Author name cluster

Wenwu Wang

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

7 papers

1 author row

EAAI Journal 2025 Journal Article

Attention Guided Class Activation Maps for Boosting Weakly Supervised Semantic Segmentation

Junhui Li
Lei Zhu
Wenwu Wang
Yin Gong

Weakly Supervised Semantic Segmentation (WSSS) has garnered significant attention for its ability to utilize weaker labels in place of expensive pixel-level annotations while maintaining commendable performance. Class Activation Maps (CAM) can still possess target localization capabilities without pixel-level annotations, and are thus widely used as pseudo labels to supervise subsequent segmentation tasks. With the continuous advancement of artificial intelligence, generating high-quality CAM by combining the strengths of Convolutional Neural Networks (CNN) and Transformer architectures has received widespread attention. As a classic architecture, Conformer adopts a parallel structure and has been applied in multiple WSSS models. We observed that the attention matrices of different levels of Transformer blocks in Conformer exhibit significant characteristic differences, and these matrices effectively capture the correlations between different regions. Based on this observation, we propose a method called Attention-Guided Class Activation Map (AG-CAM), which selectively utilizes attention matrices at different levels to enhance features for various purposes. Detailed experiments on common datasets have shown that the proposed AG-CAM method significantly improves the quality of class activation maps. Our work provides a more precise solution for WSSS, thereby demonstrating immense potential and value in real-world applications where data annotation is scarce.

Details DOI

AAAI Conference 2024 Conference Paper

Learning Temporal Resolution in Spectrogram for Audio Classification

Haohe Liu
Xubo Liu
Qiuqiang Kong
Wenwu Wang
Mark D. Plumbley

The audio spectrogram is a time-frequency representation that has been widely used for audio classification. One of the key attributes of the audio spectrogram is the temporal resolution, which depends on the hop size used in the Short-Time Fourier Transform (STFT). Previous works generally assume the hop size should be a constant value (e.g., 10 ms). However, a fixed temporal resolution is not always optimal for different types of sound. The temporal resolution affects not only classification accuracy but also computational cost. This paper proposes a novel method, DiffRes, that enables differentiable temporal resolution modeling for audio classification. Given a spectrogram calculated with a fixed hop size, DiffRes merges non-essential time frames while preserving important frames. DiffRes acts as a "drop-in" module between an audio spectrogram and a classifier and can be jointly optimized with the classification task. We evaluate DiffRes on five audio classification tasks, using mel-spectrograms as the acoustic features, followed by off-the-shelf classifier backbones. Compared with previous methods using the fixed temporal resolution, the DiffRes-based method can achieve the equivalent or better classification accuracy with at least 25% computational cost reduction. We further show that DiffRes can improve classification accuracy by increasing the temporal resolution of input acoustic features, without adding to the computational cost.

PDF Details DOI

JBHI Journal 2024 Journal Article

Three-Direction Fusion for Accurate Volumetric Liver and Tumor Segmentation

Feng Zhan
Wenwu Wang
Qian Chen
Yina Guo
Lidan He
Lili Wang

Biomedical image segmentation of organs, tissues and lesions has gained increasing attention in clinical treatment planning and navigation, which involves the exploration of two-dimensional (2D) and three-dimensional (3D) contexts in the biomedical image. Compared to 2D methods, 3D methods pay more attention to inter-slice correlations, which offer additional spatial information for image segmentation. An organ or tumor has a 3D structure that can be observed from three directions. Previous studies focus only on the vertical axis, limiting the understanding of the relationship between a tumor and its surrounding tissues. Important information can also be obtained from sagittal and coronal axes. Therefore, spatial information of organs and tumors can be obtained from three directions, i. e. the sagittal, coronal and vertical axes, to understand better the invasion depth of tumor and its relationship with the surrounding tissues. Moreover, the edges of organs and tumors in biomedical image may be blurred. To address these problems, we propose a three-direction fusion volumetric segmentation (TFVS) model for segmenting 3D biomedical images from three perspectives in sagittal, coronal and transverse planes, respectively. We use the dataset of the liver task provided by the Medical Segmentation Decathlon challenge to train our model. The TFVS method demonstrates a competitive performance on the 3D-IRCADB dataset. In addition, the t-test and Wilcoxon signed-rank test are also performed to show the statistical significance of the improvement by the proposed method as compared with the baseline methods. The proposed method is expected to be beneficial in guiding and facilitating clinical diagnosis and treatment.

Details DOI

AAAI Conference 2023 Conference Paper

Personalized Dialogue Generation with Persona-Adaptive Attention

Qiushi Huang
Yu Zhang
Tom Ko
Xubo Liu
Bo Wu
Wenwu Wang
H Tang

Persona-based dialogue systems aim to generate consistent responses based on historical context and predefined persona. Unlike conventional dialogue generation, the persona-based dialogue needs to consider both dialogue context and persona, posing a challenge for coherent training. Specifically, this requires a delicate weight balance between context and persona. To achieve that, in this paper, we propose an effective framework with Persona-Adaptive Attention (PAA), which adaptively integrates the weights from the persona and context information via our designed attention. In addition, a dynamic masking mechanism is applied to the PAA to not only drop redundant information in context and persona but also serve as a regularization mechanism to avoid overfitting. Experimental results demonstrate the superiority of the proposed PAA framework compared to the strong baselines in both automatic and human evaluation. Moreover, the proposed PAA approach can perform equivalently well in a low-resource regime compared to models trained in a full-data setting, which achieve a similar result with only 20% to 30% of data compared to the larger models trained in the full-data setting. To fully exploit the effectiveness of our design, we designed several variants for handling the weighted information in different ways, showing the necessity and sufficiency of our weighting and masking designs.

PDF Details DOI

JMLR Journal 2019 Journal Article

Robust Estimation of Derivatives Using Locally Weighted Least Absolute Deviation Regression

Wenwu Wang
Ping Yu
Lu Lin
Tiejun Tong

In nonparametric regression, the derivative estimation has attracted much attention in recent years due to its wide applications. In this paper, we propose a new method for the derivative estimation using the locally weighted least absolute deviation regression. Different from the local polynomial regression, the proposed method does not require a finite variance for the error term and so is robust to the presence of heavy-tailed errors. Meanwhile, it does not require a zero median or a positive density at zero for the error term in comparison with the local median regression. We further show that the proposed estimator with random difference is asymptotically equivalent to the (infinitely) composite quantile regression estimator. In other words, running one regression is equivalent to combining infinitely many quantile regressions. In addition, the proposed method is also extended to estimate the derivatives at the boundaries and to estimate higher-order derivatives. For the equidistant design, we derive theoretical results for the proposed estimators, including the asymptotic bias and variance, consistency, and asymptotic normality. Finally, we conduct simulation studies to demonstrate that the proposed method has better performance than the existing methods in the presence of outliers and heavy-tailed errors, and analyze the Chinese house price data for the past ten years to illustrate the usefulness of the proposed method. [abs] [ pdf ][ bib ] &copy JMLR 2019. ( edit, beta )

PDF Details

IJCAI Conference 2019 Conference Paper

Single-Channel Signal Separation and Deconvolution with Generative Adversarial Networks

Qiuqiang Kong
Yong Xu
Philip J. B. Jackson
Wenwu Wang
Mark D. Plumbley

Single-channel signal separation and deconvolution aims to separate and deconvolve individual sources from a single-channel mixture. Single-channel signal separation and deconvolution is a challenging problem in which no prior knowledge of the mixing filters is available. Both individual sources and mixing filters need to be estimated. In addition, a mixture may contain non-stationary noise which is unseen in the training set. We propose a synthesizing-decomposition (S-D) approach to solve the single-channel separation and deconvolution problem. In synthesizing, a generative model for sources is built using a generative adversarial network (GAN). In decomposition, both mixing filters and sources are optimized to minimize the reconstruction error of the mixture. The proposed S-D approach achieves a peak-to-noise-ratio (PSNR) of 18. 9 dB and 15. 4 dB in image inpainting and completion, outperforming a baseline convolutional neural network PSNR of 15. 3 dB and 12. 2 dB, respectively and achieves a PSNR of 13. 2 dB in source separation together with deconvolution, outperforming a convolutive non-negative matrix factorization (NMF) baseline of 10. 1 dB.

PDF Details

JMLR Journal 2015 Journal Article

Derivative Estimation Based on Difference Sequence via Locally Weighted Least Squares Regression

Wenwu Wang
Lu Lin

A new method is proposed for estimating derivatives of a nonparametric regression function. By applying Taylor expansion technique to a derived symmetric difference sequence, we obtain a sequence of approximate linear regression representation in which the derivative is just the intercept term. Using locally weighted least squares, we estimate the derivative in the linear regression model. The estimator has less bias in both valleys and peaks of the true derivative function. For the special case of a domain with equispaced design points, the asymptotic bias and variance are derived; consistency and asymptotic normality are established. In simulations our estimators have less bias and mean square error than its main competitors, especially second order derivative estimator. [abs] [ pdf ][ bib ] &copy JMLR 2015. ( edit, beta )

PDF Details