Related papers: Domain Adaptive Video Semantic Segmentation via Cr…
Contemporary domain adaptation offers a practical solution for achieving cross-domain transfer of semantic segmentation between labeled source data and unlabeled target data. These solutions have gained significant popularity; however, they…
Unsupervised domain adaptation (UDA) aims to adapt a model of the labeled source domain to an unlabeled target domain. Existing UDA-based semantic segmentation approaches always reduce the domain shifts in pixel level, feature level, and…
This paper studies the problem of semi-supervised video object segmentation(VOS). Multiple works have shown that memory-based approaches can be effective for video object segmentation. They are mostly based on pixel-level matching, both…
Unsupervised domain adaptation enables to alleviate the need for pixel-wise annotation in the semantic segmentation. One of the most common strategies is to translate images from the source domain to the target domain and then align their…
Rendering synthetic data (e.g., 3D CAD-rendered images) to generate annotations for learning deep models in vision tasks has attracted increasing attention in recent years. However, simply applying the models learnt on synthetic images may…
Reliable perception during fast motion maneuvers or in high dynamic range environments is crucial for robotic systems. Since event cameras are robust to these challenging conditions, they have great potential to increase the reliability of…
Domain shift is a very challenging problem for semantic segmentation. Any model can be easily trained on synthetic data, where images and labels are artificially generated, but it will perform poorly when deployed on real environments. In…
Although the current different types of SAM adaptation methods have achieved promising performance for various downstream tasks, such as prompt-based ones and adapter-based ones, most of them belong to the one-step adaptation paradigm. In…
Unsupervised domain adaptation is a promising technique for semantic segmentation and other computer vision tasks for which large-scale data annotation is costly and time-consuming. In semantic segmentation, it is attractive to train models…
Multi-Object Tracking (MOT) aims to associate multiple objects across video frames and is a challenging vision task due to inherent complexities in the tracking environment. Most existing approaches train and track within a single domain,…
LiDAR datasets for autonomous driving exhibit biases in properties such as point cloud density, range, and object dimensions. As a result, object detection networks trained and evaluated in different environments often experience…
In this paper, we consider the problem of unsupervised domain adaptation in the semantic segmentation. There are two primary issues in this field, i.e., what and how to transfer domain knowledge across two domains. Existing methods mainly…
Most learned B-frame codecs with hierarchical temporal prediction suffer from the domain shift issue caused by the discrepancy in the Group-of-Pictures (GOP) size used for training and test. As such, the motion estimation network may fail…
Video topic segmentation unveils the coarse-grained semantic structure underlying videos and is essential for other video understanding tasks. Given the recent surge in multi-modal, relying solely on a single modality is arguably…
The goal of the challenge is to develop a test-time adaptation (TTA) method, which could adapt the model to gradually changing domains in video sequences for semantic segmentation task. It is based on a synthetic driving video dataset -…
Referring video object segmentation (RVOS), as a supervised learning task, relies on sufficient annotated data for a given scene. However, in more realistic scenarios, only minimal annotations are available for a new scene, which poses…
The goal of cross-domain object matching (CDOM) is to find correspondence between two sets of objects in different domains in an unsupervised way. Photo album summarization is a typical application of CDOM, where photos are automatically…
Existing techniques to adapt semantic segmentation networks across the source and target domains within deep convolutional neural networks (CNNs) deal with all the samples from the two domains in a global or category-aware manner. They do…
Action recognition has been a widely studied topic with a heavy focus on supervised learning involving sufficient labeled videos. However, the problem of cross-domain action recognition, where training and testing videos are drawn from…
We propose Domain-Conditioned Meta-Contrastive Learning, a framework for improving the cross-domain generalization of vision-language models. While contrastive models such as CLIP achieve strong performance through large-scale training,…