← Search

Shao-Ping Lu

7 accepted papers

2021

DOTS: Decoupling Operation and Topology in Differentiable Architecture Search

CVPR 2021poster

Differentiable Architecture Search (DARTS) has attracted extensive attention due to its efficiency in searching for cell structures. DARTS mainly focuses on the operation search and derives the cell topology from the operation weights. However, the operation weights can not indicate the importance o…

Cited by 72PDFcodeScholar
2021

Deep Symmetric Network for Underexposed Image Enhancement With Recurrent Attentional Learning

ICCV 2021poster

Underexposed image enhancement is of importance in many research domains. In this paper, we take this problem as image feature transformation between the underexposed image and its paired enhanced version, and we propose a deep symmetric network for the issue. Our symmetric network adapts invertible…

Cited by 70PDFScholar
2021

News Content Completion with Location-Aware Image Selection

AAAI 2021technical

News, as one of the fundamental social media types, typically contains both texts and images. Image selection, which involves choosing appropriate images according to some specified contexts, is crucial for formulating good news. However, it presents two challenges: where to place images and which i…

Cited by 2SourcePDFScholar
2021

iNAS: Integral NAS for Device-Aware Salient Object Detection

ICCV 2021poster

Existing salient object detection (SOD) models usually focus on either backbone feature extractors or saliency heads, ignoring their relations. A powerful backbone could still achieve sub-optimal performance with a weak saliency head and vice versa. Moreover, the balance between model performance an…

Cited by 13PDFScholar
2020

Interactive Image Segmentation With First Click Attention

CVPR 2020poster

In the task of interactive image segmentation, users initially click one point to segment the main body of the target object and then provide more points on mislabeled regions iteratively for a precise segmentation. Existing methods treat all interaction points indiscriminately, ignoring the differe…

Cited by 201PDFScholar
2018

Structured Skip List: A Compact Data Structure for 3D Reconstruction

IROS 2018poster

The model produced by 3D reconstruction algorithm is usually represented by voxels. The management of these voxels is usually divided into two categories: ordered and unordered methods. The ordered method holds too many empty voxels to maintain data order which leads to a low storage efficiency. On…

Cited by 3SourceScholar