Piotr Dollár

Focal Loss for Dense Object Detection

The highest accuracy object detectors to date are based on a two-stage approach popularized by R-CNN, where a classifier is applied to a sparse set of candidate object locations...

Segment Anything

We introduce the Segment Anything (SA) project: a new task, model, and dataset for image segmentation. Using our efficient model in a data collection loop, we built the largest ...

Microsoft COCO: Common Objects in Context

Quickly Boosting Decision Trees - Pruning Underachieving Features Early

Boosted decision trees are one of the most popular and successful learning techniques used today. While exhibiting fast speeds at test time, relatively slow training makes them ...

Panoptic Feature Pyramid Networks

The recently introduced panoptic segmentation task has renewed our community's interest in unifying the tasks of instance segmentation (for thing classes) and semantic segmentat...

Behavior Recognition via Sparse Spatio-Temporal Features

A common trend in object recognition is to detect and leverage the use of sparse, informative feature points. The use of such features makes the problem more manageable while pr...