Search Results for author:
Found 15 papers, 4 papers with code
PanGu-Draw: Advancing Resource-Efficient Text-to-Image Synthesis with Time-Decoupled Training and Reusable Coop-Diffusion
Current large-scale diffusion models represent a giant leap forward in conditional image synthesis, capable of interpreting diverse cues like text, human poses, and edges.
Learning Low-Rank Representations for Model Compression
Vector Quantization (VQ) is an appealing model compression method to obtain a tiny model with less accuracy loss.
EfficientTrain: Exploring Generalized Curriculum Learning for Training Visual Backbones
It is also effective for self-supervised learning (e. g., MAE).
Collaboration of Experts: Achieving 80% Top-1 Accuracy on ImageNet with 100M FLOPs
Our method achieves the state-of-the-art performance on ImageNet, 80. 7% top-1 accuracy with 194M FLOPs.
Ranked #577 on
Image Classification
on ImageNet
Learning specialized activation functions with the Piecewise Linear Unit
It can learn specialized activation functions and achieves SOTA performance on large-scale datasets like ImageNet and COCO.
FixNorm: Dissecting Weight Decay for Training Deep Neural Networks
Based on this discovery, we propose a new training method called FixNorm, which discards weight decay and directly controls the two mechanisms.
AutoBSS: An Efficient Algorithm for Block Stacking Style Search
Neural network architecture design mostly focuses on the new convolutional operator or special topological structure of network block, little attention is drawn to the configuration of stacking each block, called Block Stacking Style (BSS).
DyNet: Dynamic Convolution for Accelerating Convolutional Neural Networks
On one hand, we can reduce the computation cost remarkably while maintaining the performance.
Adversarial AutoAugment
The augmentation policy network attempts to increase the training loss of a target network through generating adversarial augmentation policies, while the target network can learn more robust features from harder examples to improve the generalization.
Ranked #594 on
Image Classification
on ImageNet
BETANAS: BalancEd TrAining and selective drop for Neural Architecture Search
Automatic neural architecture search techniques are becoming increasingly important in machine learning area.
DyNet: Dynamic Convolution for Accelerating Convolution Neural Networks
To verify the scalability, we also apply DyNet on segmentation task, the results show that DyNet can reduces 69. 3% FLOPs while maintaining the Mean IoU on segmentation task.
IRLAS: Inverse Reinforcement Learning for Architecture Search
Motivated by the fact that human-designed networks are elegant in topology with a fast inference speed, we propose a mirror stimuli function inspired by biological cognition theory to extract the abstract topological knowledge of an expert human-design network (ResNeXt).
Synaptic Strength For Convolutional Neural Network
Inspired by the relevant concept in neural science literature, we propose Synaptic Pruning: a data-driven method to prune connections between input and output feature maps with a newly proposed class of parameters called Synaptic Strength.
BlockQNN: Efficient Block-wise Neural Network Architecture Generation
The block-wise generation brings unique advantages: (1) it yields state-of-the-art results in comparison to the hand-crafted networks on image classification, particularly, the best network generated by BlockQNN achieves 2. 35% top-1 error rate on CIFAR-10.
Practical Block-wise Neural Network Architecture Generation
Convolutional neural networks have gained a remarkable success in computer vision.
