Zobrazeno 1 - 10
of 2 680
pro vyhledávání: '"SUN, YANAN"'
Deep long-tailed recognition has been widely studied to address the issue of imbalanced data distributions in real-world scenarios. However, there has been insufficient focus on the design of neural architectures, despite empirical evidence suggestin
Externí odkaz:
http://arxiv.org/abs/2411.06098
In this paper, we show that, a good style representation is crucial and sufficient for generalized style transfer without test-time tuning. We achieve this through constructing a style-aware encoder and a well-organized style dataset called StyleGall
Externí odkaz:
http://arxiv.org/abs/2407.01414
The field of text-to-image (T2I) generation has made significant progress in recent years, largely driven by advancements in diffusion models. Linguistic control enables effective content creation, but struggles with fine-grained control over image g
Externí odkaz:
http://arxiv.org/abs/2406.18958
Neural predictors are effective in boosting the time-consuming performance evaluation stage in neural architecture search (NAS), owing to their direct estimation of unseen architectures. Despite the effectiveness, training a powerful neural predictor
Externí odkaz:
http://arxiv.org/abs/2406.02056
To defend deep neural networks from adversarial attacks, adversarial training has been drawing increasing attention for its effectiveness. However, the accuracy and robustness resulting from the adversarial training are limited by the architecture, b
Externí odkaz:
http://arxiv.org/abs/2405.05502
Efforts to overcome catastrophic forgetting have primarily centered around developing more effective Continual Learning (CL) methods. In contrast, less attention was devoted to analyzing the role of network architecture design (e.g., network depth, w
Externí odkaz:
http://arxiv.org/abs/2404.14829
Autor:
Sun, Yanan, Valachovic, Edward
Air quality is a critical component of environmental health. Monitoring and analysis of particulate matter with a diameter of 2.5 micrometers or smaller (PM2.5) plays a pivotal role in understanding air quality changes. This study focuses on the appl
Externí odkaz:
http://arxiv.org/abs/2404.08738
As Pre-trained Language Models (PLMs), a popular approach for code intelligence, continue to grow in size, the computational cost of their usage has become prohibitively expensive. Prompt learning, a recent development in the field of natural languag
Externí odkaz:
http://arxiv.org/abs/2403.13588
Evolutionary neural architecture search (ENAS) employs evolutionary algorithms to find high-performing neural architectures automatically, and has achieved great success. However, compared to the empirical success, its rigorous theoretical analysis h
Externí odkaz:
http://arxiv.org/abs/2401.11712