object detection
PulseAugur coverage of object detection — every cluster mentioning object detection across labs, papers, and developer communities, ranked by signal.
2 天有情绪数据
-
新的RBDC协议将视觉模型训练成本降低了30%
研究人员开发了一种名为RBDC的新训练协议，以提高训练大型视觉模型的可资源效率。该方法通过无参数的块对角线方式递归地耦合独立训练的、更窄的模型。在ImageNet上使用Vision Transformers和ResNets进行的评估表明，与现有的增长方法相比，FLOPs减少了30%，准确率相当，并且在相同的训练FLOPs下性能有所提高。RBDC训练的模型在作为对象检测和实例分割等下游任务的骨干网络方面也显示出增强的效用。
-
New MS-DePro method improves object detection with depth and text prompts
Researchers have developed a new method called MS-DePro to improve object detection across different domains. This approach uses depth maps and text prompts to create more robust, domain-agnostic features. By integratin…
-
Surveys explore robot learning from human videos and world models, while new networks tackle driver monitoring.
Two new survey papers explore advancements in robot learning, focusing on different data acquisition and utilization strategies. One paper provides a comprehensive review of world models, which are predictive representa…
-
Lilian Weng details fast object detection models like YOLO and SSD
Two new research papers propose novel approaches to object detection. VFM4SDG aims to improve single-domain generalized object detection by using a frozen vision foundation model to maintain cross-domain stability, addr…