LYLingfeng Yang

Lingfeng Yang

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Lingfeng Yang has a total of 16 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Shadow-DETR: Alleviating matching conflicts through shadow queries

    by Yunfei Ma, Jie Li, Lingfeng Yang, Yifei Su, Yingpeng Li, Wankou Yang


  • Open Access

    A survey of historical learning: learning models with learning history

    by Xiang Li, Ge Wu, Lingfeng Yang, Wenhai Wang, Renjie Song, Ming-Ming Cheng, Jian Yang

    New knowledge originates from the old. The various types of elements, deposited in the training history, are a large amount of wealth for improving learning deep models. In this survey, we comprehensively review and summarize the topic–“Historical Learning: Learning Models with Learning History”, which learns better neural models with the help of their learning history during its optimization, from three detailed aspects: Historical Type (what), Utility Part (where) and Storage Form (how). To our best knowledge, it is the first survey that systematically studies the methodologies which make use of various historical statistics when training deep neural networks. The discussions with related topics like recurrent/memory networks, ensemble learning, and reinforcement learning are demonstrated. We also expose future challenges of this topic and encourage the community to pay attention to the think of historical learning principles when designing algorithms. The paper list related to historical learning is available at https://github.com/Martinser/Awesome-Historical-Learning.


  • Open Access

    Revisiting Prompt Pretraining of Vision-Language Models

    by Zhenyuan Chen, Lingfeng Yang, Shuo Chen, Zhaowei Chen, Jiajun Liang, Xiang Li

    Prompt learning is an effective method to customize Vision-Language Models (VLMs) for various downstream tasks, involving tuning very few parameters of input prompt tokens. Recently, prompt pretraining in large-scale dataset (e.g., ImageNet-21K) has played a crucial role in prompt learning for universal visual discrimination. However, we revisit and observe that the limited learnable prompts could face underfitting risks given the extensive images during prompt pretraining, simultaneously leading to poor generalization. To address the above issues, in this paper, we propose a general framework termed Revisiting Prompt Pretraining (RPP), which targets at improving the fitting and generalization ability from two aspects: prompt structure and prompt supervision. For prompt structure, we break the restriction in common practice where query, key, and value vectors are derived from the shared learnable prompt token. Instead, we introduce unshared individual query, key, and value learnable prompts, thereby enhancing the model's fitting capacity through increased parameter diversity. For prompt supervision, we additionally utilize soft labels derived from zero-shot probability predictions provided by a pretrained Contrastive Language Image Pretraining (CLIP) teacher model. These soft labels yield more nuanced and general insights into the inter-class relationships, thereby endowing the pretraining process with better generalization ability. RPP produces a more resilient prompt initialization, enhancing its robust transferability across diverse visual recognition tasks. Experiments across various benchmarks consistently confirm the state-of-the-art (SOTA) performance of our pretrained prompts. Codes and models will be made available soon.

  • Open Access

    APF-GAN: Exploring asymmetric pre-training and fine-tuning strategy for conditional generative adversarial network

    by Yuxuan Li, Lingfeng Yang, Xiang Li

    The use of generative adversarial network (GAN)based models for the conditional generation of image semantic segmentation has shown promising results in recent years. However, there are still some limitations, including limited diversity of image style, distortion of detailed texture, unbalanced color tone, and lengthy training time. To address these issues, we propose an asymmetric pre-training and fine-tuning (APF)-GAN model. In the pretraining phase, we introduce a progressive growing mechanism for pix2pix conditional GAN frameworks to efficiently generate high-quality images with details. Subsequently, in the fine-tuning phase, we introduce novel semantic spatially-guided noise to improve the robustness of the model and increase style diversity. The proposed algorithm outperformed the high-performance GauGAN model and won the championship of the Second Jittor Artificial Intelligence Challenge. Our model was implemented in the Jittor framework and is available at https:// github.com/zcablii/jittor-Torile-PG_SPADE. 1 APF-GAN 1.1 Asymmetric pre-training and fine-tuning strategy In this study, we propose an asymmetric pretraining and fine-tuning strategy for the conditional generative adversarial network (APF-GAN) model


  • Open Access

    A Survey of Historical Learning: Learning Models with Learning History

    by Xiang Li, Ge Wu, Lingfeng Yang, Wenhai Wang, Renjie Song, Jian Yang

    New knowledge originates from the old. The various types of elements, deposited in the training history, are a large amount of wealth for improving learning deep models. In this survey, we comprehensively review and summarize the topic--``Historical Learning: Learning Models with Learning History'', which learns better neural models with the help of their learning history during its optimization, from three detailed aspects: Historical Type (what), Functional Part (where) and Storage Form (how). To our best knowledge, it is the first survey that systematically studies the methodologies which make use of various historical statistics when training deep neural networks. The discussions with related topics like recurrent/memory networks, ensemble learning, and reinforcement learning are demonstrated. We also expose future challenges of this topic and encourage the community to pay attention to the think of historical learning principles when designing algorithms. The paper list related to historical learning is available at \url{https://github.com/Martinser/Awesome-Historical-Learning.}