Glance Annotation
Glance annotation, a novel data labeling paradigm, focuses on minimizing annotation effort while maximizing model performance in various machine learning tasks, particularly in computer vision and natural language processing. Current research explores efficient algorithms and model architectures, such as those based on transformers and generative adversarial networks, to leverage these sparsely annotated datasets for tasks ranging from object detection and video anomaly detection to multimodal question answering and logical reasoning. This approach holds significant promise for improving the efficiency and scalability of training complex models, particularly in domains with limited labeled data, thereby impacting both research methodologies and real-world applications.
Papers
Fast Chain-of-Thought: A Glance of Future from Parallel Decoding Leads to Answers Faster
Hongxuan Zhang, Zhining Liu, Yao Zhao, Jiaqi Zheng, Chenyi Zhuang, Jinjie Gu, Guihai Chen
GlanceSeg: Real-time microaneurysm lesion segmentation with gaze-map-guided foundation model for early detection of diabetic retinopathy
Hongyang Jiang, Mengdi Gao, Zirong Liu, Chen Tang, Xiaoqing Zhang, Shuai Jiang, Wu Yuan, Jiang Liu
A Closer Look at the Self-Verification Abilities of Large Language Models in Logical Reasoning
Ruixin Hong, Hongming Zhang, Xinyu Pang, Dong Yu, Changshui Zhang