Junying Huang

TL;DR: The Vision Meets Drone Object Detection in Image Challenge (VME-DET 2019) as discussed by the authors, held in conjunction with the 17th International Conference on Computer Vision (ICCV 2019), focuses on image object detection on drones.

TL;DR: This paper proposes an adaptive cropping method based on a Difficult Region Estimation Network (DREN) to enhance the detection of the difficult targets, which allows the detector to fully exploit its performance during the testing phase.

TL;DR: This work attempts to achieve the virtual-to-real scene parsing from a new perspective inspired by few-shot learning, and develops a two-stage adversarial network which contains a scene parser and two discriminators that can handle the problem of scarce target data well and make full use of the limited semantic labels.

TL;DR: This work proposes a novel few-shot supervised domain adaptation framework for semantic segmentation to exploit adversarial learning to align the features extracted from networks with a pairing method of creating pairs using source data and target data.

TL;DR: Zhang et al. as discussed by the authors proposed a local-agnostic training strategy to avoid the discriminative location bias between the base and novel categories, and a novel local-level similarity measure to capture the accurate comparison between local level features, and synthesize different knowledge transfers from the base category according to different location features.