Weichao Lan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Weichao Lan has a total of 14 co-authors. Here are the top co-authors by number of shared publications:
- Yiu-Ming Cheung
Hong Kong Baptist University, Hong Kong, Hong Kong
7 shared publications - Zhikai Hu
Hong Kong Baptist University
6 shared publications - Mengke Li
College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China
4 shared publications - Juyong Jiang
The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China
2 shared publications - Buhua Liu
The Hong Kong University of Science and Technology - Guangzhou Campus
1 shared publication - Donglin Zhang
School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, China
1 shared publication
Latest Publications
- Open Access
- 11 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cognitive and Developmental Systems
- Vol. 17 (6) , 1377-1388
Improve Knowledge Distillation via Label Revision and Data Selection
Knowledge distillation (KD) transferring knowledge from a large teacher model to a lightweight student one has received great attention in deep model compression. In addition to the supervision of ground truth, the vanilla KD method regards the predictions of the teacher as soft labels to supervise the training of the student model. Based on vanilla KD, various approaches have been developed to further improve the performance of the student model. However, few of these previous methods have considered the reliability of the supervision from teacher models. Supervision from erroneous predictions may mislead the training of the student model. This paper therefore proposes to tackle this problem from two aspects: Label Revision to rectify the incorrect supervision and Data Selection to select appropriate samples for distillation to reduce the impact of erroneous supervision. In the former, we propose to rectify the teacher’s inaccurate predictions using the ground truth. In the latter, we introduce a data selection technique to choose suitable training samples to be supervised by the teacher, thereby reducing the impact of incorrect predictions to some extent. Experiment results demonstrate the effectiveness of the proposed method, which can be further combined with other distillation approaches to enhance their performance.
- 11 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cognitive and Developmental Systems
- Vol. 17 (6) , 1377-1388
Open AccessImprove Knowledge Distillation via Label Revision and Data Selection
Knowledge distillation (KD) transferring knowledge from a large teacher model to a lightweight student one has received great attention in deep model compression. In addition to the supervision of ground truth, the vanilla KD method regards the predictions of the teacher as soft labels to supervise the training of the student model. Based on vanilla KD, various approaches have been developed to further improve the performance of the student model. However, few of these previous methods have considered the reliability of the supervision from teacher models. Supervision from erroneous predictions may mislead the training of the student model. This paper therefore proposes to tackle this problem from two aspects: Label Revision to rectify the incorrect supervision and Data Selection to select appropriate samples for distillation to reduce the impact of erroneous supervision. In the former, we propose to rectify the teacher’s inaccurate predictions using the ground truth. In the latter, we introduce a data selection technique to choose suitable training samples to be supervised by the teacher, thereby reducing the impact of incorrect predictions to some extent. Experiment results demonstrate the effectiveness of the proposed method, which can be further combined with other distillation approaches to enhance their performance.
- Open Access
- 24 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 36 (6) , 10257-10270
Convolution Filter Compression via Sparse Linear Combinations of Quantized Basis
Convolutional neural networks (CNNs) have achieved significant performance on various real-life tasks. However, the large number of parameters in convolutional layers requires huge storage and computation resources, making it challenging to deploy CNNs on memory-constrained embedded devices. In this article, we propose a novel compression method that generates the convolution filters in each layer using a set of learnable low-dimensional quantized filter bases. The proposed method reconstructs the convolution filters by stacking the linear combinations of these filter bases. By using quantized values in weights, the compact filters can be represented using fewer bits so that the network can be highly compressed. Furthermore, we explore the sparsity of coefficients through $L_1$ -ball projection when conducting linear combination to further reduce the storage consumption and prevent overfitting. We also provide a detailed analysis of the compression performance of the proposed method. Evaluations of image classification and object detection tasks using various network structures demonstrate that the proposed method achieves a higher compression ratio with comparable accuracy compared with the existing state-of-the-art filter decomposition and network quantization methods.
- 24 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 36 (6) , 10257-10270
Open AccessConvolution Filter Compression via Sparse Linear Combinations of Quantized Basis
Convolutional neural networks (CNNs) have achieved significant performance on various real-life tasks. However, the large number of parameters in convolutional layers requires huge storage and computation resources, making it challenging to deploy CNNs on memory-constrained embedded devices. In this article, we propose a novel compression method that generates the convolution filters in each layer using a set of learnable low-dimensional quantized filter bases. The proposed method reconstructs the convolution filters by stacking the linear combinations of these filter bases. By using quantized values in weights, the compact filters can be represented using fewer bits so that the network can be highly compressed. Furthermore, we explore the sparsity of coefficients through $L_1$ -ball projection when conducting linear combination to further reduce the storage consumption and prevent overfitting. We also provide a detailed analysis of the compression performance of the proposed method. Evaluations of image classification and object detection tasks using various network structures demonstrate that the proposed method achieves a higher compression ratio with comparable accuracy compared with the existing state-of-the-art filter decomposition and network quantization methods.
- Open Access
- 15 May 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Artificial Intelligence
- Vol. 5 (10) , 5026-5039
Adjusting Logit in Gaussian Form for Long-Tailed Visual Recognition
It is not uncommon that real-world data are distributed with a long tail. For such data, the learning of deep neural networks becomes challenging because it is hard to classify tail classes correctly. In the literature, several existing methods have addressed this problem by reducing classifier bias, provided that the features obtained with long-tailed data are representative enough. However, we find that training directly on long-tailed data leads to uneven embedding space. That is, the embedding space of head classes severely compresses that of tail classes, which is not conducive to subsequent classifier learning. This paper therefore studies the problem of long-tailed visual recognition from the perspective of feature level. We introduce feature augmentation to balance the embedding distribution. The features of different classes are perturbed with varying amplitudes in Gaussian form. Based on these perturbed features, two novel logit adjustment methods are proposed to improve model performance at a modest computational overhead. Subsequently, the distorted embedding spaces of all classes can be calibrated. In such balanced-distributed embedding spaces, the biased classifier can be eliminated by simply retraining the classifier with class-balanced sampling data. Extensive experiments conducted on benchmark datasets demonstrate the superior performance of the proposed method over the state-of-the-art ones. Source code is available at https://github.com/Keke921/GCLLoss .
- 15 May 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Artificial Intelligence
- Vol. 5 (10) , 5026-5039
Open AccessAdjusting Logit in Gaussian Form for Long-Tailed Visual Recognition
It is not uncommon that real-world data are distributed with a long tail. For such data, the learning of deep neural networks becomes challenging because it is hard to classify tail classes correctly. In the literature, several existing methods have addressed this problem by reducing classifier bias, provided that the features obtained with long-tailed data are representative enough. However, we find that training directly on long-tailed data leads to uneven embedding space. That is, the embedding space of head classes severely compresses that of tail classes, which is not conducive to subsequent classifier learning. This paper therefore studies the problem of long-tailed visual recognition from the perspective of feature level. We introduce feature augmentation to balance the embedding distribution. The features of different classes are perturbed with varying amplitudes in Gaussian form. Based on these perturbed features, two novel logit adjustment methods are proposed to improve model performance at a modest computational overhead. Subsequently, the distorted embedding spaces of all classes can be calibrated. In such balanced-distributed embedding spaces, the biased classifier can be eliminated by simply retraining the classifier with class-balanced sampling data. Extensive experiments conducted on benchmark datasets demonstrate the superior performance of the proposed method over the state-of-the-art ones. Source code is available at https://github.com/Keke921/GCLLoss .
- Open Access
- 23 April 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 46 (12) , 7636-7650
Cross-Modal Hashing Method With Properties of Hamming Space: A New Perspective
Cross-modal hashing (CMH) has attracted considerable attention in recent years. Almost all existing CMH methods primarily focus on reducing the modality gap and semantic gap, i.e., aligning multi-modal features and their semantics in Hamming space, without taking into account the space gap, i.e., difference between the real number space and the Hamming space. In fact, the space gap can affect the performance of CMH methods. In this paper, we analyze and demonstrate how the space gap affects the existing CMH methods, which therefore raises two problems: solution space compression and loss function oscillation. These two problems eventually cause the retrieval performance deteriorating. Based on these findings, we propose a novel algorithm, namely Semantic Channel Hashing (SCH). First, we classify sample pairs into fully semantic-similar, partially semantic-similar, and semantic-negative ones based on their similarity and impose different constraints on them, respectively, to ensure that the entire Hamming space is utilized. Then, we introduce a semantic channel to alleviate the issue of loss function oscillation. Experimental results on three public datasets demonstrate that SCH outperforms the state-of-the-art methods. Furthermore, experimental validations are provided to substantiate the conjectures regarding solution space compression and loss function oscillation, offering visual evidence of their impact on the CMH methods.
- 23 April 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 46 (12) , 7636-7650
Open AccessCross-Modal Hashing Method With Properties of Hamming Space: A New Perspective
Cross-modal hashing (CMH) has attracted considerable attention in recent years. Almost all existing CMH methods primarily focus on reducing the modality gap and semantic gap, i.e., aligning multi-modal features and their semantics in Hamming space, without taking into account the space gap, i.e., difference between the real number space and the Hamming space. In fact, the space gap can affect the performance of CMH methods. In this paper, we analyze and demonstrate how the space gap affects the existing CMH methods, which therefore raises two problems: solution space compression and loss function oscillation. These two problems eventually cause the retrieval performance deteriorating. Based on these findings, we propose a novel algorithm, namely Semantic Channel Hashing (SCH). First, we classify sample pairs into fully semantic-similar, partially semantic-similar, and semantic-negative ones based on their similarity and impose different constraints on them, respectively, to ensure that the entire Hamming space is utilized. Then, we introduce a semantic channel to alleviate the issue of loss function oscillation. Experimental results on three public datasets demonstrate that SCH outperforms the state-of-the-art methods. Furthermore, experimental validations are provided to substantiate the conjectures regarding solution space compression and loss function oscillation, offering visual evidence of their impact on the CMH methods.
- Open Access
- 10 October 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 46 (1) , 103-116
Compact Neural Network via Stacking Hybrid Units
As an effective tool for network compression, pruning techniques have been widely used to reduce the large number of parameters in deep neural networks (NNs). Nevertheless, unstructured pruning has the limitation of dealing with the sparse and irregular weights. By contrast, structured pruning can help eliminate this drawback but it requires complex criteria to determine which components to be pruned. Therefore, this paper presents a new method termed BUnit-Net, which directly constructs compact NNs by stacking designed basic units, without requiring additional judgement criteria anymore. Given the basic units of various architectures, they are combined and stacked systematically to build up compact NNs which involve fewer weight parameters due to the independence among the units. In this way, BUnit-Net can achieve the same compression effect as unstructured pruning while the weight tensors can still remain regular and dense. We formulate BUnit-Net in diverse popular backbones in comparison with the state-of-the-art pruning methods on different benchmark datasets. Moreover, two new metrics are proposed to evaluate the trade-off of compression performance. Experiment results show that BUnit-Net can achieve comparable classification accuracy while saving around 80% FLOPs and 73% parameters. That is, stacking basic units provides a new promising way for network compression.
- 10 October 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 46 (1) , 103-116
Open AccessCompact Neural Network via Stacking Hybrid Units
As an effective tool for network compression, pruning techniques have been widely used to reduce the large number of parameters in deep neural networks (NNs). Nevertheless, unstructured pruning has the limitation of dealing with the sparse and irregular weights. By contrast, structured pruning can help eliminate this drawback but it requires complex criteria to determine which components to be pruned. Therefore, this paper presents a new method termed BUnit-Net, which directly constructs compact NNs by stacking designed basic units, without requiring additional judgement criteria anymore. Given the basic units of various architectures, they are combined and stacked systematically to build up compact NNs which involve fewer weight parameters due to the independence among the units. In this way, BUnit-Net can achieve the same compression effect as unstructured pruning while the weight tensors can still remain regular and dense. We formulate BUnit-Net in diverse popular backbones in comparison with the state-of-the-art pruning methods on different benchmark datasets. Moreover, two new metrics are proposed to evaluate the trade-off of compression performance. Experiment results show that BUnit-Net can achieve comparable classification accuracy while saving around 80% FLOPs and 73% parameters. That is, stacking basic units provides a new promising way for network compression.
- Open Access
- 22 August 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 34 (4) , 2989-3002
Joint Semantic Preserving Sparse Hashing for Cross-Modal Retrieval
Supervised cross-modal hashing has received wide attention in recent years. However, existing methods primarily rely on sample-wise semantic relationships to evaluate the semantic similarity between samples, overlooking the impact of label distribution on enhancing retrieval performance. Moreover, the limited representation capability of traditional dense hash codes hinders the preservation of semantic relationship. To overcome these challenges, we propose a new method, Joint Semantic Preserving Sparse Hashing (JSPSH). Specifically, we introduce a new concept of cluster-wise semantic relationship, which leverages label distribution to indicate which samples are more suitable for clustering. Then, we jointly utilize sample-wise and cluster-wise semantic relationships to supervise the learning of hash codes. In this way, JSPSH preserves both kinds of semantic relationships to ensure that more samples with similar semantics are clustered together, thereby achieving better retrieval results. Furthermore, we utilize high-dimensional sparse hash codes that offer stronger representation capability to preserve such more complex semantics. Finally, an interaction term is introduced in hash functions learning stage to further narrow the gap between modalities. Experimental results on three large-scale datasets demonstrate the effectiveness of JSPSH in achieving superior retrieval performance. Codes are available at https://github.com/hutt94/JSPSH.
- 22 August 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 34 (4) , 2989-3002
Open AccessJoint Semantic Preserving Sparse Hashing for Cross-Modal Retrieval
Supervised cross-modal hashing has received wide attention in recent years. However, existing methods primarily rely on sample-wise semantic relationships to evaluate the semantic similarity between samples, overlooking the impact of label distribution on enhancing retrieval performance. Moreover, the limited representation capability of traditional dense hash codes hinders the preservation of semantic relationship. To overcome these challenges, we propose a new method, Joint Semantic Preserving Sparse Hashing (JSPSH). Specifically, we introduce a new concept of cluster-wise semantic relationship, which leverages label distribution to indicate which samples are more suitable for clustering. Then, we jointly utilize sample-wise and cluster-wise semantic relationships to supervise the learning of hash codes. In this way, JSPSH preserves both kinds of semantic relationships to ensure that more samples with similar semantics are clustered together, thereby achieving better retrieval results. Furthermore, we utilize high-dimensional sparse hash codes that offer stronger representation capability to preserve such more complex semantics. Finally, an interaction term is introduced in hash functions learning stage to further narrow the gap between modalities. Experimental results on three large-scale datasets demonstrate the effectiveness of JSPSH in achieving superior retrieval performance. Codes are available at https://github.com/hutt94/JSPSH.
- Open Access
Compact Neural Networks via Stacking Designed Basic Units
Unstructured pruning has the limitation of dealing with the sparse and irregular weights. By contrast, structured pruning can help eliminate this drawback but it requires complex criterion to determine which components to be pruned. To this end, this paper presents a new method termed TissueNet, which directly constructs compact neural networks with fewer weight parameters by independently stacking designed basic units, without requiring additional judgement criteria anymore. Given the basic units of various architectures, they are combined and stacked in a certain form to build up compact neural networks. We formulate TissueNet in diverse popular backbones for comparison with the state-of-the-art pruning methods on different benchmark datasets. Moreover, two new metrics are proposed to evaluate compression performance. Experiment results show that TissueNet can achieve comparable classification accuracy while saving up to around 80% FLOPs and 89.7% parameters. That is, stacking basic units provides a new promising way for network compression.
Open AccessCompact Neural Networks via Stacking Designed Basic Units
Unstructured pruning has the limitation of dealing with the sparse and irregular weights. By contrast, structured pruning can help eliminate this drawback but it requires complex criterion to determine which components to be pruned. To this end, this paper presents a new method termed TissueNet, which directly constructs compact neural networks with fewer weight parameters by independently stacking designed basic units, without requiring additional judgement criteria anymore. Given the basic units of various architectures, they are combined and stacked in a certain form to build up compact neural networks. We formulate TissueNet in diverse popular backbones for comparison with the state-of-the-art pruning methods on different benchmark datasets. Moreover, two new metrics are proposed to evaluate compression performance. Experiment results show that TissueNet can achieve comparable classification accuracy while saving up to around 80% FLOPs and 89.7% parameters. That is, stacking basic units provides a new promising way for network compression.