Jianan Li

TL;DR: SAF R-CNN as discussed by the authors introduces multiple built-in subnetworks which detect pedestrians with scales from disjoint ranges, and outputs from all of the sub-networks are then adaptively combined to generate the final detection results that are shown to be robust to large variance in instance scales.

TL;DR: In this article, a dual path network (DPN) is proposed for image classification, which shares common features while maintaining the flexibility to explore new features through dual path architectures, achieving state-of-the-art performance on the ImagNet-1k, Places365 and PASCAL VOC datasets.

TL;DR: This work addresses the small object detection problem by developing a single architecture that internally lifts representations of small objects to super-resolved ones, achieving similar characteristics as large objects and thus more discriminative for detection.

TL;DR: Li et al. as discussed by the authors proposed a new Generative Adversarial Network (GAN) model that improves small object detection through narrowing representation difference of small objects from the large ones.

TL;DR: This work reveals the equivalence of the state-of-the-art Residual Network (ResNet) and Densely Convolutional Network (DenseNet) within the HORNN framework, and finds that ResNet enables feature re-usage while DenseNet enables new features exploration which are both important for learning good representations.