Segment Anything
PulseAugur coverage of Segment Anything — every cluster mentioning Segment Anything across labs, papers, and developer communities, ranked by signal.
-
PanoSAMic model enhances panoramic image segmentation using SAM features
Researchers have developed PanoSAMic, a novel approach for segmenting panoramic images by leveraging the pre-trained Segment Anything (SAM) model. This method adapts SAM's encoder to output multi-stage features and inco…
-
H-Sets framework uncovers feature interactions in image classifiers
Researchers have developed H-Sets, a new framework designed to uncover and attribute higher-order feature interactions within image classifiers. This method moves beyond analyzing individual features to understand how g…
-
SAM 3：AI之眼 — Nikhila & Pengchuan (Meta Superintelligence)，特邀 Joseph Nelson (Roboflow)
Meta AI 发布了 SAM 3，这是其 Segment Anything 项目的一项重大进展，能够使用自然语言提示在图像和视频中进行概念分割、检测和跟踪。该新模型通过实时识别诸如“黄色校车”等概念的每一个实例，并以惊人的速度，实现了人类水平的详尽性。SAM 3 与 Gemini 等多模态大语言模型集成，可执行复杂的视觉推理任务，并通过在 Roboflow 平台上的应用，已节省了超过 130 年的标注时间。