Related papers: Unsupervised Domain Adaptive Lane Detection via Co…

Despite growing interest in object detection, very few works address the extremely practical problem of cross-domain robustness especially for automative applications. In order to prevent drops in performance due to domain shift, we…

In real applications, object detectors based on deep networks still face challenges of the large domain gap between the labeled training data and unlabeled testing data. To reduce the gap, recent techniques are proposed by aligning the…

Most existing multi-source domain adaptation (MSDA) methods minimize the distance between multiple source-target domain pairs via feature distribution alignment, an approach borrowed from the single source setting. However, with diverse…

Cross-domain pedestrian detection aims to generalize pedestrian detectors from one label-rich domain to another label-scarce domain, which is crucial for various real-world applications. Most recent works focus on domain alignment to train…

Most existing scene text detectors require large-scale training data which cannot scale well due to two major factors: 1) scene text images often have domain-specific distributions; 2) collecting large-scale annotated scene text images is…

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…

We aim to localize objects in images using image-level supervision only. Previous approaches to this problem mainly focus on discriminative object regions and often fail to locate precise object boundaries. We address this problem by…

Contrastive learning has achieved remarkable success in representation learning via self-supervision in unsupervised settings. However, effectively adapting contrastive learning to supervised learning tasks remains as a challenge in…

This work tackles the unsupervised cross-domain object detection problem which aims to generalize a pre-trained object detector to a new target domain without labels. We propose an uncertainty-aware model adaptation method, which is based…

Face Presentation Attack Detection (PAD) has drawn increasing attentions to secure the face recognition systems that are widely used in many applications. Conventional face anti-spoofing methods have been proposed, assuming that testing is…

Semantic segmentation provides pixel-level scene understanding essential for autonomous driving and fine-grained perception tasks. However, training segmentation models requires costly, labor-intensive annotations on real-world datasets.…

Fully convolutional models for dense prediction have proven successful for a wide range of visual tasks. Such models perform well in a supervised setting, but performance can be surprisingly poor under domain shifts that appear mild to a…

Unsupervised domain adaptation is critical in various computer vision tasks, such as object detection, instance segmentation, etc. They attempt to reduce domain bias-induced performance degradation while also promoting model application…

Domain adaptation aims to leverage a labeled source domain to learn a classifier for the unlabeled target domain with a different distribution. Previous methods mostly match the distribution between two domains by global or class alignment.…

The major challenge in today's computer vision scenario is the availability of good quality labeled data. In a field of study like image classification, where data is of utmost importance, we need to find more reliable methods which can…

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…

Many existing unsupervised domain adaptation (UDA) methods primarily focus on covariate shift, limiting their effectiveness in imbalanced domain adaptation (IDA) where both covariate shift and label shift coexist. Recent IDA methods have…

Lane detection is a critical component of Advanced Driver-Assistance Systems (ADAS) and Automated Driving System (ADS), providing essential spatial information for lateral control. However, domain shifts often undermine model reliability…

Semantic segmentation requires a lot of training data, which necessitates costly annotation. There have been many studies on unsupervised domain adaptation (UDA) from one domain to another, e.g., from computer graphics to real images.…

Object counting models suffer when deployed across domains with differing density variety, since density shifts are inherently task-relevant and violate standard domain adaptation assumptions. To address this, we propose a theoretical…