Related papers: Learnable Motion-Focused Tokenization for Effectiv…
Learning models on one labeled dataset that generalize well on another domain is a difficult task, as several shifts might happen between the data domains. This is notably the case for lidar data, for which models can exhibit large…
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 -…
Medical image segmentation methods normally perform poorly when there is a domain shift between training and testing data. Unsupervised Domain Adaptation (UDA) addresses the domain shift problem by training the model using both labeled data…
For video models to be transferred and applied seamlessly across video tasks in varied environments, Video Unsupervised Domain Adaptation (VUDA) has been introduced to improve the robustness and transferability of video models. However,…
With the advancement of autonomous driving, numerous annotated multi-modality datasets have become available. This presents an opportunity to develop domain-adaptive 3D object detectors for new environments without relying on…
Recently, anatomical landmark detection has achieved great progresses on single-domain data, which usually assumes training and test sets are from the same domain. However, such an assumption is not always true in practice, which can cause…
We consider the problem of source-free unsupervised category-level pose estimation from only RGB images to a target domain without any access to source domain data or 3D annotations during adaptation. Collecting and annotating real-world 3D…
Recent developments in the unsupervised domain adaptation (UDA) enable the unsupervised machine learning (ML) prediction for target data, thus this will accelerate real world applications with ML models such as image recognition tasks in…
Although action recognition has achieved impressive results over recent years, both collection and annotation of video training data are still time-consuming and cost intensive. Therefore, image-to-video adaptation has been proposed to…
Unsupervised Domain Adaptation (UDA) aims to adapt models trained on a source domain to a new target domain where no labelled data is available. In this work, we investigate the problem of UDA from a synthetic computer-generated domain to a…
Unsupervised domain adaptation (UDA) aims to learn transferable representation across domains. Recently a few UDA works have successfully applied Transformer-based methods and achieved state-of-the-art (SOTA) results. However, it remains…
In precision agriculture, vision models often struggle with new, unseen fields where crops and weeds have been influenced by external factors, resulting in compositions and appearances that differ from the learned distribution. This paper…
Conventional Unsupervised Domain Adaptation (UDA) strives to minimize distribution discrepancy between domains, which neglects to harness rich semantics from data and struggles to handle complex domain shifts. A promising technique is to…
Multimodal large language models (MLLMs) achieve remarkable progress in cross-modal perception and reasoning, yet a fundamental question remains unresolved: should the vision encoder be fine-tuned or frozen? Despite the success of models…
To build a cross-modal latent space between 3D human motion and language, acquiring large-scale and high-quality human motion data is crucial. However, unlike the abundance of image data, the scarcity of motion data has limited the…
Unsupervised domain adaptation is one of the challenging problems in computer vision. This paper presents a novel approach to unsupervised domain adaptations based on the optimal transport-based distance. Our approach allows aligning target…
A source model trained on source data and a target model learned through unsupervised domain adaptation (UDA) usually encode different knowledge. To understand the adaptation process, we portray their knowledge difference with image…
Intermediate training of pre-trained transformer-based language models on domain-specific data leads to substantial gains for downstream tasks. To increase efficiency and prevent catastrophic forgetting alleviated from full domain-adaptive…
Segmenting images is critical for visual understanding but demands extensive pixel-level annotations. Foundational models have enabled new paradigms for predicting new classes guided by textual prompts, without annotations from the target…
Multi-source unsupervised domain adaptation (MUDA) is a framework to address the challenge of annotated data scarcity in a target domain via transferring knowledge from multiple annotated source domains. When the source domains are…