L. Lin

Publications
Influence

SNAS: Stochastic Neural Architecture Search

S. Xie, H. Zheng, Chunxiao Liu, L. Lin
Computer Science, Mathematics
ICLR
27 September 2018

We propose Stochastic Neural Architecture Search (SNAS), an economical end-to-end solution to Neural Architecture search (NAS) that trains neural operation parameters and architecture distribution parameters in same round of back propagation, while maintaining the completeness and differentiability of the NAS pipeline. Expand

Is Faster R-CNN Doing Well for Pedestrian Detection?

L. Zhang, L. Lin, Xiaodan Liang, Kaiming He
Computer Science
ECCV
24 July 2016

In this paper, we investigate issues involving Faster R-CNN for pedestrian detection. Expand

NTIRE 2017 Challenge on Single Image Super-Resolution: Methods and Results

R. Timofte, Eirikur Agustsson, +74 authors Q. Guo
Computer Science
IEEE Conference on Computer Vision and Pattern…
21 July 2017

This paper reviews the first challenge on single image super-resolution (restoration of rich details in an low resolution image) with focus on proposed solutions and results. Expand

Deep feature learning with relative distance comparison for person re-identification

Sheng-yong Ding, L. Lin, Guangrun Wang, Hong-Yang Chao
Mathematics, Computer Science
Pattern Recognit.
1 October 2015

We present a scalable distance driven feature learning framework based on the deep neural network for person re-identification, and demonstrate its effectiveness to handle the existing challenges. Expand

Bit-Scalable Deep Hashing With Regularized Similarity Learning for Image Retrieval and Person Re-Identification

Ruimao Zhang, L. Lin, Rui Zhang, W. Zuo, Lei Zhang
Computer Science, Medicine
IEEE Transactions on Image Processing
11 August 2015

We propose a supervised learning framework to generate compact and bit-scalable hashing codes directly from raw images. Expand

Deep Cocktail Network: Multi-source Unsupervised Domain Adaptation with Category Shift

Ruijia Xu, Ziliang Chen, W. Zuo, J. Yan, L. Lin
Computer Science, Mathematics
IEEE/CVF Conference on Computer Vision and…
2 March 2018

Unsupervised domain adaptation (UDA) conventionally assumes labeled source samples coming from a single underlying source distribution. Expand

Cost-Effective Active Learning for Deep Image Classification

Keze Wang, Dongyu Zhang, Ya Li, Ruimao Zhang, L. Lin
Computer Science
IEEE Transactions on Circuits and Systems for…
13 January 2017

In this paper, we propose a novel active learning (AL) framework, which is capable of building a competitive classifier with optimal feature representation via a limited amount of labeled training instances in an incremental learning manner. Expand

Instance-Level Salient Object Segmentation

Guanbin Li, Y. Xie, L. Lin, Y. Yu
Computer Science
IEEE Conference on Computer Vision and Pattern…
12 April 2017

In this paper, we present a salient instance segmentation method that produces a saliency mask with distinct object instance labels for an input image. Expand

Multi-level Wavelet-CNN for Image Restoration

P. Liu, Hongzhi Zhang, Kai Zhang, L. Lin, W. Zuo
Computer Science
IEEE/CVF Conference on Computer Vision and…
18 May 2018

In this paper, we present a novel multi-level wavelet CNN (MWCNN) model for better tradeoff between receptive field size and computational efficiency. Expand

Toward Characteristic-Preserving Image-based Virtual Try-On Network

Bochao Wang, Hongwei Zhang, Xiaodan Liang, Y. Chen, L. Lin, Meng Yang
Computer Science
ECCV
20 July 2018

We propose a new fully-learnable Characteristic-Preserving Virtual Try-On Network (CP-VTON) for addressing all real-world challenges in this task. Expand

Recommended Authors