Zobrazeno 1 - 6
of 6
pro vyhledávání: '"Lee, JunHoo"'
Conventional dataset distillation requires significant computational resources and assumes access to the entire dataset, an assumption impractical as it presumes all data resides on a central server. In this paper, we focus on dataset distillation in
Externí odkaz:
http://arxiv.org/abs/2405.00348
Large Models (LMs) have heightened expectations for the potential of general AI as they are akin to human intelligence. This paper shows that recent large models such as Stable Diffusion and DALL-E3 also share the vulnerability of human intelligence,
Externí odkaz:
http://arxiv.org/abs/2404.15154
Coreset selection is a method for selecting a small, representative subset of an entire dataset. It has been primarily researched in image classification, assuming there is only one object per image. However, coreset selection for object detection is
Externí odkaz:
http://arxiv.org/abs/2404.09161
Deep learning has achieved tremendous success. \nj{However,} unlike SVMs, which provide direct decision criteria and can be trained with a small dataset, it still has significant weaknesses due to its requirement for massive datasets during training
Externí odkaz:
http://arxiv.org/abs/2403.17329
Although meta-learning seems promising performance in the realm of rapid adaptability, it is constrained by fixed cardinality. When faced with tasks of varying cardinalities that were unseen during training, the model lacks its ability. In this paper
Externí odkaz:
http://arxiv.org/abs/2401.05097
In this paper, we hypothesize that gradient-based meta-learning (GBML) implicitly suppresses the Hessian along the optimization trajectory in the inner loop. Based on this hypothesis, we introduce an algorithm called SHOT (Suppressing the Hessian alo
Externí odkaz:
http://arxiv.org/abs/2310.02751