**ReLU6** is a modification of the [rectified linear unit](https://paperswithcode.com/method/relu) where we limit the activation to a maximum size of $6$. This is due to increased robustness when used with low-precision computation.

Image Credit: [PyTorch](https://pytorch.org/docs/master/generated/torch.nn.ReLU6.html)

**MultiGrain** is a type of image model that learns a single embedding for classes, instances and copies.  In other words, it is a convolutional neural network that is suitable for both image classification and instance retrieval. We learn MultiGrain by jointly training an image embedding for multiple tasks. The resulting representation is compact and can outperform narrowly-trained embeddings. The learned embedding output incorporates different levels of granularity.

MultiGrain

MultiGrain: a unified image embedding for classes and instances

ReLU6

MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications

**UFLoss**, or **Unsupervised Feature Loss**, is a patch-based unsupervised learned feature loss for deep learning (DL) based reconstructions. The UFLoss provides instance-level discrimination by mapping similar instances to similar low-dimensional feature vectors using a pre-trained mapping network (UFLoss Network). The rationale of using features from large-patches (typically 40×40 pixels for a 300×300 pixels image) is that we want the UFLoss to capture mid-level structural and semantic features instead of using small patches (typically around 10×10 pixels), which only contain local edge information. On the other hand, the authors avoid using global features due to the fact that the training set (typically around 5000 slices) is usually not large enough to capture common and general features at a large-image scale.

Source	MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
Year	2000
Data Source	Papers with Code archive (CC BY-SA)