Pedestrian Attribute Recognition (PAR) plays a crucial role in various computer vision applications, demanding precise and reliable identification of attributes from pedestrian images. Traditional PAR methods, though ...
详细信息
The proliferation of Internet of Things (IoT) devices and edge computing applications has heightened the demand for efficient resource allocation and pricing mechanisms. Effective pricing strategies play a crucial rol...
详细信息
Discrete chaotic systems based on memristors exhibit excellent dynamical properties and are more straightforward to implement in hardware, making them highly suitable for generating cryptographic keystreams. However, ...
详细信息
Recent studies have focused on leveraging large-scale artificial intelligence (LAI) models to improve semantic representation and compression capabilities. However, the substantial computational demands of LAI models ...
详细信息
Visual Place Recognition (VPR) is aimed at predicting the location of a query image by referencing a database of geotagged images. For VPR task, often fewer discriminative local regions in an image produce important e...
详细信息
Retrieval models typically rely on costly human-labeled query-document relevance annotations for training and evaluation. To reduce this cost and leverage the potential of Large Language Models (LLMs) in relevance jud...
详细信息
Retrieval models typically rely on costly human-labeled query-document relevance annotations for training and evaluation. To reduce this cost and leverage the potential of Large Language Models (LLMs) in relevance judgments, we aim to explore whether LLM-generated annotations can effectively replace human annotations in training retrieval models. Retrieval usually emphasizes relevance, which indicates "topic-relatedness" of a document to a query, while in RAG, the value of a document (or utility), depends on how it contributes to answer generation. Recognizing this mismatch, some researchers use LLM performance on downstream tasks with documents as labels, but this approach requires manual answers for specific tasks, leading to high costs and limited generalization. In another line of work, prompting LLMs to select useful documents as RAG references eliminates the need for human annotation and is not task-specific. If we leverage LLMs’ utility judgments to annotate retrieval data, we may retain cross-task generalization without human annotation in large-scale corpora. Therefore, we investigate utility-focused annotation via LLMs for large-scale retriever training data across both in-domain and out-of-domain settings on the retrieval and RAG tasks. To reduce the impact of low-quality positives labeled by LLMs, we design a novel loss function, i.e., Disj-InfoNCE. Our experiments reveal that: (1) Retrievers trained on utility-focused annotations significantly outperform those trained on human annotations in the out-of-domain setting on both tasks, demonstrating superior generalization capabilities. (2) LLM annotation does not replace human annotation in the in-domain setting. However, incorporating just 20% human-annotated data enables retrievers trained with utility-focused annotations to match the performance of models trained entirely with human annotations, while adding 100% human annotations further significantly enhances performance on both tasks. We hope our wor
Raman distributed optical fiber temperature sensor based on single-photon detection (RDTS-SPD) improves the spatial resolution in temperature sensing. However, the temperature accuracy of RDTS-SPD is hindered by the p...
详细信息
Blood vessel analysis is significant in many clinical domains, such as laryngology, ophthalmology, and neurosurgery. The second near-infrared window (NIR-II) fluorescence imaging is a promising technique in providing ...
详细信息
Demographic attributes are important resources for market analysis, which are widely used to characterize different types of users. However, such signals are only available for a small fraction of users due to the dif...
详细信息
The electrocardiogram diagnosis played an important role in early arrhythmia prevention and cardiovascular disease detection. How to analysis and detect the electrocardiogram automatically becomes a challenging task i...
详细信息
暂无评论