arxiv: https://arxiv.org/abs/1710.10903 key points introduce “graph attention network(GAT)” which consists of “graph attention layers” which incorporate the “self-attention” idea from transformers to graph neural network the graph attention layers work by calculating weights of a node’s neighbors from the features of the neighbors by taking other neighbor’s existence into account. Read more…
arxiv: https://arxiv.org/abs/2111.15664 Key Points visual document understanding model which does OCR + downstream task in one step with a single end-to-end model outputs are generative, and formatted to be convertible to JSON, which makes this architecture highly compatible to various downstream tasks. present SynthDoG, a synthetic document image generator used in Read more…
arxiv: https://arxiv.org/abs/1910.13461 key points propose autoregressive model named BART, which is architecturally similar to standard transformer encoder + decoder Check out 5 pretraining tasks, and experiment which pretraining task is most helpful test BART performance with large scale pretraining on downstream tasks Model Architecture This work introduces BART, which is fundamentally Read more…
arxiv: https://arxiv.org/abs/2106.11539 this work proposes a backbone for visual document understanding domain. It uses text, visual, spatial features. Key points use text, visual, spatial features at each encoding layer, keep feeding in visual and spatial features on the input side. This has the ‘residual’ connection effect. text and visual features Read more…
arxiv: https://arxiv.org/abs/2012.14740 LayoutLMv2 is a work improved from LayoutLM. This line of work focues on creating a model for document understanding. The main task of this genre is to extract useful information when a document is given. In this case, it tries to extract information when a document image is Read more…
arxiv: https://arxiv.org/abs/2008.13367 key points another anchor-free point based object detection network introduce new loss, varifocal loss which is a forked version from focal loss. Makes some changes from focal loss to compensate positive/negative imbalance futher. instead of prediction classification and IOU score separately, this work predicts a single scalar which Read more…
key point compared to resnet, the residual blocks are upgraded to have multiple “paths” or as the paper puts it “cardinality” which can be treated as another model architecture design hyper parameter. resnext architectures that have sufficient cardinality shows improved performance tldr: use improved residual blocks compared to resnet Different Read more…
arxiv: https://arxiv.org/abs/1803.01534
this paper propose a network structure(“PANet”) with bottom up path augmentation and a few other tweak methods which results in better instance segmentation performance.
(more…)arxiv: https://arxiv.org/abs/2003.12294
this approach will try to take global context into account by adopting transformer, and also use similar structure to reason semantic content.
(more…)arxiv link: https://arxiv.org/abs/1902.09630 key points using l1/l2 norm losses may not always align with the objective of improving IOU IOU is a good metric but they cannot be directly used as loss because it cannot backpropagate when there is no overlap at all GIOU is a modified IOU formula that Read more…