Zobrazeno 1 - 10
of 27
pro vyhledávání: '"Fu, Minghao"'
Music classification, with a wide range of applications, is one of the most prominent tasks in music information retrieval. To address the absence of comprehensive datasets and high-performing methods in the classification of mainstage dance music, t
Externí odkaz:
http://arxiv.org/abs/2409.06690
The rapid scaling of large vision pretrained models makes fine-tuning tasks more and more difficult on edge devices with low computational resources. We explore a new visual adaptation paradigm called edge tuning, which treats large pretrained models
Externí odkaz:
http://arxiv.org/abs/2406.17559
Deep Click-Through Rate (CTR) prediction models play an important role in modern industrial recommendation scenarios. However, high memory overhead and computational costs limit their deployment in resource-constrained environments. Low-rank approxim
Externí odkaz:
http://arxiv.org/abs/2405.18146
In finetuning a large pretrained model to downstream tasks, parameter-efficient fine-tuning (PEFT) methods can effectively finetune pretrained models with few trainable parameters, but suffer from high GPU memory consumption and slow training speed.
Externí odkaz:
http://arxiv.org/abs/2402.04009
Long-tailed object detection faces great challenges because of its extremely imbalanced class distribution. Recent methods mainly focus on the classification bias and its loss function design, while ignoring the subtle influence of the regression bra
Externí odkaz:
http://arxiv.org/abs/2401.15885
When pre-trained models become rapidly larger, the cost of fine-tuning on downstream tasks steadily increases, too. To economically fine-tune these models, parameter-efficient transfer learning (PETL) is proposed, which only tunes a tiny subset of tr
Externí odkaz:
http://arxiv.org/abs/2312.07856
Self-supervised learning (SSL) methods targeting scene images have seen a rapid growth recently, and they mostly rely on either a dedicated dense matching mechanism or a costly unsupervised object discovery module. This paper shows that instead of hi
Externí odkaz:
http://arxiv.org/abs/2308.03286
While scene text image super-resolution (STISR) has yielded remarkable improvements in accurately recognizing scene text, prior methodologies have placed excessive emphasis on optimizing performance, rather than paying due attention to efficiency - a
Externí odkaz:
http://arxiv.org/abs/2306.02443
In order to mimic the human few-shot learning (FSL) ability better and to make FSL closer to real-world applications, this paper proposes a practical FSL (pFSL) setting. pFSL is based on unsupervised pretrained models (analogous to human prior knowle
Externí odkaz:
http://arxiv.org/abs/2305.17368
Few-shot recognition learns a recognition model with very few (e.g., 1 or 5) images per category, and current few-shot learning methods focus on improving the average accuracy over many episodes. We argue that in real-world applications we may often
Externí odkaz:
http://arxiv.org/abs/2203.06574