大坝破洪水中波传播的计算预测是流体动力和水文学中的长期问题。到目前为止，基于圣人方程的常规数值模型是主要方法。在这里，我们表明，以最少的数据训练的机器学习模型可以帮助预测一维大坝破洪水的长期动态行为，其精度令人满意。为此，我们使用lax-wendroff数值方案为一维大坝洪水方案求解了圣人方程，并通过模拟结果训练储层计算机网络（RC-ESN），由模拟结果组成时间序列深度。我们展示了RC-ESN模型的良好预测能力，该模型预测波传播行为286在大坝破洪水中，均方根误差（RMSE）小于0.01，表现优于传统的长期短期内存（LSTM）模型仅达到仅81个时步的可比RMSE。为了显示RC-ESN模型的性能，我们还提供了有关关键参数（包括训练集大小，储层大小和光谱半径）的预测准确性的灵敏度分析。结果表明，RC-ESN较少依赖训练集尺寸，介质储层尺寸k = 1200〜2600就足够了。我们确认光谱半径\ r {ho}对预测准确性显示了复杂的影响，并建议当前较小的光谱半径\ r {ho}。通过更改大坝断裂的初始流程深度，我们还得出了一个结论，即RC-ESN的预测范围大于LSTM的预测范围。

Underwater automatic target recognition (UATR) has been a challenging research topic in ocean engineering. Although deep learning brings opportunities for target recognition on land and in the air, underwater target recognition techniques based on deep learning have lagged due to sensor performance and the size of trainable data. This letter proposed a framework for learning the visual representation of underwater acoustic imageries, which takes a transformer-based style transfer model as the main body. It could replace the low-level texture features of optical images with the visual features of underwater acoustic imageries while preserving their raw high-level semantic content. The proposed framework could fully use the rich optical image dataset to generate a pseudo-acoustic image dataset and use it as the initial sample to train the underwater acoustic target recognition model. The experiments select the dual-frequency identification sonar (DIDSON) as the underwater acoustic data source and also take fish, the most common marine creature, as the research subject. Experimental results show that the proposed method could generate high-quality and high-fidelity pseudo-acoustic samples, achieve the purpose of acoustic data enhancement and provide support for the underwater acoustic-optical images domain transfer research.

在深海勘探领域，声纳目前是唯一有效的长距离传感装置。复杂的水下环境，如噪声干扰，低目标强度或背景动态，对声纳成像带来了许多负面影响。其中，非线性强度的问题非常普遍。它也被称为声学传感器成像的各向异性，即当自主水下车辆（AUV）携带声纳从不同角度检测到相同的目标时，图像对之间的强度变化有时非常大，这使得传统匹配算法成为了传统的匹配算法几乎无效。但是，图像匹配是诸如导航，定位和映射等综合任务的基础。因此，获得稳健和准确的匹配结果是非常有价值的。本文提出了一种基于相位信息和深卷积特征的组合匹配方法。它具有两个出色的优势：一个是深度卷积特征可用于衡量声纳图像的本地和全球位置的相似性;另一种是可以在声纳图像的关键目标位置执行本地特征匹配。该方法不需要复杂的手动设计，并以关闭端到端的方式完成非线性强度声纳图像的匹配任务。特征匹配实验在AUV捕获的深海声纳图像上进行，结果表明我们的提议具有卓越的匹配精度和鲁棒性。

在深海勘探领域，声纳目前是唯一有效的长距离传感装置。复杂的水下环境，如噪声干扰，低目标强度或背景动态，对声纳成像带来了许多负面影响。其中，非线性强度的问题非常普遍。它也被称为声学成像的各向异性，即，当AUV携带声纳从不同角度检测到相同的目标时，图像对之间的强度差值有时非常大，这使得传统的匹配算法几乎无效。但是，图像匹配是诸如导航，定位和映射等综合任务的基础。因此，获得稳健和准确的匹配结果是非常有价值的。本文提出了一种基于相位信息和深卷积特征的组合匹配方法。它有两个出色的优势：一个是，可以使用深度卷积功能来衡量声纳图像的本地和全球位置的相似性;另一种是可以在声纳图像的关键目标位置执行本地特征匹配。该方法不需要复杂的手动设计，并以关闭端到端的方式完成非线性强度声纳图像的匹配任务。特征匹配实验在AUV捕获的深海声纳图像上进行，结果表明我们的建议具有良好的匹配准确性和鲁棒性。

In this paper, we propose a robust 3D detector, named Cross Modal Transformer (CMT), for end-to-end 3D multi-modal detection. Without explicit view transformation, CMT takes the image and point clouds tokens as inputs and directly outputs accurate 3D bounding boxes. The spatial alignment of multi-modal tokens is performed implicitly, by encoding the 3D points into multi-modal features. The core design of CMT is quite simple while its performance is impressive. CMT obtains 73.0% NDS on nuScenes benchmark. Moreover, CMT has a strong robustness even if the LiDAR is missing. Code will be released at https://github.com/junjie18/CMT.

Dataset distillation has emerged as a prominent technique to improve data efficiency when training machine learning models. It encapsulates the knowledge from a large dataset into a smaller synthetic dataset. A model trained on this smaller distilled dataset can attain comparable performance to a model trained on the original training dataset. However, the existing dataset distillation techniques mainly aim at achieving the best trade-off between resource usage efficiency and model utility. The security risks stemming from them have not been explored. This study performs the first backdoor attack against the models trained on the data distilled by dataset distillation models in the image domain. Concretely, we inject triggers into the synthetic data during the distillation procedure rather than during the model training stage, where all previous attacks are performed. We propose two types of backdoor attacks, namely NAIVEATTACK and DOORPING. NAIVEATTACK simply adds triggers to the raw data at the initial distillation phase, while DOORPING iteratively updates the triggers during the entire distillation procedure. We conduct extensive evaluations on multiple datasets, architectures, and dataset distillation techniques. Empirical evaluation shows that NAIVEATTACK achieves decent attack success rate (ASR) scores in some cases, while DOORPING reaches higher ASR scores (close to 1.0) in all cases. Furthermore, we conduct a comprehensive ablation study to analyze the factors that may affect the attack performance. Finally, we evaluate multiple defense mechanisms against our backdoor attacks and show that our attacks can practically circumvent these defense mechanisms.

Automatic music generation with artificial intelligence typically requires a large amount of data which is hard to obtain for many less common genres and musical instruments. To tackle this issue, we present ongoing work and preliminary findings on the possibility for deep models to transfer knowledge from language to music, by finetuning large language models pre-trained on a massive text corpus on only hundreds of MIDI files of drum performances. We show that by doing so, one of the largest, state-of-the-art models (GPT3) is capable of generating reasonable drum grooves, while models that are not pre-trained (Transformer) shows no such ability beyond naive repetition. Evaluating generated music is a challenging task, more so is evaluating drum grooves with little precedence in literature. Hence, we propose a tailored structural evaluation method and analyze drum grooves produced by GPT3 compared to those played by human professionals, exposing the strengths and weaknesses of such generation by language-to-music transfer. Our findings suggest that language-to-music transfer learning with large language models is viable and promising.

Few Shot Instance Segmentation (FSIS) requires models to detect and segment novel classes with limited several support examples. In this work, we explore a simple yet unified solution for FSIS as well as its incremental variants, and introduce a new framework named Reference Twice (RefT) to fully explore the relationship between support/query features based on a Transformer-like framework. Our key insights are two folds: Firstly, with the aid of support masks, we can generate dynamic class centers more appropriately to re-weight query features. Secondly, we find that support object queries have already encoded key factors after base training. In this way, the query features can be enhanced twice from two aspects, i.e., feature-level and instance-level. In particular, we firstly design a mask-based dynamic weighting module to enhance support features and then propose to link object queries for better calibration via cross-attention. After the above steps, the novel classes can be improved significantly over our strong baseline. Additionally, our new framework can be easily extended to incremental FSIS with minor modification. When benchmarking results on the COCO dataset for FSIS, gFSIS, and iFSIS settings, our method achieves a competitive performance compared to existing approaches across different shots, e.g., we boost nAP by noticeable +8.2/+9.4 over the current state-of-the-art FSIS method for 10/30-shot. We further demonstrate the superiority of our approach on Few Shot Object Detection. Code and model will be available.

Graph Neural Networks (GNNs) have shown satisfying performance on various graph learning tasks. To achieve better fitting capability, most GNNs are with a large number of parameters, which makes these GNNs computationally expensive. Therefore, it is difficult to deploy them onto edge devices with scarce computational resources, e.g., mobile phones and wearable smart devices. Knowledge Distillation (KD) is a common solution to compress GNNs, where a light-weighted model (i.e., the student model) is encouraged to mimic the behavior of a computationally expensive GNN (i.e., the teacher GNN model). Nevertheless, most existing GNN-based KD methods lack fairness consideration. As a consequence, the student model usually inherits and even exaggerates the bias from the teacher GNN. To handle such a problem, we take initial steps towards fair knowledge distillation for GNNs. Specifically, we first formulate a novel problem of fair knowledge distillation for GNN-based teacher-student frameworks. Then we propose a principled framework named RELIANT to mitigate the bias exhibited by the student model. Notably, the design of RELIANT is decoupled from any specific teacher and student model structures, and thus can be easily adapted to various GNN-based KD frameworks. We perform extensive experiments on multiple real-world datasets, which corroborates that RELIANT achieves less biased GNN knowledge distillation while maintaining high prediction utility.

This paper focuses on designing efficient models with low parameters and FLOPs for dense predictions. Even though CNN-based lightweight methods have achieved stunning results after years of research, trading-off model accuracy and constrained resources still need further improvements. This work rethinks the essential unity of efficient Inverted Residual Block in MobileNetv2 and effective Transformer in ViT, inductively abstracting a general concept of Meta-Mobile Block, and we argue that the specific instantiation is very important to model performance though sharing the same framework. Motivated by this phenomenon, we deduce a simple yet efficient modern \textbf{I}nverted \textbf{R}esidual \textbf{M}obile \textbf{B}lock (iRMB) for mobile applications, which absorbs CNN-like efficiency to model short-distance dependency and Transformer-like dynamic modeling capability to learn long-distance interactions. Furthermore, we design a ResNet-like 4-phase \textbf{E}fficient \textbf{MO}del (EMO) based only on a series of iRMBs for dense applications. Massive experiments on ImageNet-1K, COCO2017, and ADE20K benchmarks demonstrate the superiority of our EMO over state-of-the-art methods, \eg, our EMO-1M/2M/5M achieve 71.5, 75.1, and 78.4 Top-1 that surpass \textbf{SoTA} CNN-/Transformer-based models, while trading-off the model accuracy and efficiency well.