We consider the problem of unsupervised domain adaptation in semantic segmentation. A key in this campaign consists in reducing the domain shift, i.e., enforcing the data distributions of the two domains to be similar. One of the common strategies is to align the marginal distribution in the feature space through adversarial learning. However, this global alignment strategy does not consider the category-level joint distribution. A possible consequence of such global movement is that some categories which are originally well aligned between the source and target may be incorrectly mapped, thus leading to worse segmentation results in target domain. To address this problem, we introduce a category-level adversarial network, aiming to enforce local semantic consistency during the trend of global alignment. Our idea is to take a close look at the category-level joint distribution and align each class with an adaptive adversarial loss. Specifically, we reduce the weight of the adversarial loss for category-level aligned features while increasing the adversarial force for those poorly aligned. In this process, we decide how well a feature is category-level aligned between source and target by a co-training approach. In two domain adaptation tasks, i.e., GTA5 → Cityscapes and SYN-THIA → Cityscapes, we validate that the proposed method matches the state of the art in segmentation accuracy.

Deep learning-based physical-layer secret key generation (PKG) has been used to overcome the imperfect uplink/downlink channel reciprocity in frequency division duplexing (FDD) orthogonal frequency division multiplexing (OFDM) systems. However, existing efforts have focused on key generation for users in a specific environment where the training samples and test samples obey the same distribution, which is unrealistic for real world applications. This paper formulates the PKG problem in multiple environments as a learning-based problem by learning the knowledge such as data and models from known environments to generate keys quickly and efficiently in multiple new environments. Specifically, we propose deep transfer learning (DTL) and meta-learning-based channel feature mapping algorithms for key generation. The two algorithms use different training methods to pre-train the model in the known environments, and then quickly adapt and deploy the model to new environments. Simulation results show that compared with the methods without adaptation, the DTL and meta-learning algorithms both can improve the performance of generated keys. In addition, the complexity analysis shows that the meta-learning algorithm can achieve better performance than the DTL algorithm with less time, lower CPU and GPU resources.

如今，基础模型已成为人工智能中的基本基础设施之一，铺平了通往通用情报的方式。但是，现实提出了两个紧急挑战：现有的基础模型由英语社区主导；用户通常会获得有限的资源，因此不能总是使用基础模型。为了支持中文社区的发展，我们介绍了一个名为Fengshenbang的开源项目，该项目由认知计算与自然语言研究中心（CCNL）领导。我们的项目具有全面的功能，包括大型预培训模型，用户友好的API，基准，数据集等。我们将所有这些都包装在三个子项目中：风水次模型，风水框架和狂热基准。 Fengshenbang的开源路线图旨在重新评估中国预培训的大型大型模型的开源社区，促使整个中国大型模型社区的发展。我们还希望构建一个以用户为中心的开源生态系统，以允许个人访问所需的模型以匹配其计算资源。此外，我们邀请公司，大学和研究机构与我们合作建立大型开源模型的生态系统。我们希望这个项目将成为中国认知情报的基础。

语音情感识别（SER）有许多挑战，但是主要挑战之一是每个框架都没有统一的标准。在本文中，我们提出了Speecheq，这是一个基于多尺度统一度量的统一SER任务的框架。该指标可以通过多任务学习（MTL）培训，其中包括情感状态类别（EIS）和情感强度量表（EIS）的两个情感识别任务，以及两个音素识别和性别识别的辅助任务。对于此框架，我们构建了一个普通话SER数据集-Secemeeq数据集（SEQD）。我们对普通话的公共CASIA和ESD数据集进行了实验，这些实验表明我们的方法比基线方法相对较大，分别获得8.0 \％和6.5 \％的准确性提高。关于Iemocap的其他实验，具有四个情感类别（即生气，快乐，悲伤和中性）也表明所提出的方法达到了78.16％的加权准确性（WA）的最新方法，并且准确性不体（UA） 77.47％。

This paper presents a novel intrinsic image transfer (IIT) algorithm for illumination manipulation, which creates a local image translation between two illumination surfaces. This model is built on an optimization-based framework consisting of three photo-realistic losses defined on the sub-layers factorized by an intrinsic image decomposition. We illustrate that all losses can be reduced without the necessity of taking an intrinsic image decomposition under the well-known spatial-varying illumination illumination-invariant reflectance prior knowledge. Moreover, with a series of relaxations, all of them can be directly defined on images, giving a closed-form solution for image illumination manipulation. This new paradigm differs from the prevailing Retinex-based algorithms, as it provides an implicit way to deal with the per-pixel image illumination. We finally demonstrate its versatility and benefits to the illumination-related tasks such as illumination compensation, image enhancement, and high dynamic range (HDR) image compression, and show the high-quality results on natural image datasets.

Unsupervised domain adaptation (UDA) for semantic segmentation is a promising task freeing people from heavy annotation work. However, domain discrepancies in low-level image statistics and high-level contexts compromise the segmentation performance over the target domain. A key idea to tackle this problem is to perform both image-level and feature-level adaptation jointly. Unfortunately, there is a lack of such unified approaches for UDA tasks in the existing literature. This paper proposes a novel UDA pipeline for semantic segmentation that unifies image-level and feature-level adaptation. Concretely, for image-level domain shifts, we propose a global photometric alignment module and a global texture alignment module that align images in the source and target domains in terms of image-level properties. For feature-level domain shifts, we perform global manifold alignment by projecting pixel features from both domains onto the feature manifold of the source domain; and we further regularize category centers in the source domain through a category-oriented triplet loss and perform target domain consistency regularization over augmented target domain images. Experimental results demonstrate that our pipeline significantly outperforms previous methods. In the commonly tested GTA5$\rightarrow$Cityscapes task, our proposed method using Deeplab V3+ as the backbone surpasses previous SOTA by 8%, achieving 58.2% in mIoU.

Different people speak with diverse personalized speaking styles. Although existing one-shot talking head methods have made significant progress in lip sync, natural facial expressions, and stable head motions, they still cannot generate diverse speaking styles in the final talking head videos. To tackle this problem, we propose a one-shot style-controllable talking face generation framework. In a nutshell, we aim to attain a speaking style from an arbitrary reference speaking video and then drive the one-shot portrait to speak with the reference speaking style and another piece of audio. Specifically, we first develop a style encoder to extract dynamic facial motion patterns of a style reference video and then encode them into a style code. Afterward, we introduce a style-controllable decoder to synthesize stylized facial animations from the speech content and style code. In order to integrate the reference speaking style into generated videos, we design a style-aware adaptive transformer, which enables the encoded style code to adjust the weights of the feed-forward layers accordingly. Thanks to the style-aware adaptation mechanism, the reference speaking style can be better embedded into synthesized videos during decoding. Extensive experiments demonstrate that our method is capable of generating talking head videos with diverse speaking styles from only one portrait image and an audio clip while achieving authentic visual effects. Project Page: https://github.com/FuxiVirtualHuman/styletalk.

Witnessing the impressive achievements of pre-training techniques on large-scale data in the field of computer vision and natural language processing, we wonder whether this idea could be adapted in a grab-and-go spirit, and mitigate the sample inefficiency problem for visuomotor driving. Given the highly dynamic and variant nature of the input, the visuomotor driving task inherently lacks view and translation invariance, and the visual input contains massive irrelevant information for decision making, resulting in predominant pre-training approaches from general vision less suitable for the autonomous driving task. To this end, we propose PPGeo (Policy Pre-training via Geometric modeling), an intuitive and straightforward fully self-supervised framework curated for the policy pretraining in visuomotor driving. We aim at learning policy representations as a powerful abstraction by modeling 3D geometric scenes on large-scale unlabeled and uncalibrated YouTube driving videos. The proposed PPGeo is performed in two stages to support effective self-supervised training. In the first stage, the geometric modeling framework generates pose and depth predictions simultaneously, with two consecutive frames as input. In the second stage, the visual encoder learns driving policy representation by predicting the future ego-motion and optimizing with the photometric error based on current visual observation only. As such, the pre-trained visual encoder is equipped with rich driving policy related representations and thereby competent for multiple visuomotor driving tasks. Extensive experiments covering a wide span of challenging scenarios have demonstrated the superiority of our proposed approach, where improvements range from 2% to even over 100% with very limited data. Code and models will be available at https://github.com/OpenDriveLab/PPGeo.

Increasing research interests focus on sequential recommender systems, aiming to model dynamic sequence representation precisely. However, the most commonly used loss function in state-of-the-art sequential recommendation models has essential limitations. To name a few, Bayesian Personalized Ranking (BPR) loss suffers the vanishing gradient problem from numerous negative sampling and predictionbiases; Binary Cross-Entropy (BCE) loss subjects to negative sampling numbers, thereby it is likely to ignore valuable negative examples and reduce the training efficiency; Cross-Entropy (CE) loss only focuses on the last timestamp of the training sequence, which causes low utilization of sequence information and results in inferior user sequence representation. To avoid these limitations, in this paper, we propose to calculate Cumulative Cross-Entropy (CCE) loss over the sequence. CCE is simple and direct, which enjoys the virtues of painless deployment, no negative sampling, and effective and efficient training. We conduct extensive experiments on five benchmark datasets to demonstrate the effectiveness and efficiency of CCE. The results show that employing CCE loss on three state-of-the-art models GRU4Rec, SASRec, and S3-Rec can reach 125.63%, 69.90%, and 33.24% average improvement of full ranking NDCG@5, respectively. Using CCE, the performance curve of the models on the test data increases rapidly with the wall clock time, and is superior to that of other loss functions in almost the whole process of model training.

Recent advances in self-supervised learning (SSL) in computer vision are primarily comparative, whose goal is to preserve invariant and discriminative semantics in latent representations by comparing siamese image views. However, the preserved high-level semantics do not contain enough local information, which is vital in medical image analysis (e.g., image-based diagnosis and tumor segmentation). To mitigate the locality problem of comparative SSL, we propose to incorporate the task of pixel restoration for explicitly encoding more pixel-level information into high-level semantics. We also address the preservation of scale information, a powerful tool in aiding image understanding but has not drawn much attention in SSL. The resulting framework can be formulated as a multi-task optimization problem on the feature pyramid. Specifically, we conduct multi-scale pixel restoration and siamese feature comparison in the pyramid. In addition, we propose non-skip U-Net to build the feature pyramid and develop sub-crop to replace multi-crop in 3D medical imaging. The proposed unified SSL framework (PCRLv2) surpasses its self-supervised counterparts on various tasks, including brain tumor segmentation (BraTS 2018), chest pathology identification (ChestX-ray, CheXpert), pulmonary nodule detection (LUNA), and abdominal organ segmentation (LiTS), sometimes outperforming them by large margins with limited annotations.