Fine Grained
Fine-grained analysis focuses on achieving high precision and detail in various domains, moving beyond coarse-grained classifications. Current research emphasizes developing models capable of handling nuanced distinctions, often employing techniques like multi-modal learning, transformer architectures, and diffusion models to achieve this fine-grained understanding in tasks ranging from image captioning and object detection to legal analysis and speech processing. This detailed level of analysis is crucial for advancing fields like medical diagnosis, legal technology, and scientific discovery, enabling more accurate and insightful interpretations of complex data. The development of robust and efficient fine-grained models is driving progress across numerous scientific and practical applications.
Papers
There's no Data Like Better Data: Using QE Metrics for MT Data Filtering
Jan-Thorsten Peter, David Vilar, Daniel Deutsch, Mara Finkelstein, Juraj Juraska, Markus Freitag
u-LLaVA: Unifying Multi-Modal Tasks via Large Language Model
Jinjin Xu, Liwu Xu, Yuzhe Yang, Xiang Li, Fanyi Wang, Yanchun Xie, Yi-Jie Huang, Yaqian Li
Protein-ligand binding representation learning from fine-grained interactions
Shikun Feng, Minghao Li, Yinjun Jia, Weiying Ma, Yanyan Lan
FLIP: Fine-grained Alignment between ID-based Models and Pretrained Language Models for CTR Prediction
Hangyu Wang, Jianghao Lin, Xiangyang Li, Bo Chen, Chenxu Zhu, Ruiming Tang, Weinan Zhang, Yong Yu
Revisiting Evaluation Metrics for Semantic Segmentation: Optimization and Evaluation of Fine-grained Intersection over Union
Zifu Wang, Maxim Berman, Amal Rannen-Triki, Philip H. S. Torr, Devis Tuia, Tinne Tuytelaars, Luc Van Gool, Jiaqian Yu, Matthew B. Blaschko