transportation development. This article adapts this model to investigate whether and how node, place, and mobility would be associated with the transmission risks and presences of the local COVID-19 cases in a city. Similar studies on the model and its relevance to COVID-19, according to our knowledge, have not been undertaken before. Moreover, the unique metric drawn from detailed visit history of the infected, i.e., the COVID-19 footprints, is proposed and exploited. This study then empirically uses the adapted model to examine the station-level factors affecting the local COVID-19 footprints. The model accounts for traditional measures of the node and place as well as actual human mobility patterns associated with the node and place. It finds that stations with high node, place, and human mobility indices normally have more COVID-19 footprints in proximity. A multivariate regression is fitted to see whether and to what degree different indices and indicators can predict the COVID-19 footprints. The results indicate that many of the place, node, and human mobility indicators significantly impact the concentration of COVID-19 footprints. These are useful for policy-makers to predict and monitor hotspots for COVID-19 and other pandemics transmission.

Text-to-SQL semantic parsing is an important NLP task, which greatly facilitates the interaction between users and the database and becomes the key component in many human-computer interaction systems. Much recent progress in text-to-SQL has been driven by large-scale datasets, but most of them are centered on English. In this work, we present MultiSpider, the largest multilingual text-to-SQL dataset which covers seven languages (English, German, French, Spanish, Japanese, Chinese, and Vietnamese). Upon MultiSpider, we further identify the lexical and structural challenges of text-to-SQL (caused by specific language properties and dialect sayings) and their intensity across different languages. Experimental results under three typical settings (zero-shot, monolingual and multilingual) reveal a 6.1% absolute drop in accuracy in non-English languages. Qualitative and quantitative analyses are conducted to understand the reason for the performance drop of each language. Besides the dataset, we also propose a simple schema augmentation framework SAVe (Schema-Augmentation-with-Verification), which significantly boosts the overall performance by about 1.8% and closes the 29.5% performance gap across languages.

Practical applications employing deep learning must guarantee inference quality. However, we found that the inference quality of state-of-the-art and state-of-the-practice in practical applications has a long tail distribution. In the real world, many tasks have strict requirements for the quality of deep learning inference, such as safety-critical and mission-critical tasks. The fluctuation of inference quality seriously affects its practical applications, and the quality at the tail may lead to severe consequences. State-of-the-art and state-of-the-practice with outstanding inference quality designed and trained under loose constraints still have poor inference quality under constraints with practical application significance. On the one hand, the neural network models must be deployed on complex systems with limited resources. On the other hand, safety-critical and mission-critical tasks need to meet more metric constraints while ensuring high inference quality. We coin a new term, ``tail quality,'' to characterize this essential requirement and challenge. We also propose a new metric, ``X-Critical-Quality,'' to measure the inference quality under certain constraints. This article reveals factors contributing to the failure of using state-of-the-art and state-of-the-practice algorithms and systems in real scenarios. Therefore, we call for establishing innovative methodologies and tools to tackle this enormous challenge.

Automatic image colorization is a particularly challenging problem. Due to the high illness of the problem and multi-modal uncertainty, directly training a deep neural network usually leads to incorrect semantic colors and low color richness. Existing transformer-based methods can deliver better results but highly depend on hand-crafted dataset-level empirical distribution priors. In this work, we propose DDColor, a new end-to-end method with dual decoders, for image colorization. More specifically, we design a multi-scale image decoder and a transformer-based color decoder. The former manages to restore the spatial resolution of the image, while the latter establishes the correlation between semantic representations and color queries via cross-attention. The two decoders incorporate to learn semantic-aware color embedding by leveraging the multi-scale visual features. With the help of these two decoders, our method succeeds in producing semantically consistent and visually plausible colorization results without any additional priors. In addition, a simple but effective colorfulness loss is introduced to further improve the color richness of generated results. Our extensive experiments demonstrate that the proposed DDColor achieves significantly superior performance to existing state-of-the-art works both quantitatively and qualitatively. Codes will be made publicly available.

Previous computation models either have equivalent abilities in representing all computations but fail to provide primitive operators for programming complex algorithms or lack generalized expression ability to represent newly-added computations. This article presents a unified computation model with generalized expression ability and a concise set of primitive operators for programming high-level algorithms. We propose a unified data abstraction -- Tensor of List, and offer a unified computation model based on Tensor of List, which we call the ToL model (in short, ToL). ToL introduces five atomic computations that can represent any elementary computation by finite composition, ensured with strict formal proof. Based on ToL, we design a pure-functional language -- ToLang. ToLang provides a concise set of primitive operators that can be used to program complex big data and AI algorithms. Our evaluations show ToL has generalized expression ability and a built-in performance indicator, born with a strictly defined computation metric -- elementary operation count (EOPs), consistent with FLOPs within a small error range.

Medical Visual Question Answering (Medical-VQA) aims to answer clinical questions regarding radiology images, assisting doctors with decision-making options. Nevertheless, current Medical-VQA models learn cross-modal representations through residing vision and texture encoders in dual separate spaces, which lead to indirect semantic alignment. In this paper, we propose UnICLAM, a Unified and Interpretable Medical-VQA model through Contrastive Representation Learning with Adversarial Masking. Specifically, to learn an aligned image-text representation, we first establish a unified dual-stream pre-training structure with the gradually soft-parameter sharing strategy. Technically, the proposed strategy learns a constraint for the vision and texture encoders to be close in a same space, which is gradually loosened as the higher number of layers. Moreover, for grasping the semantic representation, we extend the unified Adversarial Masking data augmentation strategy to the contrastive representation learning of vision and text in a unified manner, alleviating the meaningless of the commonly used random mask. Concretely, while the encoder training minimizes the distance between the original feature and the masking feature, the adversarial masking model keeps adversarial learning to conversely maximize the distance. Furthermore, we also intuitively take a further exploration of the unified adversarial masking strategy, which improves the potential ante-hoc interpretability with remarkable performance and efficiency. Experimental results on VQA-RAD and SLAKE public benchmarks demonstrate that UnICLAM outperforms the existing 11 state-of-the-art Medical-VQA models. More importantly, we make an additional discussion about the performance of UnICLAM in diagnosing heart failure, verifying that UnICLAM exhibits superior few-shot adaption performance in practical disease diagnosis.