• Publications
  • Influence
Random Erasing Data Augmentation
TLDR
In training, Random Erasing randomly selects a rectangle region in an image and erases its pixels with random values and yields consistent improvement over strong baselines in image classification, object detection and person re-identification. Expand
Soft Filter Pruning for Accelerating Deep Convolutional Neural Networks
TLDR
The proposed Soft Filter Pruning method enables the pruned filters to be updated when training the model after pruning, which has two advantages over previous works: larger model capacity and less dependence on the pre-trained model. Expand
Image-Image Domain Adaptation with Preserved Self-Similarity and Domain-Dissimilarity for Person Re-identification
TLDR
Through domain adaptation experiment, it is shown that images generated by SPGAN are more suitable for domain adaptation and yield consistent and competitive re-ID accuracy on two large-scale datasets. Expand
Contrastive Adaptation Network for Unsupervised Domain Adaptation
TLDR
This paper proposes Contrastive Adaptation Network optimizing a new metric which explicitly models the intra- class domain discrepancy and the inter-class domain discrepancy, and designs an alternating update strategy for training CAN in an end-to-end manner. Expand
Self-produced Guidance for Weakly-supervised Object Localization
TLDR
Self-produced Guidance (SPG) masks which separate the foreground i.e., the object of interest, from the background to provide the classification networks with spatial correlation information of pixels are proposed. Expand
Multi-Interest Network with Dynamic Routing for Recommendation at Tmall
TLDR
This paper designs a multi-interest extractor layer based on the recently proposed dynamic routing mechanism, which is applicable for modeling and extracting diverse interests from user's behaviors, and proposes a technique named label-aware attention to help the learning process of user representations. Expand
Multi-Modal Curriculum Learning for Semi-Supervised Image Classification
TLDR
A well-organized propagation process leveraging multiple teachers and one learner enables the multi-modal curriculum learning (MMCL) strategy to outperform five state-of-the-art methods on eight popular image data sets. Expand
Deep Adversarial Attention Alignment for Unsupervised Domain Adaptation: the Benefit of Target Expectation Maximization
TLDR
This paper proposes an attention alignment scheme on all the target convolutional layers to uncover the knowledge shared by the source domain, and estimates the posterior label distribution of the unlabeled data for target network training. Expand
Attract or Distract: Exploit the Margin of Open Set
TLDR
This paper exploits the semantic structure of open set data from two aspects: 1)Semantic Categorical Alignment, which aims to achieve good separability of target known classes by categorically aligning the centroid of target with the source, and 2) Semantic Contrastive Mapping,Which aims to push the unknown class away from the decision boundary. Expand
Content-Consistent Matching for Domain Adaptive Semantic Segmentation
TLDR
This paper considers the adaptation of semantic segmentation from the synthetic source domain to the real target domain and proposes a content-consistent matching (CCM) model, which yields consistent improvements over the baselines and performs favorably against previous state-of-the-arts tasks. Expand
...
1
2
3
...