Search Results for author:
Found 14 papers, 5 papers with code
TVT: Training-Free Vision Transformer Search on Tiny Datasets
In this paper, for the first time, we investigate how to search in a training-free manner with the help of teacher models and devise an effective Training-free ViT (TVT) search framework.
EMQ: Evolving Training-free Proxies for Automated Mixed Precision Quantization
In particular, we devise an elaborate search space involving the existing proxies and perform an evolution search to discover the best correlated MQ proxy.
Self-Evolution Learning for Mixup: Enhance Data Augmentation on Few-Shot Text Classification Tasks
However, most of the mixup methods do not consider the varying degree of learning difficulty in different stages of training and generate new samples with one hot labels, resulting in the model over confidence.
Progressive Meta-Pooling Learning for Lightweight Image Classification Model
Practical networks for edge devices adopt shallow depth and small convolutional kernels to save memory and computational cost, which leads to a restricted receptive field.
RD-NAS: Enhancing One-shot Supernet Ranking Ability via Ranking Distillation from Zero-cost Proxies
In this paper, we propose Ranking Distillation one-shot NAS (RD-NAS) to enhance ranking consistency, which utilizes zero-cost proxies as the cheap teacher and adopts the margin ranking loss to distill the ranking knowledge.
OVO: One-shot Vision Transformer Search with Online distillation
OVO samples sub-nets for both teacher and student networks for better distillation results.
DMFormer: Closing the Gap Between CNN and Vision Transformers
Vision transformers have shown excellent performance in computer vision tasks.
AIM 2022 Challenge on Super-Resolution of Compressed Image and Video: Dataset, Methods and Results
The homepage of this challenge is at https://github. com/RenYang-home/AIM22_CompressSR.
Prior-Guided One-shot Neural Architecture Search
In this paper, we present Prior-Guided One-shot NAS (PGONAS) to strengthen the ranking correlation of supernets.
Learning Convolutional Neural Networks in the Frequency Domain
The most important motivation of this research is that we can use the straightforward element-wise multiplication operation to replace the image convolution in the frequency domain based on the Cross-Correlation Theorem, which obviously reduces the computation complexity.
Multi-trial Neural Architecture Search with Lottery Tickets
Neural architecture search (NAS) has brought significant progress in recent image recognition tasks.
Fixed-size Objects Encoding for Visual Relationship Detection
Instead, we propose a novel method to encode all background objects in each image by using one fixed-size vector (i. e., FBE vector).
STMARL: A Spatio-Temporal Multi-Agent Reinforcement Learning Approach for Cooperative Traffic Light Control
Moreover, based on the temporally-dependent traffic information, we design a Graph Neural Network based model to represent relationships among multiple traffic lights, and the decision for each traffic light will be made in a distributed way by the deep Q-learning method.
DropFilter: A Novel Regularization Method for Learning Convolutional Neural Networks
Most of previous methods mainly consider to drop features from input data and hidden layers, such as Dropout, Cutout and DropBlocks.
