**Generalized Focal Loss (GFL)** is a loss function for object detection that combines Quality [Focal Loss](https://paperswithcode.com/method/focal-loss) and Distribution Focal Loss into a general form.

**ConvBERT** is a modification on the [BERT](https://paperswithcode.com/method/bert) architecture which uses a [span-based dynamic convolution](https://paperswithcode.com/method/span-based-dynamic-convolution) to replace self-attention heads to directly model local dependencies. Specifically a new [mixed attention module](https://paperswithcode.com/method/mixed-attention-block) replaces the [self-attention modules](https://paperswithcode.com/method/scaled) in BERT, which leverages the advantages of [convolution](https://paperswithcode.com/method/convolution) to better capture local dependency. Additionally, a new span-based dynamic convolution operation is used to utilize multiple input tokens to dynamically generate the convolution kernel. Lastly, ConvBERT also incorporates some new model designs including the bottleneck attention and grouped linear operator for the feed-forward module (reducing the number of parameters).

ConvBERT

ConvBERT: Improving BERT with Span-based Dynamic Convolution

Generalized Focal Loss

Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detection

**Visual-Spatial-Graph Network** (VSGNet) is a network for human-object interaction detection. It extracts visual features from the image representing the human-object pair, refines the features with spatial configurations of the pair, and utilizes the structural connections between the pair via graph convolutions.

Source	Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detection
Year	2000
Data Source	CC BY-SA - https://paperswithcode.com