https://github.com/Oguzhanercan/Vision-Transformers
Training data-efficient image transformers & distillation through attention
Papers with Code 아카이브
Document Layout Analysis
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 1
- 평가표
- 6
- 보존된 평가 기록
- 30
"Document Layout Analysis is performed to determine physical structure of a document, that is, to determine document components. These document components can consist of single connected components-regions [...] of pixels that are adjacent to form single regions [...] , or group of text lines. A text line is a group of characters, symbols, and words that are adjacent, “relatively close” to each other and through which a straight line can be drawn (usually with horizontal or vertical orientation)." L. O'Gorman, "The document spectrum for page layout analysis," in IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 15, no. 11, pp. 1162-1173, Nov. 1993.
Image credit: PubLayNet: largest dataset ever for document layout analysis
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/PaddlePaddle/PLSC/tree/master/task/classification/deit
Training data-efficient image transformers & distillation through attention
https://github.com/PaddlePaddle/PaddleClas
Training data-efficient image transformers & distillation through attention
https://github.com/PaddlePaddle/PaddleNLP/tree/develop/paddlenlp/transformers/layoutlm
LayoutLM: Pre-training of Text and Layout for Document Image Understanding
https://github.com/PaddlePaddle/PaddleNLP/tree/develop/paddlenlp/transformers/layoutlmv2
LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document Understanding
https://github.com/PaddlePaddle/PaddleOCR
LayoutLM: Pre-training of Text and Layout for Document Image Understanding
https://github.com/SaipingZhang/DVC_P
https://github.com/TACJu/TransFG
Training data-efficient image transformers & distillation through attention
https://github.com/UdbhavPrasad072300/Transformer-Implementations
Training data-efficient image transformers & distillation through attention
https://github.com/affjljoo3581/deit3-jax
Training data-efficient image transformers & distillation through attention
https://github.com/ahmedelmahy/myownvit
Training data-efficient image transformers & distillation through attention
https://github.com/aiot-mlsys-lab/famba-v
Training data-efficient image transformers & distillation through attention
https://github.com/alessiomora/unlearning_fl
Training data-efficient image transformers & distillation through attention
https://github.com/alibaba/EasyCV
Training data-efficient image transformers & distillation through attention
https://github.com/aprilbian/h-DJSCC
https://github.com/asrafulashiq/deit-custom
Training data-efficient image transformers & distillation through attention
https://github.com/beiluo97/hflic
https://github.com/binzzheng/DVC-PyTorch
https://github.com/bshantam97/Attention_Based_Networks
Training data-efficient image transformers & distillation through attention
https://github.com/bunny98/Text-to-Image-Using-GAN
TAC-GAN - Text Conditioned Auxiliary Classifier Generative Adversarial Network
https://github.com/chend-vl/instructocr
Towards End-to-End Unified Scene Text Detection and Layout Analysis
https://github.com/clementchadebec/benchmark_VAE
Learning to Generate Images with Perceptual Similarity Metrics
https://github.com/code-implementation1/Code1/tree/main/DeiT
Training data-efficient image transformers & distillation through attention
https://github.com/cogtoolslab/physics-benchmarking-neurips2021
Training data-efficient image transformers & distillation through attention
https://github.com/cvlab-stonybrook/DewarpNet
https://github.com/cydal/LayoutML_pytorch
LayoutLM: Pre-training of Text and Layout for Document Image Understanding
https://github.com/dashayushman/TAC-GAN
TAC-GAN - Text Conditioned Auxiliary Classifier Generative Adversarial Network
https://github.com/dhlab-epfl/dhSegment-torch
dhSegment: A generic deep-learning approach for document segmentation
https://github.com/digital-history-bonn/chronicling-germany-code
dhSegment: A generic deep-learning approach for document segmentation
https://github.com/docling-project/docling
DocLayNet: A Large Human-Annotated Dataset for Document-Layout Analysis
https://github.com/ds4sd/quackling
DocLayNet: A Large Human-Annotated Dataset for Document-Layout Analysis
https://github.com/facebookresearch/NeuralCompression/tree/main/projects/illm
Improving Statistical Fidelity for Neural Image Compression with Implicit Local Likelihood Models
https://github.com/facebookresearch/data2vec_vision
LayoutLM: Pre-training of Text and Layout for Document Image Understanding
https://github.com/facebookresearch/neuralcompression
https://github.com/facebookresearch/vissl
https://github.com/faymek/compression
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.