E2ETag: An End-to-End Trainable Method for Generating and Detecting Fiducial Markers

1 code implementation • 29 May 2021 • J. Brennan Peace, Eric Psota, Yanfeng Liu, Lance C. Pérez

Existing fiducial markers solutions are designed for efficient detection and decoding, however, their ability to stand out in natural environments is difficult to infer from relatively limited analysis.

Exploiting Invariance in Training Deep Neural Networks

1 code implementation • 30 Mar 2021 • Chengxi Ye, Xiong Zhou, Tristan McKinney, Yanfeng Liu, Qinggang Zhou, Fedor Zhdanov

Inspired by two basic mechanisms in animal visual systems, we introduce a feature transform technique that imposes invariance properties in the training of deep neural networks.

Image Classification Object Detection +1

Layered Embeddings for Amodal Instance Segmentation

1 code implementation • 14 Feb 2020 • Yanfeng Liu, Eric Psota, Lance Pérez

The proposed method extends upon the representational output of semantic instance segmentation by explicitly including both visible and occluded parts.

Amodal Instance Segmentation Semantic Segmentation