Benefiting from the intrinsic supervision information exploitation capability, contrastive learning has achieved promising performance in the field of deep graph clustering recently. However, we observe that two drawbacks of the positive and negative sample construction mechanisms limit the performance of existing algorithms from further improvement. 1) The quality of positive samples heavily depends on the carefully designed data augmentations, while inappropriate data augmentations would easily lead to the semantic drift and indiscriminative positive samples. 2) The constructed negative samples are not reliable for ignoring important clustering information. To solve these problems, we propose a Cluster-guided Contrastive deep Graph Clustering network (CCGC) by mining the intrinsic supervision information in the high-confidence clustering results. Specifically, instead of conducting complex node or edge perturbation, we construct two views of the graph by designing special Siamese encoders whose weights are not shared between the sibling sub-networks. Then, guided by the high-confidence clustering information, we carefully select and construct the positive samples from the same high-confidence cluster in two views. Moreover, to construct semantic meaningful negative sample pairs, we regard the centers of different high-confidence clusters as negative samples, thus improving the discriminative capability and reliability of the constructed sample pairs. Lastly, we design an objective function to pull close the samples from the same cluster while pushing away those from other clusters by maximizing and minimizing the cross-view cosine similarity between positive and negative samples. Extensive experimental results on six datasets demonstrate the effectiveness of CCGC compared with the existing state-of-the-art algorithms.

As one of the prevalent methods to achieve automation systems, Imitation Learning (IL) presents a promising performance in a wide range of domains. However, despite the considerable improvement in policy performance, the corresponding research on the explainability of IL models is still limited. Inspired by the recent approaches in explainable artificial intelligence methods, we proposed a model-agnostic explaining framework for IL models called R2RISE. R2RISE aims to explain the overall policy performance with respect to the frames in demonstrations. It iteratively retrains the black-box IL model from the randomized masked demonstrations and uses the conventional evaluation outcome environment returns as the coefficient to build an importance map. We also conducted experiments to investigate three major questions concerning frames' importance equality, the effectiveness of the importance map, and connections between importance maps from different IL models. The result shows that R2RISE successfully distinguishes important frames from the demonstrations.

With the rapid deployment of graph neural networks (GNNs) based techniques into a wide range of applications such as link prediction, node classification, and graph classification the explainability of GNNs has become an indispensable component for predictive and trustworthy decision-making. Thus, it is critical to explain why graph neural network (GNN) makes particular predictions for them to be believed in many applications. Some GNNs explainers have been proposed recently. However, they lack to generate accurate and real explanations. To mitigate these limitations, we propose GANExplainer, based on Generative Adversarial Network (GAN) architecture. GANExplainer is composed of a generator to create explanations and a discriminator to assist with the Generator development. We investigate the explanation accuracy of our models by comparing the performance of GANExplainer with other state-of-the-art methods. Our empirical results on synthetic datasets indicate that GANExplainer improves explanation accuracy by up to 35\% compared to its alternatives.

Data Augmentation (DA) is frequently used to automatically provide additional training data without extra human annotation. However, data augmentation may introduce noisy data that impairs training. To guarantee the quality of augmented data, existing methods either assume no noise exists in the augmented data and adopt consistency training or use simple heuristics such as training loss and diversity constraints to filter out ``noisy'' data. However, those filtered examples may still contain useful information, and dropping them completely causes loss of supervision signals. In this paper, based on the assumption that the original dataset is cleaner than the augmented data, we propose an on-the-fly denoising technique for data augmentation that learns from soft augmented labels provided by an organic teacher model trained on the cleaner original data. A simple self-regularization module is applied to force the model prediction to be consistent across two distinct dropouts to further prevent overfitting on noisy labels. Our method can be applied to augmentation techniques in general and can consistently improve the performance on both text classification and question-answering tasks.

LiDAR-based 3D Object detectors have achieved impressive performances in many benchmarks, however, multisensors fusion-based techniques are promising to further improve the results. PointPainting, as a recently proposed framework, can add the semantic information from the 2D image into the 3D LiDAR point by the painting operation to boost the detection performance. However, due to the limited resolution of 2D feature maps, severe boundary-blurring effect happens during re-projection of 2D semantic segmentation into the 3D point clouds. To well handle this limitation, a general multimodal fusion framework MSF has been proposed to fuse the semantic information from both the 2D image and 3D points scene parsing results. Specifically, MSF includes three main modules. First, SOTA off-the-shelf 2D/3D semantic segmentation approaches are employed to generate the parsing results for 2D images and 3D point clouds. The 2D semantic information is further re-projected into the 3D point clouds with calibrated parameters. To handle the misalignment between the 2D and 3D parsing results, an AAF module is proposed to fuse them by learning an adaptive fusion score. Then the point cloud with the fused semantic label is sent to the following 3D object detectors. Furthermore, we propose a DFF module to aggregate deep features in different levels to boost the final detection performance. The effectiveness of the framework has been verified on two public large-scale 3D object detection benchmarks by comparing with different baselines. The experimental results show that the proposed fusion strategies can significantly improve the detection performance compared to the methods using only point clouds and the methods using only 2D semantic information. Most importantly, the proposed approach significantly outperforms other approaches and sets new SOTA results on the nuScenes testing benchmark.

Copy-Paste is a simple and effective data augmentation strategy for instance segmentation. By randomly pasting object instances onto new background images, it creates new training data for free and significantly boosts the segmentation performance, especially for rare object categories. Although diverse, high-quality object instances used in Copy-Paste result in more performance gain, previous works utilize object instances either from human-annotated instance segmentation datasets or rendered from 3D object models, and both approaches are too expensive to scale up to obtain good diversity. In this paper, we revisit Copy-Paste at scale with the power of newly emerged zero-shot recognition models (e.g., CLIP) and text2image models (e.g., StableDiffusion). We demonstrate for the first time that using a text2image model to generate images or zero-shot recognition model to filter noisily crawled images for different object categories is a feasible way to make Copy-Paste truly scalable. To make such success happen, we design a data acquisition and processing framework, dubbed "X-Paste", upon which a systematic study is conducted. On the LVIS dataset, X-Paste provides impressive improvements over the strong baseline CenterNet2 with Swin-L as the backbone. Specifically, it archives +2.6 box AP and +2.1 mask AP gains on all classes and even more significant gains with +6.8 box AP +6.5 mask AP on long-tail classes.

Neural Radiance Fields (NeRF) methods have proved effective as compact, high-quality and versatile representations for 3D scenes, and enable downstream tasks such as editing, retrieval, navigation, etc. Various neural architectures are vying for the core structure of NeRF, including the plain Multi-Layer Perceptron (MLP), sparse tensors, low-rank tensors, hashtables and their compositions. Each of these representations has its particular set of trade-offs. For example, the hashtable-based representations admit faster training and rendering but their lack of clear geometric meaning hampers downstream tasks like spatial-relation-aware editing. In this paper, we propose Progressive Volume Distillation (PVD), a systematic distillation method that allows any-to-any conversions between different architectures, including MLP, sparse or low-rank tensors, hashtables and their compositions. PVD consequently empowers downstream applications to optimally adapt the neural representations for the task at hand in a post hoc fashion. The conversions are fast, as distillation is progressively performed on different levels of volume representations, from shallower to deeper. We also employ special treatment of density to deal with its specific numerical instability problem. Empirical evidence is presented to validate our method on the NeRF-Synthetic, LLFF and TanksAndTemples datasets. For example, with PVD, an MLP-based NeRF model can be distilled from a hashtable-based Instant-NGP model at a 10X~20X faster speed than being trained the original NeRF from scratch, while achieving a superior level of synthesis quality. Code is available at https://github.com/megvii-research/AAAI2023-PVD.

随着向设备深度学习的转变，确保在各种计算平台上的AI服务的一致行为变得非常重要。我们的工作解决了降低视力倒数的预测不一致的新兴问题：由较不准确的模型正确预测但错误地预测的测试样品。我们介绍了回归约束的神经体系结构搜索（Reg-NAS），以设计一个高度准确的模型家庭，这些模型会导致更少的负面流动。 Reg-NAS由两个组成部分组成：（1）一种新型的体系结构约束，使较大的模型能够包含较小的权重，从而最大化权重共享。这一想法源于我们的观察结果，即网络之间的重量较大会导致相似的样本预测，并导致负面量较少。 （2）一种新颖的搜索奖励，在体系结构搜索指标中同时结合了TOP-1的准确性和负面翻转。我们证明，\ regnas可以在三个流行的架构搜索空间中成功找到具有很少负面额的理想体系结构。与现有的最新方法相比，Reg-NAS可实现33-48％的负面流量相对减少。

作为多媒体信息检索中越来越流行的任务，视频瞬间检索（VMR）旨在根据给定的语言查询从未修剪视频中定位目标时刻。以前的大多数方法都在很大程度上取决于众多手动注释（即瞬间边界），在实践中获取非常昂贵。此外，由于不同数据集之间的域间隙，直接将这些预训练的模型应用于看不见的域，这会导致显着的性能下降。在本文中，我们专注于一项新任务：跨域VMR，其中一个域中完全注重数据集（````源域'''），但是感兴趣的域（``目标域''）仅包含未通知的数据集。据我们所知，我们介绍了有关跨域VMR的第一项研究。为了解决这一新任务，我们提出了一个新型的多模式跨域比对（MMCDA）网络，以将注释知识从源域转移到目标域。但是，由于源和目标域之间的域差异以及视频和查询之间的语义差距，直接将经过训练的模型应用于目标域通常会导致性能下降。为了解决这个问题，我们开发了三个新型模块：（i）域对齐模块旨在使每种模式的不同域之间的特征分布对齐； （ii）跨模式对齐模块旨在将视频和查询特征映射到关节嵌入空间中，并将目标域不同模态之间的特征分布对齐； （iii）特定的比对模块试图获得特定帧与给定查询之间的细粒度相似性以进行最佳定位。通过共同训练这三个模块，我们的MMCDA可以学习域不变和语义一致的跨模式表示。

基于激光雷达的3D单一对象跟踪是机器人技术和自动驾驶中的一个具有挑战性的问题。当前，现有方法通常会遇到长距离对象通常具有非常稀疏或部分倾斜的点云的问题，这使得模型含糊不清。模棱两可的功能将很难找到目标对象，并最终导致不良跟踪结果。为了解决此问题，我们使用功能强大的变压器体系结构，并为基于点云的3D单一对象跟踪任务提出一个点轨转换器（PTT）模块。具体而言，PTT模块通过计算注意力重量来生成微调的注意力特征，该功能指导追踪器的重点关注目标的重要功能，并提高复杂场景中的跟踪能力。为了评估我们的PTT模块，我们将PTT嵌入主要方法中，并构建一个名为PTT-NET的新型3D SOT跟踪器。在PTT-NET中，我们分别将PTT嵌入了投票阶段和提案生成阶段。投票阶段中的PTT模块可以模拟点斑块之间的交互作用，该点贴片学习上下文依赖于上下文。同时，提案生成阶段中的PTT模块可以捕获对象和背景之间的上下文信息。我们在Kitti和Nuscenes数据集上评估了PTT-NET。实验结果证明了PTT模块的有效性和PTT-NET的优越性，PTT-NET的优势超过了基线，在CAR类别中〜10％。同时，我们的方法在稀疏场景中也具有显着的性能提高。通常，变压器和跟踪管道的组合使我们的PTT-NET能够在两个数据集上实现最先进的性能。此外，PTT-NET可以在NVIDIA 1080TI GPU上实时以40fps实时运行。我们的代码是为研究社区开源的，网址为https://github.com/shanjiayao/ptt。