Jinjin Zheng

Zhixiang Wei, Lin Chen, Yi Jin et al.

In this paper, we first assess and harness various Vision Foundation Models (VFMs) in the context of Domain Generalized Semantic Segmentation (DGSS). Driven by the motivation that Leveraging Stronger pre-trained models and Fewer trainable parameters for Superior generalizability, we introduce a robust fine-tuning approach, namely Rein, to parameter-efficiently harness VFMs for DGSS. Built upon a set of trainable tokens, each linked to distinct instances, Rein precisely refines and forwards the feature maps from each layer to the next layer within the backbone. This process produces diverse refinements for different categories within a single image. With fewer trainable parameters, Rein efficiently fine-tunes VFMs for DGSS tasks, surprisingly surpassing full parameter fine-tuning. Extensive experiments across various settings demonstrate that Rein significantly outperforms state-of-the-art methods. Remarkably, with just an extra 1% of trainable parameters within the frozen backbone, Rein achieves a mIoU of 78.4% on the Cityscapes, without accessing any real urban-scene datasets.Code is available at https://github.com/w1oves/Rein.git.

Zhixiang Wei, Xiaoxiao Ma, Ruishen Yan et al.

Vision Foundation Models(VFMs) have achieved remarkable success in various computer vision tasks. However, their application to semantic segmentation is hindered by two significant challenges: (1) the disparity in data scale, as segmentation datasets are typically much smaller than those used for VFM pre-training, and (2) domain distribution shifts, where real-world segmentation scenarios are diverse and often underrepresented during pre-training. To overcome these limitations, we present Rein++, an efficient VFM-based segmentation framework that demonstrates superior generalization from limited data and enables effective adaptation to diverse unlabeled scenarios. Specifically, Rein++ comprises a domain generalization solution Rein-G and a domain adaptation solution Rein-A. Rein-G introduces a set of trainable, instance-aware tokens that effectively refine the VFM's features for the segmentation task. This parameter-efficient approach fine-tunes less than 1% of the backbone's parameters, enabling robust generalization. Building on the Rein-G, Rein-A performs unsupervised domain adaptation at both the instance and logit levels to mitigate domain shifts. In addition, it incorporates a semantic transfer module that leverages the class-agnostic capabilities of the segment anything model to enhance boundary details in the target domain. The integrated Rein++ pipeline first learns a generalizable model on a source domain (e.g., daytime scenes) and subsequently adapts it to diverse target domains (e.g., nighttime scenes) without any target labels. Comprehensive experiments demonstrate that Rein++ significantly outperforms state-of-the-art methods with efficient training, underscoring its roles an efficient, generalizable, and adaptive segmentation solution for VFMs, even for large models with billions of parameters. The code is available at https://github.com/wloves/Rein.

W. X. Chen, X. Y. Cui, J. Zheng et al.

A head-mounted display (HMD) is a portable and interactive display device. With the development of 5G technology, it may become a general-purpose computing platform in the future. Human-computer interaction (HCI) technology for HMDs has also been of significant interest in recent years. In addition to tracking gestures and speech, tracking human eyes as a means of interaction is highly effective. In this paper, we propose two UnityEyes-based convolutional neural network models, UEGazeNet and UEGazeNet*, which can be used for input images with low resolution and high resolution, respectively. These models can perform rapid interactions by classifying gaze trajectories (GTs), and a GTgestures dataset containing data for 10,200 "eye-painting gestures" collected from 15 individuals is established with our gaze-tracking method. We evaluated the performance both indoors and outdoors and the UEGazeNet can obtaine results 52\% and 67\% better than those of state-of-the-art networks. The generalizability of our GTgestures dataset using a variety of gaze-tracking models is evaluated, and an average recognition rate of 96.71\% is obtained by our method.