Piotr Dollár

Research topics

• Advanced Neural Network Applications · 6 papers
• Domain Adaptation and Few-Shot Learning · 4 papers
• Advanced Image and Video Retrieval Techniques · 2 papers
• Video Surveillance and Tracking Methods · 2 papers
• Adversarial Robustness in Machine Learning · 2 papers
• Human Pose and Action Recognition · 1 paper

Frequent co-authors

• Ross Girshick · 6 papers
• Kaiming He · 5 papers
• Tsung-Yi Lin · 3 papers
• Priya Goyal · 2 papers
• Bharath Hariharan · 1 paper
• Serge Belongie · 1 paper
• Georgia Gkioxari · 1 paper
• Saining Xie · 1 paper

Papers

1. Feature Pyramid Networks for Object Detection2017 · 30,041 citations

   Feature pyramids are a basic component in recognition systems for detecting objects at different scales. But pyramid representations have been avoided in recent object detectors that are based on deep convolutional networks, partially because they are slow to compute and…

2. Mask R-CNN2017 · 29,845 citations

   We present a conceptually simple, flexible, and general framework for object instance segmentation. Our approach efficiently detects objects in an image while simultaneously generating a high-quality segmentation mask for each instance. The method, called Mask R-CNN, extends Faster R-CNN by…

3. Focal Loss for Dense Object Detection2017 · 27,631 citations

   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. In contrast, one-stage detectors that are applied over a regular, dense…

4. Aggregated Residual Transformations for Deep Neural Networks2017 · 12,052 citations

   We present a simple, highly modularized network architecture for image classification. Our network is constructed by repeating a building block that aggregates a set of transformations with the same topology. Our simple design results in a homogeneous, multi-branch architecture that…

5. Segment Anything2023 · 10,762 citations

   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 segmentation dataset to date (by far), with over 1 billion masks…

6. Focal Loss for Dense Object DetectionIEEE Transactions on Pattern Analysis and Machine Intelligence · 2018 · 9,900 citations

   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. In contrast, one-stage detectors that are applied over a regular, dense…