Ziqiu Chi
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Ziqiu Chi has a total of 21 co-authors. Here are the top co-authors by number of shared publications:
- Zhe Wang
East China University of Science and Technology
11 shared publications - Wenli Du
East China University of Science and Technology
6 shared publications - Hai Yang
East China University of Science and Technology
4 shared publications - Dongdong Li
Department of Computer Science and Engineering, East China University of Science and Technology, Shanghai, China
3 shared publications - Xinlei Xu
Department of Computer Science and Engineering, Key Laboratory of Smart Manufacturing in Energy Chemical Process, Ministry of Education, East China University of Science and Technology, Shanghai, China
3 shared publications Mengping Yang
Ministry of Education, and the Department of Computer Science and Engineering, Key Laboratory of Smart Manufacturing in Energy Chemical Process, East China University of Science and Technology, Shanghai, China
2 shared publications
Latest Publications
- 19 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 36 (8) , 14975-14987
BFCP: Pursue Better Forward Compatibility Pretraining for Few-Shot Class-Incremental Learning
Few-shot class-incremental learning (FSCIL) requires learning new knowledge without forgetting old knowledge. Forward compatibility can reserve space for novel classes while maintaining base class knowledge in incremental learning. Better forward compatibility is crucial for effectively mastering all knowledge, especially when dealing with a few unknown new classes. In this article, we propose the better forward compatibility pretraining (BFCP) to further enhance forward compatibility in FSCIL. We adopt a two-stage training for the backbone network in the base session. First, we train the backbone network at the image-level to enhance its feature extraction capability, enabling the model to extract valuable information from unknown class images. Second, we fine-tune the backbone network at the feature-level with fake prototypes and instances to achieve clustering base classes and reserve space for unknown new classes. For all incremental new sessions, we freeze the backbone network and employ prototype rectification without further training to refine the prototypes of the novel classes. We conduct extensive experiments with different input scales, including federated cross-domain pretraining and cross-domain class-incremental experiments. BFCP efficiently handles both novel and base classes of each incremental session and significantly outperforms state-of-the-art methods, achieving an average accuracy of 63.47% on the CIFAR100 dataset.
- 19 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 36 (8) , 14975-14987
BFCP: Pursue Better Forward Compatibility Pretraining for Few-Shot Class-Incremental Learning
Few-shot class-incremental learning (FSCIL) requires learning new knowledge without forgetting old knowledge. Forward compatibility can reserve space for novel classes while maintaining base class knowledge in incremental learning. Better forward compatibility is crucial for effectively mastering all knowledge, especially when dealing with a few unknown new classes. In this article, we propose the better forward compatibility pretraining (BFCP) to further enhance forward compatibility in FSCIL. We adopt a two-stage training for the backbone network in the base session. First, we train the backbone network at the image-level to enhance its feature extraction capability, enabling the model to extract valuable information from unknown class images. Second, we fine-tune the backbone network at the feature-level with fake prototypes and instances to achieve clustering base classes and reserve space for unknown new classes. For all incremental new sessions, we freeze the backbone network and employ prototype rectification without further training to refine the prototypes of the novel classes. We conduct extensive experiments with different input scales, including federated cross-domain pretraining and cross-domain class-incremental experiments. BFCP efficiently handles both novel and base classes of each incremental session and significantly outperforms state-of-the-art methods, achieving an average accuracy of 63.47% on the CIFAR100 dataset.
- 25 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 36 (8) , 14843-14854
Transductive Parameter-Free Propagation Framework for Few-Shot Distribution Rectification
Few-shot learning (FSL) is challenging due to the scarce labeled novel-class data. Researchers have to train the embedding function with auxiliary base-class data to obtain the novel-class embeddings. However, the domain gap makes the novel-class embedding unsatisfactory, as the novel class and the base class are disjoint. Recent studies prove that embedding rectification shows great potential, introduces miscellaneous variants, and achieves similar performances. Nonetheless, while each method demonstrates unique strengths, they often address distinct challenges in isolation, limiting their applicability in more complex or diverse scenarios. In this article, we take a closer look at these methods and hypothesize that a general embedding rectification framework is more essential to the model’s performance. To verify our observation, we propose: 1) a distribution propagation (DisP) layer distinguishes the inter-class margin and increases intra-class aggregation, performing the task-level rectification; and 2) a prototype propagation (ProtoP) layer moves the prototype toward the ideal class center, applying the prototype-query level rectification. Our framework aims to maximize the actual data distribution. Although pseudo-labeling proves effective in achieving this goal, a significant challenge is ensuring the reliable retention of only high-confidence predictions. To overcome this, we introduce a distribution-based pseudo-labeling method pseudo-query upgrade (PseQUp) that provides more reliable pseudo-labeling samples without relying on confidence scores. We evaluate the proposed method in both transfer learning and meta-learning scenarios. Empirical experiments show the applicable and plug-and-play ability of the proposed methods.
- 25 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 36 (8) , 14843-14854
Transductive Parameter-Free Propagation Framework for Few-Shot Distribution Rectification
Few-shot learning (FSL) is challenging due to the scarce labeled novel-class data. Researchers have to train the embedding function with auxiliary base-class data to obtain the novel-class embeddings. However, the domain gap makes the novel-class embedding unsatisfactory, as the novel class and the base class are disjoint. Recent studies prove that embedding rectification shows great potential, introduces miscellaneous variants, and achieves similar performances. Nonetheless, while each method demonstrates unique strengths, they often address distinct challenges in isolation, limiting their applicability in more complex or diverse scenarios. In this article, we take a closer look at these methods and hypothesize that a general embedding rectification framework is more essential to the model’s performance. To verify our observation, we propose: 1) a distribution propagation (DisP) layer distinguishes the inter-class margin and increases intra-class aggregation, performing the task-level rectification; and 2) a prototype propagation (ProtoP) layer moves the prototype toward the ideal class center, applying the prototype-query level rectification. Our framework aims to maximize the actual data distribution. Although pseudo-labeling proves effective in achieving this goal, a significant challenge is ensuring the reliable retention of only high-confidence predictions. To overcome this, we introduce a distribution-based pseudo-labeling method pseudo-query upgrade (PseQUp) that provides more reliable pseudo-labeling samples without relying on confidence scores. We evaluate the proposed method in both transfer learning and meta-learning scenarios. Empirical experiments show the applicable and plug-and-play ability of the proposed methods.
- Open Access
- 26 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 5079-5088
Semantic-Aware Generator and Low-level Feature Augmentation for Few-shot Image Generation
Few-shot image generation aims to generate novel images for an unseen category with only a few samples. Prior studies fail to produce novel images with desirable diversity and fidelity. To ameliorate the generation quality, we in this paper propose a Semantic-Aware Generator (SAG) to provide explicit semantic guidance to the discriminator, and a Low-level Feature Augmentation (LFA) technique to provide fine-grained information, facilitating the diversity. Specifically, we observe that the generator feature layers contain different levels of semantic information. Such observation motivates us to employ intermediate feature maps of the generator as semantic labels to guide the discriminator, improving the semantic awareness of the generator. Moreover, spatially informative and diverse features obtained via LFA contribute to better generation quality. Together with the aforementioned module, we conduct extensive experiments on three representative benchmarks and the results demonstrate the effectiveness and advancement of our method.
- 26 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 5079-5088
Open AccessSemantic-Aware Generator and Low-level Feature Augmentation for Few-shot Image Generation
Few-shot image generation aims to generate novel images for an unseen category with only a few samples. Prior studies fail to produce novel images with desirable diversity and fidelity. To ameliorate the generation quality, we in this paper propose a Semantic-Aware Generator (SAG) to provide explicit semantic guidance to the discriminator, and a Low-level Feature Augmentation (LFA) technique to provide fine-grained information, facilitating the diversity. Specifically, we observe that the generator feature layers contain different levels of semantic information. Such observation motivates us to employ intermediate feature maps of the generator as semantic labels to guide the discriminator, improving the semantic awareness of the generator. Moreover, spatially informative and diverse features obtained via LFA contribute to better generation quality. Together with the aforementioned module, we conduct extensive experiments on three representative benchmarks and the results demonstrate the effectiveness and advancement of our method.
- 31 October 2022
- Published by Springer Nature
- p. 1-17
WaveGAN: Frequency-Aware GAN for High-Fidelity Few-Shot Image Generation
- 31 October 2022
- Published by Springer Nature
- p. 1-17
WaveGAN: Frequency-Aware GAN for High-Fidelity Few-Shot Image Generation
- 21 October 2022
- Published by Elsevier in Expert Systems with Applications
- Vol. 214
Complementary features based prototype self-updating for few-shot learning
- 21 October 2022
- Published by Elsevier in Expert Systems with Applications
- Vol. 214
Complementary features based prototype self-updating for few-shot learning
- 22 August 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 35 (7) , 7278-7290
Multiple Kernel Subspace Learning for Clustering and Classification
In the face of high-dimensional and complex data, effective subspace can preserve specific statistical properties and provide an appropriate representation of data, which generally facilitates the underlying tasks such as clustering or classification. Meanwhile, multiple kernel learning is a technique to combine multiple kernels from different feature spaces effectively. Thus, by incorporating multiple kernels into the process of subspace learning, different feature spaces can be projected into a unified subspace. This paper proposes the Multiple Kernel Subspace Learning (MKSL) for embedding the original space into a unified subspace. Multiple kernels of different feature spaces are combined by MKSL in the process of learning, which can extend the suitability for various applications. Moreover, to generate the optimal combination kernel of subspace learning, we propose a two-step iteration strategy to learn the appropriate kernel weights and transformation matrix of projecting simultaneously. Furthermore, our proposed formulation of MKSL can introduce different prior knowledge such as class information and neighborhood relationships. Thus it is competent to the unsupervised learning, semi-supervised learning, and supervised learning. Extensive experiments are conducted on diverse datasets, and the performances are comprehensively evaluated on different tasks. The experimental results indicate that the proposed algorithm is outstanding in unsupervised clustering task and effective in supervised and semi-supervised classification tasks.
- 22 August 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 35 (7) , 7278-7290
Multiple Kernel Subspace Learning for Clustering and Classification
In the face of high-dimensional and complex data, effective subspace can preserve specific statistical properties and provide an appropriate representation of data, which generally facilitates the underlying tasks such as clustering or classification. Meanwhile, multiple kernel learning is a technique to combine multiple kernels from different feature spaces effectively. Thus, by incorporating multiple kernels into the process of subspace learning, different feature spaces can be projected into a unified subspace. This paper proposes the Multiple Kernel Subspace Learning (MKSL) for embedding the original space into a unified subspace. Multiple kernels of different feature spaces are combined by MKSL in the process of learning, which can extend the suitability for various applications. Moreover, to generate the optimal combination kernel of subspace learning, we propose a two-step iteration strategy to learn the appropriate kernel weights and transformation matrix of projecting simultaneously. Furthermore, our proposed formulation of MKSL can introduce different prior knowledge such as class information and neighborhood relationships. Thus it is competent to the unsupervised learning, semi-supervised learning, and supervised learning. Extensive experiments are conducted on diverse datasets, and the performances are comprehensively evaluated on different tasks. The experimental results indicate that the proposed algorithm is outstanding in unsupervised clustering task and effective in supervised and semi-supervised classification tasks.
- 14 April 2022
- Published by Elsevier in Expert Systems with Applications
- Vol. 202
Multi-attention mutual information distributed framework for few-shot learning
- 14 April 2022
- Published by Elsevier in Expert Systems with Applications
- Vol. 202
Multi-attention mutual information distributed framework for few-shot learning
- 14 January 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Intelligent Systems
- Vol. 37 (2) , 44-54
Heterogeneous Federated Meta-Learning With Mutually Constrained Propagation
Federated learning is a popular framework that guarantees privacy security. Thereinto, heterogeneity is a challenging barrier. We propose a meta-based federated method with mutually constrained propagation (2MFed) method to cope with this. First, 2MFed gives each client the right to choose the most appropriate model from server-side parallel models as its local model, which tolerates hardware heterogeneity. Second, the server mutually exchanges the information of parallel models under the consistency and disparity constraints to improve robustness, thus eliminating data heterogeneity. Third, we use the power of the meta-based label propagation algorithm to treat the federated training as the federated few-shot problem, which removes the model heterogeneity. Finally, extensive experiments confirm the effectiveness of the proposed method. In addition, we evaluate the proposed method on few-shot tasks and demonstrate its excellent performance further.
- 14 January 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Intelligent Systems
- Vol. 37 (2) , 44-54
Heterogeneous Federated Meta-Learning With Mutually Constrained Propagation
Federated learning is a popular framework that guarantees privacy security. Thereinto, heterogeneity is a challenging barrier. We propose a meta-based federated method with mutually constrained propagation (2MFed) method to cope with this. First, 2MFed gives each client the right to choose the most appropriate model from server-side parallel models as its local model, which tolerates hardware heterogeneity. Second, the server mutually exchanges the information of parallel models under the consistency and disparity constraints to improve robustness, thus eliminating data heterogeneity. Third, we use the power of the meta-based label propagation algorithm to treat the federated training as the federated few-shot problem, which removes the model heterogeneity. Finally, extensive experiments confirm the effectiveness of the proposed method. In addition, we evaluate the proposed method on few-shot tasks and demonstrate its excellent performance further.
- 2 November 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 32 (7) , 4163-4173
Learning to Capture the Query Distribution for Few-Shot Learning
In the Few-Shot Learning (FSL), much of the related efforts only rely on the few available labeled samples (support set) building approach. However, the challenge is that the support set is easy-to-be-biased, so that they cannot be competent prototypes and are hard to represent the class distribution, leading to performance bottlenecks. In this paper, we propose to solve this obstacle by capturing the distribution of the unlabeled samples (query set). We propose two sampling methods: DeepSearch ( $\cal DS$ ) and WideSearch ( $\cal WS$ ). Both approaches are simple to implement and have no trainable parameters. They search the query samples near to the support set in different manners. Afterward, the statistic information is calculated, and we generate the latent samples according to it. The generated latent set is promising. First, it brings the query set distribution information to the classifier, which significantly improves the performance of the cross-entropy-based classifier. Second, it helps the support set become the better prototypes, which boosts the performance of the prototype-based classifier. Third, we find few latent samples are enough to boost the performance. Abundant experiments prove the proposed method achieves state-of-the-art performance on the few-shot tasks. Finally, rich ablation studies explain the compelling details of our approach.
- 2 November 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 32 (7) , 4163-4173
Learning to Capture the Query Distribution for Few-Shot Learning
In the Few-Shot Learning (FSL), much of the related efforts only rely on the few available labeled samples (support set) building approach. However, the challenge is that the support set is easy-to-be-biased, so that they cannot be competent prototypes and are hard to represent the class distribution, leading to performance bottlenecks. In this paper, we propose to solve this obstacle by capturing the distribution of the unlabeled samples (query set). We propose two sampling methods: DeepSearch ( $\cal DS$ ) and WideSearch ( $\cal WS$ ). Both approaches are simple to implement and have no trainable parameters. They search the query samples near to the support set in different manners. Afterward, the statistic information is calculated, and we generate the latent samples according to it. The generated latent set is promising. First, it brings the query set distribution information to the classifier, which significantly improves the performance of the cross-entropy-based classifier. Second, it helps the support set become the better prototypes, which boosts the performance of the prototype-based classifier. Third, we find few latent samples are enough to boost the performance. Abundant experiments prove the proposed method achieves state-of-the-art performance on the few-shot tasks. Finally, rich ablation studies explain the compelling details of our approach.
- 21 April 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 33 (10) , 5888-5897
Explicit Metric-Based Multiconcept Multi-Instance Learning With Triplet and Superbag
Multi-instance learning (MIL) has garnered considerable attention in recent years due to its favorable performance in various scenarios. Nonetheless, most previous studies have implicitly expressed the correlation between instances and bags. Moreover, the importance of negative instances has been largely overlooked. Hence, we seek to present an explicit and intuitively understandable method that can compensate for these deficiencies. In this article, we creatively introduce a metric-based multiconcept MIL approach based on two aspects. First, the triplet-based bag embedding method identifies instance categories and builds attention weights for every instance explicitly. Accordingly, bag embedding is accomplished under the limitation of weak supervision. Second, the developed instance correlation metric approach in the superbag considers the multiconcept issue to boost the model generalization performance. We have designed a rich variety of experiments to demonstrate the performance of our algorithm. The artificial data experiment reveals the interpretability of the proposed network. The results of the comparison experiment confirm that our method shows favorable performance in multiple tasks. Finally, we illustrate the motivation of the presented method by the ablation experiments.
- 21 April 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 33 (10) , 5888-5897
Explicit Metric-Based Multiconcept Multi-Instance Learning With Triplet and Superbag
Multi-instance learning (MIL) has garnered considerable attention in recent years due to its favorable performance in various scenarios. Nonetheless, most previous studies have implicitly expressed the correlation between instances and bags. Moreover, the importance of negative instances has been largely overlooked. Hence, we seek to present an explicit and intuitively understandable method that can compensate for these deficiencies. In this article, we creatively introduce a metric-based multiconcept MIL approach based on two aspects. First, the triplet-based bag embedding method identifies instance categories and builds attention weights for every instance explicitly. Accordingly, bag embedding is accomplished under the limitation of weak supervision. Second, the developed instance correlation metric approach in the superbag considers the multiconcept issue to boost the model generalization performance. We have designed a rich variety of experiments to demonstrate the performance of our algorithm. The artificial data experiment reveals the interpretability of the proposed network. The results of the comparison experiment confirm that our method shows favorable performance in multiple tasks. Finally, we illustrate the motivation of the presented method by the ablation experiments.