Search Results for author:
Found 7 papers, 1 papers with code
An empirical study of a pruning mechanism
For the pruning and retraining phase, whether the pruned-and-retrained network benefits from the pretrained network indded is examined.
Joint Negative and Positive Learning for Noisy Labels
Based on the fact that directly providing the label to the data (Positive Learning; PL) has a risk of allowing CNNs to memorize the contaminated labels for the case of noisy data, the indirect learning approach that uses complementary labels (Negative Learning for Noisy Labels; NLNL) has proven to be highly effective in preventing overfitting to noisy data as it reduces the risk of providing faulty target.
DLCFT: Deep Linear Continual Fine-Tuning for General Incremental Learning
We show that this allows us to design a linear model where quadratic parameter regularization method is placed as the optimal continual learning policy, and at the same time enjoying the high performance of neural networks.
UniCLIP: Unified Framework for Contrastive Language-Image Pre-training
Pre-training vision-language models with contrastive objectives has shown promising results that are both scalable to large uncurated datasets and transferable to many downstream applications.
Lightweight Monocular Depth Estimation via Token-Sharing Transformer
While most lightweight monocular depth estimation methods have been developed using convolution neural networks, the Transformer has been gradually utilized in monocular depth estimation recently.
Disposable Transfer Learning for Selective Source Task Unlearning
Whether the model successfully unlearns the source task is measured by piggyback learning accuracy (PL accuracy).
FRED: Towards a Full Rotation-Equivariance in Aerial Image Object Detection
Compared to state-of-the-art methods, our proposed method delivers comparable performance on DOTA-v1. 0 and outperforms by 1. 5 mAP on DOTA-v1. 5, all while significantly reducing the model parameters to 16%.
