Xiang An
Xiang An has a total of 31 co-authors. Here are the top co-authors by number of shared publications:
- Jiankang Deng
Imperial College London
3 shared publications - Ziyong Feng
DeepGlint, Beijing, China
3 shared publications - Kaicheng Yang
DeepGlint, Beijing, China
2 shared publications Weimo Deng
2 shared publicationsYongle Zhao
2 shared publications- Bin Qin
DeepGlint
1 shared publication
Latest Publications
- Open Access
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 3487-3496
RealSyn : An Effective and Scalable Multimodal Interleaved Document Transformation Paradigm
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 3487-3496
Open AccessRealSyn : An Effective and Scalable Multimodal Interleaved Document Transformation Paradigm
- Open Access
Region-based Cluster Discrimination for Visual Representation Learning
Learning visual representations is foundational for a broad spectrum of downstream tasks. Although recent vision-language contrastive models, such as CLIP and SigLIP, have achieved impressive zero-shot performance via large-scale vision-language alignment, their reliance on global representations constrains their effectiveness for dense prediction tasks, such as grounding, OCR, and segmentation. To address this gap, we introduce Region-Aware Cluster Discrimination (RICE), a novel method that enhances region-level visual and OCR capabilities. We first construct a billion-scale candidate region dataset and propose a Region Transformer layer to extract rich regional semantics. We further design a unified region cluster discrimination loss that jointly supports object and OCR learning within a single classification framework, enabling efficient and scalable distributed training on large-scale data. Extensive experiments show that RICE consistently outperforms previous methods on tasks, including segmentation, dense detection, and visual perception for Multimodal Large Language Models (MLLMs). The pre-trained models have been released at https://github.com/deepglint/MVT.
Open AccessRegion-based Cluster Discrimination for Visual Representation Learning
Learning visual representations is foundational for a broad spectrum of downstream tasks. Although recent vision-language contrastive models, such as CLIP and SigLIP, have achieved impressive zero-shot performance via large-scale vision-language alignment, their reliance on global representations constrains their effectiveness for dense prediction tasks, such as grounding, OCR, and segmentation. To address this gap, we introduce Region-Aware Cluster Discrimination (RICE), a novel method that enhances region-level visual and OCR capabilities. We first construct a billion-scale candidate region dataset and propose a Region Transformer layer to extract rich regional semantics. We further design a unified region cluster discrimination loss that jointly supports object and OCR learning within a single classification framework, enabling efficient and scalable distributed training on large-scale data. Extensive experiments show that RICE consistently outperforms previous methods on tasks, including segmentation, dense detection, and visual perception for Multimodal Large Language Models (MLLMs). The pre-trained models have been released at https://github.com/deepglint/MVT.
- 31 December 2024
- Published by Springer Nature
- p. 17-30
Grounding Deliberate Reasoning in Multimodal Large Language Models
- 31 December 2024
- Published by Springer Nature
- p. 17-30
Grounding Deliberate Reasoning in Multimodal Large Language Models
- 3 November 2024
- Published by Springer Nature
- p. 428-444
Multi-label Cluster Discrimination for Visual Representation Learning
- 3 November 2024
- Published by Springer Nature
- p. 428-444
Multi-label Cluster Discrimination for Visual Representation Learning
- Open Access
Partial FC: Training 10 Million Identities on a Single Machine
Face recognition has been an active and vital topic among computer vision community for a long time. Previous researches mainly focus on loss functions used for facial feature extraction network, among which the improvements of softmax-based loss functions greatly promote the performance of face recognition. However, the contradiction between the drastically increasing number of face identities and the shortage of GPU memories is gradually becoming irreconcilable. In this paper, we thoroughly analyze the optimization goal of softmax-based loss functions and the difficulty of training massive identities. We find that the importance of negative classes in softmax function in face representation learning is not as high as we previously thought. The experiment demonstrates no loss of accuracy when training with only 10\% randomly sampled classes for the softmax-based loss functions, compared with training with full classes using state-of-the-art models on mainstream benchmarks. We also implement a very efficient distributed sampling algorithm, taking into account model accuracy and training efficiency, which uses only eight NVIDIA RTX2080Ti to complete classification tasks with tens of millions of identities. The code of this paper has been made available https://github.com/deepinsight/insightface/tree/master/recognition/partial_fc.
Open AccessPartial FC: Training 10 Million Identities on a Single Machine
Face recognition has been an active and vital topic among computer vision community for a long time. Previous researches mainly focus on loss functions used for facial feature extraction network, among which the improvements of softmax-based loss functions greatly promote the performance of face recognition. However, the contradiction between the drastically increasing number of face identities and the shortage of GPU memories is gradually becoming irreconcilable. In this paper, we thoroughly analyze the optimization goal of softmax-based loss functions and the difficulty of training massive identities. We find that the importance of negative classes in softmax function in face representation learning is not as high as we previously thought. The experiment demonstrates no loss of accuracy when training with only 10\% randomly sampled classes for the softmax-based loss functions, compared with training with full classes using state-of-the-art models on mainstream benchmarks. We also implement a very efficient distributed sampling algorithm, taking into account model accuracy and training efficiency, which uses only eight NVIDIA RTX2080Ti to complete classification tasks with tens of millions of identities. The code of this paper has been made available https://github.com/deepinsight/insightface/tree/master/recognition/partial_fc.