Related papers: Grad-CL: Source Free Domain Adaptation with Gradie…

Understanding point clouds captured from the real-world is challenging due to shifts in data distribution caused by varying object scales, sensor angles, and self-occlusion. Prior works have addressed this issue by combining recent learning…

This paper proposes a novel pixel-level distribution regularization scheme (DRSL) for self-supervised domain adaptation of semantic segmentation. In a typical setting, the classification loss forces the semantic segmentation model to…

Generalized Category Discovery (GCD) aims to cluster unlabeled images into known and novel categories using labeled images from known classes. To address the challenge of transferring features from known to unknown classes while mitigating…

Supervised learning for semantic segmentation requires a large number of labeled samples, which is difficult to obtain in the field of remote sensing. Self-supervised learning (SSL), can be used to solve such problems by pre-training a…

A deep learning model trained on some labeled data from a certain source domain generally performs poorly on data from different target domains due to domain shifts. Unsupervised domain adaptation methods address this problem by alleviating…

Liver segmentation on images acquired using computed tomography (CT) and magnetic resonance imaging (MRI) plays an important role in clinical management of liver diseases. Compared to MRI, CT images of liver are more abundant and readily…

Previous research has shown that constraining the gradient of loss function with respect to model-predicted probabilities can enhance the model robustness against noisy labels. These methods typically specify a fixed optimal threshold for…

Large Vision-Language Models like CLIP have become a powerful foundation for Unsupervised Domain Adaptation due to their strong zero-shot generalization. State-of-the-art methods typically leverage CLIP to generate pseudo-labels for the…

Domain adaptive semantic segmentation enables robust pixel-wise understanding in real-world driving scenes. Source-free domain adaptation, as a more practical technique, addresses the concerns of data privacy and storage limitations in…

Glaucoma is a chronic eye disease that leads to irreversible vision loss. The cup to disc ratio (CDR) plays an important role in the screening and diagnosis of glaucoma. Thus, the accurate and automatic segmentation of optic disc (OD) and…

This report is a reproducibility study of the paper "CDUL: CLIP-Driven Unsupervised Learning for Multi-Label Image Classification" (Abdelfattah et al, ICCV 2023). Our report makes the following contributions: (1) We provide a reproducible,…

Domain adaptation has become a widely adopted approach in machine learning due to the high costs associated with labeling data. It is typically applied when access to a labeled source domain is available. However, in real-world scenarios,…

Text-guided medical segmentation enhances segmentation accuracy by utilizing clinical reports as auxiliary information. However, existing methods typically rely on unaligned image and text encoders, which necessitate complex interaction…

Training (source) domain bias affects state-of-the-art object detectors, such as Faster R-CNN, when applied to new (target) domains. To alleviate this problem, researchers proposed various domain adaptation methods to improve object…

Domain Adaptation (DA) is crucial for robust deployment of medical image segmentation models when applied to new clinical centers with significant domain shifts. Source-Free Domain Adaptation (SFDA) is appealing as it can deal with privacy…

Graph contrastive learning (GCL) learns node and graph representations by contrasting multiple views of the same graph. Existing methods typically rely on fixed, handcrafted views-usually a local and a global perspective, which limits their…

Due to the advantages of leveraging unlabeled data and learning meaningful representations, semi-supervised learning and contrastive learning have been progressively combined to achieve better performances in popular applications with few…

Vision-language models, such as contrastive language-image pre-training (CLIP), have demonstrated impressive results in natural image domains. However, these models often struggle when applied to specialized domains like remote sensing, and…

Significant progress has been achieved on the improvement and downstream usages of the Contrastive Language-Image Pre-training (CLIP) vision-language model, while less attention is paid to the interpretation of CLIP. We propose a…

Semi-supervised learning has substantially advanced medical image segmentation since it alleviates the heavy burden of acquiring the costly expert-examined annotations. Especially, the consistency-based approaches have attracted more…