Related papers: Self-Supervised Visual Prompting for Cross-Domain …

Source-free domain adaptation (SFDA) for segmentation aims at adapting a model trained in the source domain to perform well in the target domain with only the source model and unlabeled target data. Inspired by the recent success of Segment…

The domain discrepancy existed between medical images acquired in different situations renders a major hurdle in deploying pre-trained medical image segmentation models for clinical use. Since it is less possible to distribute training data…

Semantic segmentation plays a critical role in enabling intelligent vehicles to comprehend their surrounding environments. However, deep learning-based methods usually perform poorly in domain shift scenarios due to the lack of labeled data…

Existing Source-free Unsupervised Domain Adaptation (SUDA) approaches inherently exhibit catastrophic forgetting. Typically, models trained on a labeled source domain and adapted to unlabeled target data improve performance on the target…

Contemporary domain adaptive semantic segmentation aims to address data annotation challenges by assuming that target domains are completely unannotated. However, annotating a few target samples is usually very manageable and worthwhile…

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…

Semantic segmentation models based on convolutional neural networks have recently displayed remarkable performance for a multitude of applications. However, these models typically do not generalize well when applied on new domains,…

Large-scale labeled training datasets have enabled deep neural networks to excel across a wide range of benchmark vision tasks. However, in many applications, it is prohibitively expensive and time-consuming to obtain large quantities of…

In defense-related remote sensing applications, such as vehicle detection on satellite imagery, supervised learning requires a huge number of labeled examples to reach operational performances. Such data are challenging to obtain as it…

In this paper, we investigate self-supervised pre-training methods for document text recognition. Nowadays, large unlabeled datasets can be collected for many research tasks, including text recognition, but it is costly to annotate them.…

The Segment Anything Model (SAM), with its prompt-driven paradigm, exhibits strong generalization in generic segmentation tasks. However, applying SAM to remote sensing (RS) images still faces two major challenges. First, manually…

Visual Prompt Tuning (VPT) has become a promising solution for Parameter-Efficient Fine-Tuning (PEFT) approach for Vision Transformer (ViT) models by partially fine-tuning learnable tokens while keeping most model parameters frozen. Recent…

Recently, the self-supervised pre-training paradigm has shown great potential in leveraging large-scale unlabeled data to improve downstream task performance. However, increasing the scale of unlabeled pre-training data in real-world…

Semantic segmentation enables robots to perceive and reason about their environments beyond geometry. Most of such systems build upon deep learning approaches. As autonomous robots are commonly deployed in initially unknown environments,…

We present a novel approach for unsupervised road segmentation in adverse weather conditions such as rain or fog. This includes a new algorithm for source-free domain adaptation (SFDA) using self-supervised learning. Moreover, our approach…

Pixel-level vision tasks, such as semantic segmentation, require extensive and high-quality annotated data, which is costly to obtain. Semi-supervised semantic segmentation (SSSS) has emerged as a solution to alleviate the labeling burden…

Localizing natural language phrases in images is a challenging problem that requires joint understanding of both the textual and visual modalities. In the unsupervised setting, lack of supervisory signals exacerbate this difficulty. In this…

Visual detection of Micro Air Vehicles (MAVs) has attracted increasing attention in recent years due to its important application in various tasks. The existing methods for MAV detection assume that the training set and testing set have the…

Applying the knowledge of an object detector trained on a specific domain directly onto a new domain is risky, as the gap between two domains can severely degrade model's performance. Furthermore, since different instances commonly embody…

The unsupervised pretraining of object detectors has recently become a key component of object detector training, as it leads to improved performance and faster convergence during the supervised fine-tuning stage. Existing unsupervised…