• Publications
  • Influence
Learning Structured Output Representation using Deep Conditional Generative Models
TLDR
A deep conditional generative model for structured output prediction using Gaussian latent variables is developed, trained efficiently in the framework of stochastic gradient variational Bayes, and allows for fast prediction using Stochastic feed-forward inference.
FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence
TLDR
This paper demonstrates the power of a simple combination of two common SSL methods: consistency regularization and pseudo-labeling, and shows that FixMatch achieves state-of-the-art performance across a variety of standard semi-supervised learning benchmarks.
Learning to Adapt Structured Output Space for Semantic Segmentation
TLDR
A multi-level adversarial network is constructed to effectively perform output space domain adaptation at different feature levels and it is shown that the proposed method performs favorably against the state-of-the-art methods in terms of accuracy and visual quality.
Improved Deep Metric Learning with Multi-class N-pair Loss Objective
TLDR
This paper proposes a new metric learning objective called multi-class N-pair loss, which generalizes triplet loss by allowing joint comparison among more than one negative examples and reduces the computational burden of evaluating deep embedding vectors via an efficient batch construction strategy using only N pairs of examples.
Attribute2Image: Conditional Image Generation from Visual Attributes
TLDR
A layered generative model with disentangled latent variables that can be learned end-to-end using a variational auto-encoder is developed and shows excellent quantitative and visual results in the tasks of attribute-conditioned image reconstruction and completion.
ReMixMatch: Semi-Supervised Learning with Distribution Alignment and Augmentation Anchoring
TLDR
A variant of AutoAugment which learns the augmentation policy while the model is being trained, and is significantly more data-efficient than prior work, requiring between $5\times and $16\times less data to reach the same accuracy.
ReMixMatch: Semi-Supervised Learning with Distribution Matching and Augmentation Anchoring
TLDR
A variant of AutoAugment which learns the augmentation policy while the model is being trained, and is significantly more data-efficient than prior work, requiring between 5 times and 16 times less data to reach the same accuracy.
Understanding and Improving Convolutional Neural Networks via Concatenated Rectified Linear Units
TLDR
This paper proposes a novel, simple yet effective activation scheme called concatenated ReLU (CRelu) and theoretically analyze its reconstruction property in CNNs and integrates CRelu into several state-of-the-art CNN architectures and demonstrates improvement in their recognition performance on CIFAR-10/100 and ImageNet datasets with fewer trainable parameters.
Towards Large-Pose Face Frontalization in the Wild
TLDR
This work proposes a novel deep 3D Morphable Model (3DMM) conditioned Face Frontalization Generative Adversarial Network (GAN), termed as FF-GAN, to generate neutral head pose face images, which differs from both traditional GANs and 3DMM based modeling.
Augmenting CRFs with Boltzmann Machine Shape Priors for Image Labeling
TLDR
A new model is presented that uses the combined power of these two network types to build a state-of-the-art labeler and it is demonstrated that the hidden units in the RBM portion of the model can be interpreted as face attributes that have been learned without any attribute-level supervision.
...
1
2
3
4
5
...