• Publications
  • Influence
SNAS: Stochastic Neural Architecture Search
TLDR
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
  • 350
  • 84
  • PDF
Is Faster R-CNN Doing Well for Pedestrian Detection?
TLDR
In this paper, we investigate issues involving Faster R-CNN for pedestrian detection. Expand
  • 510
  • 82
  • PDF
NTIRE 2017 Challenge on Single Image Super-Resolution: Methods and Results
TLDR
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
  • 526
  • 49
  • PDF
Deep feature learning with relative distance comparison for person re-identification
TLDR
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
  • 495
  • 48
  • PDF
Bit-Scalable Deep Hashing With Regularized Similarity Learning for Image Retrieval and Person Re-Identification
TLDR
We propose a supervised learning framework to generate compact and bit-scalable hashing codes directly from raw images. Expand
  • 381
  • 41
  • PDF
Deep Cocktail Network: Multi-source Unsupervised Domain Adaptation with Category Shift
TLDR
Unsupervised domain adaptation (UDA) conventionally assumes labeled source samples coming from a single underlying source distribution. Expand
  • 104
  • 32
  • PDF
Cost-Effective Active Learning for Deep Image Classification
TLDR
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
  • 261
  • 31
  • PDF
Instance-Level Salient Object Segmentation
TLDR
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
  • 173
  • 30
  • PDF
Multi-level Wavelet-CNN for Image Restoration
TLDR
In this paper, we present a novel multi-level wavelet CNN (MWCNN) model for better tradeoff between receptive field size and computational efficiency. Expand
  • 141
  • 30
  • PDF
Toward Characteristic-Preserving Image-based Virtual Try-On Network
TLDR
We propose a new fully-learnable Characteristic-Preserving Virtual Try-On Network (CP-VTON) for addressing all real-world challenges in this task. Expand
  • 74
  • 30
  • PDF