We introduce MUSE-VL, a Unified Vision-Language Model through Semantic discrete Encoding for multimodal understanding and generation. Recently, the research community has begun exploring unified models for visual generation and understanding. However, existing vision tokenizers (e.g., VQGAN) only consider low-level information, which makes it difficult to align with language tokens. This results in high training complexity and necessitates a large amount of training data to achieve optimal performance. Additionally, their performance is still far from dedicated understanding models. This paper proposes Semantic Discrete Encoding (SDE), which effectively aligns the information of visual tokens and language tokens by adding semantic constraints to the visual tokenizer. This greatly reduces the amount of training data and improves the performance of the unified model. With the same LLM size, our method improved the understanding performance by 4.8% compared to the previous SOTA Emu3 and surpassed the dedicated understanding model LLaVA-NeXT 34B by 3.7%. Our model also surpasses the existing unified models on visual generation benchmarks.

Although good performance has been recently achieved in point cloud semantic segmentation based on deep learning, it has not been promoted due to differences in actual scenes and the time-consuming production of labeled data sets. Unsupervised domain adaptation (UDA) aims to solve the problem of how to adapt the classifier from one scene (source domain) to another unlabeled scene (target domain), which can reduce the performance drop caused by the domain shift. Since spatial information is important for light detection and ranging (LiDAR) point and the causes of domain gap in image and point cloud tasks are different, projecting point cloud into image for processing is not suitable and how to apply the image-oriented domain adaptation (DA) methods to point cloud is not trivial. In this letter, we propose a 3D point-based UDA method for point cloud semantic segmentation. This model introduces point- and set-level domain adaptive modules to achieve feature alignment between the domains. We evaluate the proposed method with two experiments, including cross terrain adaptation and airborne to mobile adaptation. Compared with the results without using DA, the mean intersection over union (mIoU) increased by 10.45% and 24.69%, respectively, indicating the effectiveness of our method.

Most semi-supervised learning models are consistency-based, which leverage unlabeled images by maximizing the similarity between different augmentations of an image. But when we apply them to human pose estimation that has extremely imbalanced class distribution, they often collapse and predict every pixel in unlabeled images as background. We find this is because the decision boundary passes the high-density areas of the minor class so more and more pixels are gradually misclassified as background. In this work, we present a surprisingly simple approach to drive the model to learn in the correct direction. For each image, it composes a pair of easy-hard augmentations and uses the more accurate predictions on the easy image to teach the network to learn pose information of the hard one. The accuracy superiority of teaching signals allows the network to be "monotonically" improved which effectively avoids collapsing. We apply our method to the state-of-the-art pose estimators and it further improves their performance on three public datasets.

Cross view feature fusion is the key to address the occlusion problem in human pose estimation. The current fusion methods need to train a separate model for every pair of cameras making them difficult to scale. In this work, we introduce MetaFuse, a pre-trained fusion model learned from a large number of cameras in the Panoptic dataset. The model can be efficiently adapted or finetuned for a new pair of cameras using a small number of labeled images. The strong adaptation power of MetaFuse is due in large part to the proposed factorization of the original fusion model into two parts-(1) a generic fusion model shared by all cameras, and (2) lightweight camera-dependent transformations. Furthermore, the generic model is learned from many cameras by a meta-learning style algorithm to maximize its adaptation capability to various camera poses. We observe in experiments that MetaFuse finetuned on the public datasets outperforms the state-of-the-arts by a large margin which validates its value in practice.