相关论文: Phrase Grounding-based Style Transfer for Single-D…

Vision models trained on multimodal datasets can benefit from the wide availability of large image-caption datasets. A recent model (CLIP) was found to generalize well in zero-shot and transfer learning settings. This could imply that…

Generalization is a pivotal challenge for agents following natural language instructions. To approach this goal, we leverage a vision-language model (VLM) for visual grounding and transfer its vision-language knowledge into reinforcement…

Generalization of machine learning models trained on a set of source domains on unseen target domains with different statistics, is a challenging problem. While many approaches have been proposed to solve this problem, they only utilize…

Domain adaptation has become a prominent problem setting in machine learning and related fields. This review asks the question: how can a classifier learn from a source domain and generalize to a target domain? We present a categorization…

In object detection, data amount and cost are a trade-off, and collecting a large amount of data in a specific domain is labor intensive. Therefore, existing large-scale datasets are used for pre-training. However, conventional transfer…

Single domain generalization (Single-DG) intends to develop a generalizable model with only one single training domain to perform well on other unknown target domains. Under the domain-hungry configuration, how to expand the coverage of…

Domain generalization (DG) aims to learn a robust model from source domains that generalize well on unseen target domains. Recent studies focus on generating novel domain samples or features to diversify distributions complementary to…

In this paper, we tackle the problem of one-shot unsupervised domain adaptation (OSUDA) for semantic segmentation where the segmentors only see one unlabeled target image during training. In this case, traditional unsupervised domain…

Unsupervised domain adaptive object detection aims to learn a robust detector in the domain shift circumstance, where the training (source) domain is label-rich with bounding box annotations, while the testing (target) domain is…

Visual grounding is a promising path toward more robust and accurate Natural Language Processing (NLP) models. Many multimodal extensions of BERT (e.g., VideoBERT, LXMERT, VL-BERT) allow a joint modeling of texts and images that lead to…

Given an arbitrary content and style image, arbitrary style transfer aims to render a new stylized image which preserves the content image's structure and possesses the style image's style. Existing arbitrary style transfer methods are…

Domain adaptive semantic segmentation aims to transfer knowledge from a labeled source domain to an unlabeled target domain. However, existing methods primarily focus on directly learning qualified target features, making it challenging to…

Semantic segmentation models trained on synthetic data often perform poorly on real-world images due to domain gaps, particularly in adverse conditions where labeled data is scarce. Yet, recent foundation models enable to generate realistic…

Domain generalization for semantic segmentation aims to mitigate the degradation in model performance caused by domain shifts. However, in many real-world scenarios, we are unable to access the model parameters and architectural details due…

Recent advances in object detection are mainly driven by deep learning with large-scale detection benchmarks. However, the fully-annotated training set is often limited for a target detection task, which may deteriorate the performance of…

An assumption widely used in recent neural style transfer methods is that image styles can be described by global statics of deep features like Gram or covariance matrices. Alternative approaches have represented styles by decomposing them…

Generalized few-shot semantic segmentation (GFSS) aims to segment objects of both base and novel classes, using sufficient samples of base classes and few samples of novel classes. Representative GFSS approaches typically employ a two-phase…

Multi-source unsupervised domain adaptation aims to leverage labeled data from multiple source domains for training a machine learning model to generalize well on a target domain without labels. Source domain selection plays a crucial role…

3D visual grounding aims to locate the referred target object in 3D point cloud scenes according to a free-form language description. Previous methods mostly follow a two-stage paradigm, i.e., language-irrelevant detection and cross-modal…

Transferring knowledge across different datasets is an important approach to successfully train deep models with a small-scale target dataset or when few labeled instances are available. In this paper, we aim at developing a model that can…