Search Results for author: Weijia Wu

Found 12 papers, 4 papers with code

BiViT: Extremely Compressed Binary Vision Transformer

no code implementations14 Nov 2022 Yefei He, Zhenyu Lou, Luoming Zhang, Weijia Wu, Bohan Zhuang, Hong Zhou

To solve this, we propose Softmax-aware Binarization, which dynamically adapts to the data distribution and reduces the error caused by binarization.

Binarization

Explore Faster Localization Learning For Scene Text Detection

no code implementations4 Jul 2022 Yuzhong Zhao, Yuanqiang Cai, Weijia Wu, Weiqiang Wang

Generally pre-training and long-time training computation are necessary for obtaining a good-performance text detector based on deep networks.

Scene Text Detection

Binarizing by Classification: Is soft function really necessary?

no code implementations16 May 2022 Yefei He, Luoming Zhang, Weijia Wu, Hong Zhou

Binary neural network leverages the $Sign$ function to binarize real values, and its non-derivative property inevitably brings huge gradient errors during backpropagation.

 Ranked #1 on Binarization on ImageNet (Top 1 Accuracy metric)

Binarization Classification +2

Data-Free Quantization with Accurate Activation Clipping and Adaptive Batch Normalization

no code implementations8 Apr 2022 Yefei He, Luoming Zhang, Weijia Wu, Hong Zhou

In this paper, we present a simple yet effective data-free quantization method with accurate activation clipping and adaptive batch normalization.

Data Free Quantization

End-to-End Video Text Spotting with Transformer

1 code implementation20 Mar 2022 Weijia Wu, Yuanqiang Cai, Chunhua Shen, Debing Zhang, Ying Fu, Hong Zhou, Ping Luo

Recent video text spotting methods usually require the three-staged pipeline, i. e., detecting text in individual images, recognizing localized text, tracking text streams with post-processing to generate final results.

Text Spotting

Contrastive Learning of Semantic and Visual Representations for Text Tracking

no code implementations30 Dec 2021 Zhuang Li, Weijia Wu, Mike Zheng Shou, Jiahong Li, Size Li, Zhongyuan Wang, Hong Zhou

Semantic representation is of great benefit to the video text tracking(VTT) task that requires simultaneously classifying, detecting, and tracking texts in the video.

Contrastive Learning

Polygon-free: Unconstrained Scene Text Detection with Box Annotations

1 code implementation26 Nov 2020 Weijia Wu, Enze Xie, Ruimao Zhang, Wenhai Wang, Hong Zhou, Ping Luo

For example, without using polygon annotations, PSENet achieves an 80. 5% F-score on TotalText [3] (vs. 80. 9% of fully supervised counterpart), 31. 1% better than training directly with upright bounding box annotations, and saves 80%+ labeling costs.

Scene Text Detection

Synthetic-to-Real Unsupervised Domain Adaptation for Scene Text Detection in the Wild

1 code implementation3 Sep 2020 Weijia Wu, Ning Lu, Enze Xie

To address the severe domain distribution mismatch, we propose a synthetic-to-real domain adaptation method for scene text detection, which transfers knowledge from synthetic data (source domain) to real data (target domain).

Adversarial Text Scene Text Detection +1

TextCohesion: Detecting Text for Arbitrary Shapes

no code implementations22 Apr 2019 Weijia Wu, Jici Xing, Hong Zhou

In this paper, we propose a pixel-wise method named TextCohesion for scene text detection, which splits a text instance into five key components: a Text Skeleton and four Directional Pixel Regions.

Curved Text Detection

Cannot find the paper you are looking for? You can Submit a new open access paper.