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 …

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 …

Bounding box (bbox) regression is a fundamental task in computer vision. So far, the most
commonly used loss functions for bbox regression are the Intersection over Union (IoU) loss …

We address the task of domain adaptation in object detection, where there is a domain gap
between a domain with annotations (source) and a domain of interest without annotations …

Existing approaches for unsupervised domain adaptive object detection perform feature
alignment via adversarial training. While these methods achieve reasonable improvements …

We present a new domain adaptive self-training pipeline, named ST3D, for unsupervised
domain adaptation on 3D object detection from point clouds. First, we pre-train the 3D …

Unsupervised object re-identification targets at learning discriminative representations for
object retrieval without any annotations. Clustering-based methods conduct training with the …

Recent advances in deep learning have led to the development of accurate and efficient
models for various computer vision applications such as classification, segmentation, and …

Cross-domain object detection is challenging, because object detection model is often
vulnerable to data variance, especially to the considerable domain shift between two …

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 …