• Publications
  • Influence
Generative Image Inpainting with Contextual Attention
TLDR
This work proposes a new deep generative model-based approach which can not only synthesize novel image structures but also explicitly utilize surrounding image features as references during network training to make better predictions.
Free-Form Image Inpainting With Gated Convolution
TLDR
The proposed gated convolution solves the issue of vanilla convolution that treats all input pixels as valid ones, generalizes partial convolution by providing a learnable dynamic feature selection mechanism for each channel at each spatial location across all layers.
Conformer: Convolution-augmented Transformer for Speech Recognition
TLDR
This work proposes the convolution-augmented transformer for speech recognition, named Conformer, which significantly outperforms the previous Transformer and CNN based models achieving state-of-the-art accuracies.
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 and gauges the state-of-the-art in single imagesuper-resolution.
Slimmable Neural Networks
TLDR
This work presents a simple and general method to train a single neural network executable at different widths, permitting instant and adaptive accuracy-efficiency trade-offs at runtime, and demonstrates better performance of slimmable models compared with individual ones across a wide range of applications.
Universally Slimmable Networks and Improved Training Techniques
TLDR
This work proposes a systematic approach to train universally slimmable networks (US-Nets), extending slimmables to execute at arbitrary width, and generalizing to networks both with and without batch normalization layers, and opens up the possibility to directly evaluate FLOPs-Accuracy spectrum of network architectures.
Wide Activation for Efficient and Accurate Image Super-Resolution
TLDR
This report demonstrates that with same parameters and computational budgets, models with wider features before ReLU activation have significantly better performance for single image super-resolution (SISR) and introduces linear low-rank convolution into SR networks to achieve even better accuracy-efficiency tradeoffs.
UnitBox: An Advanced Object Detection Network
TLDR
A novel Intersection over Union (IoU) loss function for bounding box prediction, which regresses the four bounds of a predicted box as a whole unit, and introduces the UnitBox, which performs accurate and efficient localization, shows robust to objects of varied shapes and scales, and converges fast.
BigNAS: Scaling Up Neural Architecture Search with Big Single-Stage Models
TLDR
The proposed BigNAS, an approach that challenges the conventional wisdom that post-processing of the weights is necessary to get good prediction accuracies, is proposed, able to train a single set of shared weights on ImageNet and use these weights to obtain child models whose sizes range from 200 to 1000 MFLOPs.
AutoSlim: Towards One-Shot Architecture Search for Channel Numbers
TLDR
A simple and one-shot solution to set channel numbers in a neural network to achieve better accuracy under constrained resources (e.g., FLOPs, latency, memory footprint or model size) is presented.
...
1
2
3
4
5
...