Qinghang Su
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Qinghang Su has a total of 16 co-authors. Here are the top co-authors by number of shared publications:
- Dayan Wu
Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China
5 shared publications - Weiping Wang
Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China
4 shared publications Bo Li
Institute of Information Engineering, Chinese Academy of Sciences, Beijing, 100084, China; School of Cyber Security, University of Chinese Academy of Sciences, Beijing, 100049, China; Key Laboratory of Cyberspace Security Defense, Beijing, 100084, China
3 shared publications- Bo Li
Institute of Information Engineering Chinese Academy of Sciences Beijing China
3 shared publications - Chenming Wu
Baidu, Beijing, China
2 shared publications Dayan Wu
Institute of Information Engineering,Chinese Academy of Sciences
2 shared publications
Latest Publications
- Open Access
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 4562-4570
Mitigating the Evolving Semantic Entanglement in Continual Learning of Vision-Language Models
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 4562-4570
Open AccessMitigating the Evolving Semantic Entanglement in Continual Learning of Vision-Language Models
- 22 September 2025
- Published by Elsevier in Neural Networks
- Vol. 194, 108123
Planning forward: Deep incremental hashing by gradually defrosting bits
- 22 September 2025
- Published by Elsevier in Neural Networks
- Vol. 194, 108123
Planning forward: Deep incremental hashing by gradually defrosting bits
- Open Access
- 1 September 2025
- Published by International Joint Conferences on Artificial Intelligence
- Vol. 1, 801-809
Categorical Attention: Fine-grained Language-guided Noise Filtering Network for Occluded Person Re-Identification
Person Re-Identification (ReID) aims to match individuals across different camera views, but occlusions in real-world scenarios, such as vehicles or crowds, hinder feature extraction and matching. Current occluded ReID methodologies typically leverage visual augmentation techniques in an attempt to mitigate the disruptive effects of occlusion-induced noise. However, relying solely on visual data fail to effectively filter out occlusion noise. In this paper, we introduce the Fine-grained Language-guided Noise Filtering Network (FLaN-Net) for occluded ReID. FLaN-Net innovatively employs categorical attention mechanism to generate adaptive tokens that capture the following three distinct types of visual information: comprehensive descriptions of individuals, detailed visible attributes, and characteristics of occluding objects. Subsequently, a cross-attention mechanism aligns these prompts with the image, guiding the model to focus on relevant regions. To generate robust and discriminative features for occluded pedestrians, we further introduce a dynamic weighting fusion module that integrates visual, textual, and cross-attention features based on their reliability. Experimental results demonstrate that FLaN-Net outperforms existing methods on occluded ReID benchmarks, offering a robust solution for challenging real-world conditions.
- 1 September 2025
- Published by International Joint Conferences on Artificial Intelligence
- Vol. 1, 801-809
Open AccessCategorical Attention: Fine-grained Language-guided Noise Filtering Network for Occluded Person Re-Identification
Person Re-Identification (ReID) aims to match individuals across different camera views, but occlusions in real-world scenarios, such as vehicles or crowds, hinder feature extraction and matching. Current occluded ReID methodologies typically leverage visual augmentation techniques in an attempt to mitigate the disruptive effects of occlusion-induced noise. However, relying solely on visual data fail to effectively filter out occlusion noise. In this paper, we introduce the Fine-grained Language-guided Noise Filtering Network (FLaN-Net) for occluded ReID. FLaN-Net innovatively employs categorical attention mechanism to generate adaptive tokens that capture the following three distinct types of visual information: comprehensive descriptions of individuals, detailed visible attributes, and characteristics of occluding objects. Subsequently, a cross-attention mechanism aligns these prompts with the image, guiding the model to focus on relevant regions. To generate robust and discriminative features for occluded pedestrians, we further introduce a dynamic weighting fusion module that integrates visual, textual, and cross-attention features based on their reliability. Experimental results demonstrate that FLaN-Net outperforms existing methods on occluded ReID benchmarks, offering a robust solution for challenging real-world conditions.
- 14 April 2025
- Published by Elsevier in Knowledge-Based Systems
- Vol. 318
Boundary-aware Prototype Augmentation and Dual-level Knowledge Distillation for Non-Exemplar Class-Incremental Hashing
- 14 April 2025
- Published by Elsevier in Knowledge-Based Systems
- Vol. 318
Boundary-aware Prototype Augmentation and Dual-level Knowledge Distillation for Non-Exemplar Class-Incremental Hashing
- 1 November 2024
- Published by Springer Nature
- p. 452-466
Feature Refinement and Calibration for Continual Visual Search
- 1 November 2024
- Published by Springer Nature
- p. 452-466
Feature Refinement and Calibration for Continual Visual Search
- Open Access
- 1 August 2024
- Published by Tsinghua University Press in Computational Visual Media
- Vol. 10 (4) , 725-740
Central similarity consistency hashing for asymmetric image retrieval
Asymmetric image retrieval methods have drawn much attention due to their effectiveness in resource-constrained scenarios. They try to learn two models in an asymmetric paradigm, i.e., a small model for the query side and a large model for the gallery. However, we empirically find that the mutual training scheme (learning with each other) will inevitably degrade the performance of the large gallery model, due to the negative effects exerted by the small query one. In this paper, we propose Central Similarity Consistency Hashing (CSCH), which simultaneously learns a small query model and a large gallery model in a mutually promoted manner, ensuring both high retrieval accuracy and efficiency on the query side. To achieve this, we first introduce heuristically generated hash centers as the common learning target for both two models. Instead of randomly assigning each hash center to its corresponding category, we introduce the Hungarian algorithm to optimally match each of them by aligning the Hamming similarity of hash centers to the semantic similarity of their classes. Furthermore, we introduce the instance-level consistency loss, which enables the explicit knowledge transfer from the gallery model to the query one, without the sacrifice of gallery performance. Guided by the unified learning of hash centers and the distilled knowledge from gallery model, the query model can be gradually aligned to the Hamming space of the gallery model in a decoupled manner. Extensive experiments demonstrate the superiority of our CSCH method compared with current state-of-the-art deep hashing methods. The open-source code is available at https://github.com/dubanx/CSCH.
- 1 August 2024
- Published by Tsinghua University Press in Computational Visual Media
- Vol. 10 (4) , 725-740
Open AccessCentral similarity consistency hashing for asymmetric image retrieval
Asymmetric image retrieval methods have drawn much attention due to their effectiveness in resource-constrained scenarios. They try to learn two models in an asymmetric paradigm, i.e., a small model for the query side and a large model for the gallery. However, we empirically find that the mutual training scheme (learning with each other) will inevitably degrade the performance of the large gallery model, due to the negative effects exerted by the small query one. In this paper, we propose Central Similarity Consistency Hashing (CSCH), which simultaneously learns a small query model and a large gallery model in a mutually promoted manner, ensuring both high retrieval accuracy and efficiency on the query side. To achieve this, we first introduce heuristically generated hash centers as the common learning target for both two models. Instead of randomly assigning each hash center to its corresponding category, we introduce the Hungarian algorithm to optimally match each of them by aligning the Hamming similarity of hash centers to the semantic similarity of their classes. Furthermore, we introduce the instance-level consistency loss, which enables the explicit knowledge transfer from the gallery model to the query one, without the sacrifice of gallery performance. Guided by the unified learning of hash centers and the distilled knowledge from gallery model, the query model can be gradually aligned to the Hamming space of the gallery model in a decoupled manner. Extensive experiments demonstrate the superiority of our CSCH method compared with current state-of-the-art deep hashing methods. The open-source code is available at https://github.com/dubanx/CSCH.
- Open Access
- 24 March 2024
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 38 (8) , 9169-9177
Pairwise-Label-Based Deep Incremental Hashing with Simultaneous Code Expansion
Deep incremental hashing has become a subject of considerable interest due to its capability to learn hash codes in an incremental manner, eliminating the need to generate codes for classes that have already been learned. However, accommodating more classes requires longer hash codes, and regenerating database codes becomes inevitable when code expansion is required. In this paper, we present a unified deep hash framework that can simultaneously learn new classes and increase hash code capacity. Specifically, we design a triple-channel asymmetric framework to optimize a new CNN model with a target code length and a code projection matrix. This enables us to directly generate hash codes for new images, and efficiently generate expanded hash codes for original database images from the old ones with the learned projection matrix. Meanwhile, we propose a pairwise-label-based incremental similarity-preserving loss to optimize the new CNN model, which can incrementally preserve new similarities while maintaining the old ones. Additionally, we design a double-end quantization loss to reduce the quantization error from new and original query images. As a result, our method efficiently embeds both new and original similarities into the expanded hash codes, while keeping the original database codes unchanged. We conduct extensive experiments on three widely-used image retrieval benchmarks, demonstrating that our method can significantly reduce the time required to expand existing database codes, while maintaining state-of-the-art retrieval performance.
- 24 March 2024
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 38 (8) , 9169-9177
Open AccessPairwise-Label-Based Deep Incremental Hashing with Simultaneous Code Expansion
Deep incremental hashing has become a subject of considerable interest due to its capability to learn hash codes in an incremental manner, eliminating the need to generate codes for classes that have already been learned. However, accommodating more classes requires longer hash codes, and regenerating database codes becomes inevitable when code expansion is required. In this paper, we present a unified deep hash framework that can simultaneously learn new classes and increase hash code capacity. Specifically, we design a triple-channel asymmetric framework to optimize a new CNN model with a target code length and a code projection matrix. This enables us to directly generate hash codes for new images, and efficiently generate expanded hash codes for original database images from the old ones with the learned projection matrix. Meanwhile, we propose a pairwise-label-based incremental similarity-preserving loss to optimize the new CNN model, which can incrementally preserve new similarities while maintaining the old ones. Additionally, we design a double-end quantization loss to reduce the quantization error from new and original query images. As a result, our method efficiently embeds both new and original similarities into the expanded hash codes, while keeping the original database codes unchanged. We conduct extensive experiments on three widely-used image retrieval benchmarks, demonstrating that our method can significantly reduce the time required to expand existing database codes, while maintaining state-of-the-art retrieval performance.
- 20 February 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 34 (7) , 6576-6589
From Data to Optimization: Data-Free Deep Incremental Hashing With Data Disambiguation and Adaptive Proxies
Deep incremental hashing methods require a large number of original training samples to preserve old knowledge. However, the old training samples are not always available. This “data-free” setting poses great challenges for learning discriminative codes for new classes (plasticity) and maintaining the code invariance of old ones (stability) On the one hand, the presence of ambiguous data in new-emerging classes, which is highly similar to that in old classes, further aggravates catastrophic forgetting. On the other hand, although well-separated hash codes of new classes can be learned by forcing them towards fixed hash centers, it may significantly change the learned parameters of the old model, leading to severe forgetting on old classes. To alleviate the stability-plasticity dilemma in data-free situations, this paper presents a novel deep incremental hashing method called Data-Free Deep Incremental Hashing (DFIH) from the data to the optimization aspect. We start from the data aspect and propose a data disambiguation module to reveal and discard ambiguous data, especially pixels to alleviate the forgetting issues. Subsequently, we introduce a set of trainable hash proxies during the optimization process. These proxies are optimized adaptively as well as the hash codes, not only guiding the model to learn discriminative hash codes for new classes but also avoiding the dramatic modification of the model’s parameters, thus improving plasticity and maintaining stability. Extensive experiments on six widely-used image retrieval benchmarks and sixteen incremental learning situations show the superiority of DFIH. Ablation analysis further confirms the effectiveness of the components in DFIH. The code of this work is released at https://github.com/SuQinghang/DFIH.
- 20 February 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 34 (7) , 6576-6589
From Data to Optimization: Data-Free Deep Incremental Hashing With Data Disambiguation and Adaptive Proxies
Deep incremental hashing methods require a large number of original training samples to preserve old knowledge. However, the old training samples are not always available. This “data-free” setting poses great challenges for learning discriminative codes for new classes (plasticity) and maintaining the code invariance of old ones (stability) On the one hand, the presence of ambiguous data in new-emerging classes, which is highly similar to that in old classes, further aggravates catastrophic forgetting. On the other hand, although well-separated hash codes of new classes can be learned by forcing them towards fixed hash centers, it may significantly change the learned parameters of the old model, leading to severe forgetting on old classes. To alleviate the stability-plasticity dilemma in data-free situations, this paper presents a novel deep incremental hashing method called Data-Free Deep Incremental Hashing (DFIH) from the data to the optimization aspect. We start from the data aspect and propose a data disambiguation module to reveal and discard ambiguous data, especially pixels to alleviate the forgetting issues. Subsequently, we introduce a set of trainable hash proxies during the optimization process. These proxies are optimized adaptively as well as the hash codes, not only guiding the model to learn discriminative hash codes for new classes but also avoiding the dramatic modification of the model’s parameters, thus improving plasticity and maintaining stability. Extensive experiments on six widely-used image retrieval benchmarks and sixteen incremental learning situations show the superiority of DFIH. Ablation analysis further confirms the effectiveness of the components in DFIH. The code of this work is released at https://github.com/SuQinghang/DFIH.