Search Results for author:
Found 5 papers, 3 papers with code
TinyPredNet: A Lightweight Framework for Satellite Image Sequence Prediction
In this article, we propose a lightweight prediction framework TinyPredNet for satellite image sequence prediction, in which a spatial encoder and decoder model the intra-frame appearance features and a temporal translator captures inter-frame motion patterns.
HPCR: Holistic Proxy-based Contrastive Replay for Online Continual Learning
Inspired by this finding, we propose a novel replay-based method called proxy-based contrastive replay (PCR), which replaces anchor-to-sample pairs with anchor-to-proxy pairs in the contrastive-based loss to alleviate the phenomenon of forgetting.
UER: A Heuristic Bias Addressing Approach for Online Continual Learning
By decomposing the dot-product logits into an angle factor and a norm factor, we empirically find that the bias problem mainly occurs in the angle factor, which can be used to learn novel knowledge as cosine logits.
MetaDiff: Meta-Learning with Conditional Diffusion for Few-Shot Learning
Its key idea is learning a deep model in a bi-level optimization manner, where the outer-loop process learns a shared gradient descent algorithm (i. e., its hyperparameters), while the inner-loop process leverage it to optimize a task-specific model by using only few labeled data.
PCR: Proxy-based Contrastive Replay for Online Class-Incremental Continual Learning
It aims to continuously learn new classes from data stream and the samples of data stream are seen only once, which suffers from the catastrophic forgetting issue, i. e., forgetting historical knowledge of old classes.
