黑匣子优化（BBO）具有广泛的应用，包括自动机器学习，工程，物理和实验设计。但是，在适用性，性能和效率方面，用户对用户将BBO方法应用于现有软件包的问题仍有挑战。在本文中，我们构建了OpenBox，开源和通用BBO服务，具有改进的可用性。OpenBox后面的模块化设计还有助于灵活的抽象和优化在其他现有系统中常见的基本BBO组件。OpenBox分布，容错和可扩展。为了提高效率，OpenBox进一步利用“算法不可知”并行化和转移学习。我们的实验结果表明，与现有系统相比，OpenBox的有效性和效率。

Optical coherence tomography angiography (OCTA) is a novel imaging modality that has been widely utilized in ophthalmology and neuroscience studies to observe retinal vessels and microvascular systems. However, publicly available OCTA datasets remain scarce. In this paper, we introduce the largest and most comprehensive OCTA dataset dubbed OCTA-500, which contains OCTA imaging under two fields of view (FOVs) from 500 subjects. The dataset provides rich images and annotations including two modalities (OCT/OCTA volumes), six types of projections, four types of text labels (age / gender / eye / disease) and seven types of segmentation labels (large vessel/capillary/artery/vein/2D FAZ/3D FAZ/retinal layers). Then, we propose a multi-object segmentation task called CAVF, which integrates capillary segmentation, artery segmentation, vein segmentation, and FAZ segmentation under a unified framework. In addition, we optimize the 3D-to-2D image projection network (IPN) to IPN-V2 to serve as one of the segmentation baselines. Experimental results demonstrate that IPN-V2 achieves an ~10% mIoU improvement over IPN on CAVF task. Finally, we further study the impact of several dataset characteristics: the training set size, the model input (OCT/OCTA, 3D volume/2D projection), the baseline networks, and the diseases. The dataset and code are publicly available at: https://ieee-dataport.org/open-access/octa-500.

Algorithmic solutions for multi-object tracking (MOT) are a key enabler for applications in autonomous navigation and applied ocean sciences. State-of-the-art MOT methods fully rely on a statistical model and typically use preprocessed sensor data as measurements. In particular, measurements are produced by a detector that extracts potential object locations from the raw sensor data collected for a discrete time step. This preparatory processing step reduces data flow and computational complexity but may result in a loss of information. State-of-the-art Bayesian MOT methods that are based on belief propagation (BP) systematically exploit graph structures of the statistical model to reduce computational complexity and improve scalability. However, as a fully model-based approach, BP can only provide suboptimal estimates when there is a mismatch between the statistical model and the true data-generating process. Existing BP-based MOT methods can further only make use of preprocessed measurements. In this paper, we introduce a variant of BP that combines model-based with data-driven MOT. The proposed neural enhanced belief propagation (NEBP) method complements the statistical model of BP by information learned from raw sensor data. This approach conjectures that the learned information can reduce model mismatch and thus improve data association and false alarm rejection. Our NEBP method improves tracking performance compared to model-based methods. At the same time, it inherits the advantages of BP-based MOT, i.e., it scales only quadratically in the number of objects, and it can thus generate and maintain a large number of object tracks. We evaluate the performance of our NEBP approach for MOT on the nuScenes autonomous driving dataset and demonstrate that it has state-of-the-art performance.

通过多对象跟踪（MOT）方法启用的情况感知技术将在自主导航和应用海科学等领域创建新的服务和应用程序。信仰传播（BP）是贝叶斯MOT的最新方法，但完全依赖于统计模型和预处理传感器测量。在本文中，我们为基于模型和数据驱动的MOT建立了一种混合方法。提出的神经增强信念传播（NEBP）方法通过从原始传感器数据中学到的信息以改善数据关联并拒绝错误警报测量的目标来补充BP。我们评估了NEBP方法在Nuscenes自动驾驶数据集中的MOT的性能，并证明它可以超越最先进的参考方法。

在现实世界中，在雾度下拍摄的图像的降解可以是非常复杂的，其中雾度的空间分布从图像变化到图像。最近的方法采用深神经网络直接从朦胧图像中恢复清洁场景。然而，由于悖论由真正捕获的雾霾的变化和当前网络的固定退化参数引起的悖论，最近在真实朦胧的图像上的脱水方法的泛化能力不是理想的。解决现实世界建模问题阴霾退化，我们建议通过对不均匀雾度分布的鉴定和建模密度来解决这个问题。我们提出了一种新颖的可分离混合注意力（SHA）模块来编码雾霾密度，通过捕获正交方向上的特征来实现这一目标。此外，提出了密度图以明确地模拟雾度的不均匀分布。密度图以半监督方式生成位置编码。这种雾度密度感知和建模有效地捕获特征水平的不均匀分布性变性。通过SHA和密度图的合适组合，我们设计了一种新型的脱水网络架构，实现了良好的复杂性性能权衡。两个大规模数据集的广泛实验表明，我们的方法通过量化和定性地通过大幅度超越所有最先进的方法，将最佳发布的PSNR度量从28.53 DB升高到Haze4K测试数据集和在SOTS室内测试数据集中的37.17 dB至38.41 dB。

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.