Zobrazeno 1 - 10
of 896
pro vyhledávání: '"BAI, Yue"'
Vision foundation models are renowned for their generalization ability due to massive training data. Nevertheless, they demand tremendous training resources, and the training data is often inaccessible, e.g., CLIP, DINOv2, posing great challenges to
Externí odkaz:
http://arxiv.org/abs/2407.10366
Training large language models (LLMs) and multimodal LLMs necessitates significant computing resources, and existing publicly available LLMs are typically pre-trained on diverse, privately curated datasets spanning various tasks. For instance, LLaMA,
Externí odkaz:
http://arxiv.org/abs/2407.08196
Recent studies have drawn attention to the untapped potential of the "star operation" (element-wise multiplication) in network design. While intuitive explanations abound, the foundational rationale behind its application remains largely unexplored.
Externí odkaz:
http://arxiv.org/abs/2403.19967
Current training pipelines in object recognition neglect Hue Jittering when doing data augmentation as it not only brings appearance changes that are detrimental to classification, but also the implementation is inefficient in practice. In this study
Externí odkaz:
http://arxiv.org/abs/2403.09506
Latent graph inference (LGI) aims to jointly learn the underlying graph structure and node representations from data features. However, existing LGI methods commonly suffer from the issue of supervision starvation, where massive edge weights are lear
Externí odkaz:
http://arxiv.org/abs/2310.04314
Existing video recognition algorithms always conduct different training pipelines for inputs with different frame numbers, which requires repetitive training operations and multiplying storage costs. If we evaluate the model using other frames which
Externí odkaz:
http://arxiv.org/abs/2303.14817
Anomaly detection in videos is a significant yet challenging problem. Previous approaches based on deep neural networks employ either reconstruction-based or prediction-based approaches. Nevertheless, existing reconstruction-based methods 1) rely on
Externí odkaz:
http://arxiv.org/abs/2301.12048
The state of neural network pruning has been noticed to be unclear and even confusing for a while, largely due to "a lack of standardized benchmarks and metrics" [3]. To standardize benchmarks, first, we need to answer: what kind of comparison setup
Externí odkaz:
http://arxiv.org/abs/2301.05219