Search Results for author: Zhong Zhou

Found 19 papers, 3 papers with code

Towards Generalized Few-Shot Open-Set Object Detection

2 code implementations28 Oct 2022 Binyi Su, Hua Zhang, Jingzhi Li, Zhong Zhou

In this paper, we seek a solution for the generalized few-shot open-set object detection (G-FOOD), which aims to avoid detecting unknown classes as known classes with a high confidence score while maintaining the performance of few-shot detection.

Few Shot Open Set Object Detection Object +2

BAF-Detector: An Efficient CNN-Based Detector for Photovoltaic Cell Defect Detection

1 code implementation19 Dec 2020 Binyi Su, Haiyong Chen, Zhong Zhou

Finally, the experimental results on a large-scale EL dataset including 3629 images, 2129 of which are defective, show that the proposed method achieves 98. 70% (F-measure), 88. 07% (mAP), and 73. 29% (IoU) in terms of multi-scale defects classification and detection results in raw PV cell EL images.

Defect Detection Region Proposal

Massively Parallel Cross-Lingual Learning in Low-Resource Target Language Translation

no code implementations WS 2018 Zhong Zhou, Matthias Sperber, Alex Waibel

The main challenges we identify are the lack of low-resource language data, effective methods for cross-lingual transfer, and the variable-binding problem that is common in neural systems.

Cross-Lingual Transfer Translation

A Network Structure to Explicitly Reduce Confusion Errors in Semantic Segmentation

no code implementations1 Aug 2018 Qichuan Geng, Xinyu Huang, Zhong Zhou, Ruigang Yang

Confusing classes that are ubiquitous in real world often degrade performance for many vision related applications like object detection, classification, and segmentation.

Image Segmentation object-detection +3

Part-level Car Parsing and Reconstruction from Single Street View

no code implementations27 Nov 2018 Qichuan Geng, Hong Zhang, Xinyu Huang, Sen Wang, Feixiang Lu, Xinjing Cheng, Zhong Zhou, Ruigang Yang

As it is labor-intensive to annotate semantic parts on real street views, we propose a specific approach to implicitly transfer part features from synthesized images to real street views.

Car Pose Estimation Domain Adaptation +1

Using Interlinear Glosses as Pivot in Low-Resource Multilingual Machine Translation

no code implementations7 Nov 2019 Zhong Zhou, Lori Levin, David R. Mortensen, Alex Waibel

Firstly, we pool IGT for 1, 497 languages in ODIN (54, 545 glosses) and 70, 918 glosses in Arapaho and train a gloss-to-target NMT system from IGT to English, with a BLEU score of 25. 94.

Machine Translation NMT +2

Gated Path Selection Network for Semantic Segmentation

no code implementations19 Jan 2020 Qichuan Geng, Hong Zhang, Xiaojuan Qi, Ruigang Yang, Zhong Zhou, Gao Huang

Semantic segmentation is a challenging task that needs to handle large scale variations, deformations and different viewpoints.

Segmentation Semantic Segmentation

Object-aware Feature Aggregation for Video Object Detection

no code implementations23 Oct 2020 Qichuan Geng, Hong Zhang, Na Jiang, Xiaojuan Qi, Liangjun Zhang, Zhong Zhou

As a consequence, augmenting features with such prior knowledge can effectively improve the classification and localization performance.

Object object-detection +2

SIGAN: A Novel Image Generation Method for Solar Cell Defect Segmentation and Augmentation

no code implementations11 Apr 2021 Binyi Su, Zhong Zhou, Haiyong Chen, Xiaochun Cao

Moreover, we release a new solar cell EL image dataset named as EL-2019, which includes three types of images: crack, finger interruption and defect-free.

Defect Detection Generative Adversarial Network +2

Family of Origin and Family of Choice: Massively Parallel Lexiconized Iterative Pretraining for Severely Low Resource Machine Translation

no code implementations12 Apr 2021 Zhong Zhou, Alex Waibel

In other words, given a text in 124 source languages, we translate it into a severely low resource language using only ~1, 000 lines of low resource data without any external help.

Machine Translation Translation

Active Learning for Massively Parallel Translation of Constrained Text into Low Resource Languages

no code implementations MTSummit 2021 Zhong Zhou, Alex Waibel

We compare the portion-based approach that optimizes coherence of the text locally with the random sampling approach that increases coverage of the text globally.

Active Learning Machine Translation +1

Family of Origin and Family of Choice: Massively Parallel Lexiconized Iterative Pretraining for Severely Low Resource Text-based Translation

no code implementations NAACL (SIGTYP) 2021 Zhong Zhou, Alexander Waibel

In other words, given a text in 124 source languages, we translate it into a severely low resource language using only ∼1, 000 lines of low resource data without any external help.

QR-CLIP: Introducing Explicit Open-World Knowledge for Location and Time Reasoning

no code implementations2 Feb 2023 Weimin Shi, Mingchen Zhuge, Dehong Gao, Zhong Zhou, Ming-Ming Cheng, Deng-Ping Fan

Daily images may convey abstract meanings that require us to memorize and infer profound information from them.

World Knowledge

Train Global, Tailor Local: Minimalist Multilingual Translation into Endangered Languages

no code implementations5 May 2023 Zhong Zhou, Jan Niehues, Alex Waibel

We examine two approaches: 1. best selection of seed sentences to jump start translations in a new language in view of best generalization to the remainder of a larger targeted text(s), and 2. we adapt large general multilingual translation engines from many other languages to focus on a specific text in a new, unknown language.

Humanitarian Translation

Massively Multilingual Text Translation For Low-Resource Languages

no code implementations29 Jan 2024 Zhong Zhou

Performance gain comes from massive source parallelism by careful choice of close-by language families, style-consistent corpus-level paraphrases within the same language and strategic adaptation of existing large pretrained multilingual models to the domain first and then to the language.

Humanitarian Machine Translation +1

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