**Inception-ResNet-v2** is a convolutional neural architecture that builds on the Inception family of architectures but incorporates [residual connections](https://paperswithcode.com/method/residual-connection) (replacing the filter concatenation stage of the Inception architecture).

**Feature Non-Maximum Suppression**, or **FeatureNMS**, is a post-processing step for object detection models that removes duplicates where there are multiple detections outputted per object. FeatureNMS recognizes duplicates not only based on the intersection over union between the bounding boxes, but also based on the difference of feature vectors. These feature vectors can encode more information like visual appearance.

FeatureNMS

FeatureNMS: Non-Maximum Suppression by Learning Feature Embeddings

Inception-ResNet-v2

Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning

**Kaleido-BERT**(CVPR2021) is the pioneering work that focus on solving PTM in e-commerce field. It achieves SOTA performances compared with many models published in general domain.

Source	Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning
Year	2000
Data Source	CC BY-SA - https://paperswithcode.com