Learning-Deep-Learning

Pixels to Graphs by Associative Embedding

January 2020

tl;dr: Generate relationship graphs based on associative embedding.

Overall impression

This paper is based on and is almost concurrent with associative embedding.

The heatmap for objects already has some preliminary structure for and may have inspired CenterNet.

The paper proposed a technique for supervising an unordered set of network outputs.

Note the difference between feature vector and embeddings. In this paper, the feature vectors are those generated by Stacked Hourglass backbone, and embeddings are generated with fc layers, a 8-dim vector to represent IDs.

The biggest difference between AE paper and pixel-to-graph

This paper is full of tricks to train neural networks!

Key ideas

Technical details

Notes