Related papers: AutoLabel: CLIP-based framework for Open-set Video…

"Self-training" has become a dominant method for semantic segmentation via unsupervised domain adaptation (UDA). It creates a set of pseudo labels for the target domain to give explicit supervision. However, the pseudo labels are noisy,…

Multi-modal learning has become increasingly popular due to its ability to leverage information from different data sources (e.g., text and images) to improve the model performance. Recently, CLIP has emerged as an effective approach that…

Universal Domain Adaptation (UniDA) aims to transfer knowledge from a source domain to a target domain without any constraints on label sets. Since both domains may hold private classes, identifying target common samples for domain…

Zero-shot anomaly detection (ZSAD) is crucial for detecting anomalous patterns in target datasets without using training samples, specifically in scenarios where there are distributional differences between the target domain and training…

Traditional 3D scene understanding approaches rely on labeled 3D datasets to train a model for a single task with supervision. We propose OpenScene, an alternative approach where a model predicts dense features for 3D scene points that are…

Vision-Language Models (VLMs) adapted to remote sensing rely heavily on domain-specific image-text supervision, yet high-quality annotations for satellite and aerial imagery remain scarce and expensive to produce. Prevailing pseudo-labeling…

Unsupervised Graph Domain Adaptation (UGDA) has emerged as a practical solution to transfer knowledge from a label-rich source graph to a completely unlabelled target graph. However, most methods require a labelled source graph to provide…

Open-world and anomaly segmentation methods seek to enable autonomous driving systems to detect and segment both known and unknown objects in real-world scenes. However, existing methods do not assign semantically meaningful labels to…

Zero-shot 3D object classification is crucial for real-world applications like autonomous driving, however it is often hindered by a significant domain gap between the synthetic data used for training and the sparse, noisy LiDAR scans…

Vision-language models, such as CLIP, have shown promising Out-of-Distribution (OoD) generalization under various types of distribution shifts. Recent studies attempted to investigate the leading cause of this capability. In this work, we…

The increasing adaptation of vision models across domains, such as satellite imagery and medical scans, has raised an emerging privacy risk: models may inadvertently retain and leak sensitive source-domain specific information in the target…

Deep learning has become the method of choice to tackle real-world problems in different domains, partly because of its ability to learn from data and achieve impressive performance on a wide range of applications. However, its success…

Contrastive language image pretraining (CLIP) is a standard method for training vision-language models. While CLIP is scalable, promptable, and robust to distribution shifts on image classification tasks, it lacks object localization…

Monocular 3D object detection (M3OD) has long faced challenges due to data scarcity caused by high annotation costs and inherent 2D-to-3D ambiguity. Although various weakly supervised methods and pseudo-labeling methods have been proposed…

In semantic segmentation, we aim to train a pixel-level classifier to assign category labels to all pixels in an image, where labeled training images and unlabeled test images are from the same distribution and share the same label set.…

CLIP (Contrastive Language-Image Pre-training) has attained great success in pattern recognition and computer vision. Transferring CLIP to downstream tasks (e.g. zero- or few-shot classification) is a hot topic in multimodal learning.…

Medical image classification plays a crucial role in clinical decision-making, yet most models are constrained to a fixed set of predefined classes, limiting their adaptability to new conditions. Contrastive Language-Image Pretraining…

In this work, we define and address a novel domain adaptation (DA) problem in semantic scene segmentation, where the target domain not only exhibits a data distribution shift w.r.t. the source domain, but also includes novel classes that do…

The divergence between labeled training data and unlabeled testing data is a significant challenge for recent deep learning models. Unsupervised domain adaptation (UDA) attempts to solve such problem. Recent works show that self-training is…

Pre-trained vision-language models (VLMs), exemplified by CLIP, demonstrate remarkable adaptability across zero-shot classification tasks without additional training. However, their performance diminishes in the presence of domain shifts.…