Li Zhao

Dr. Li Zhao

orcid

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
28 October 2024
Verified
Conference Paper
Open access
ZYZhenni Yu
Zhenni Yu
XZXiaoqin Zhang
Xiaoqin Zhang
LZLi Zhao
Li Zhao
Bin YiBin Yi
Bin Yi
GXGuobao Xiao
Guobao Xiao
This paper introduces a new Segment Anything Model with Depth Perception (DSAM) for Camouflaged Object Detection (COD). DSAM exploits the zero-shot capability of SAM to realize precise segmentation in the RGB-D domain. It consists of the Prompt-Deeper Module and the Finer Module. The Prompt-Deeper Module utilizes knowledge distillation and the Bias Correction Module to achieve the interaction between RGB features and depth features, especially using depth features to correct erroneous parts in RGB features. Then, the interacted features are combined with the box prompt in SAM to create a prompt with depth perception. The Finer Module explores the possibility of accurately segmenting highly camouflaged targets from a depth perspective. It uncovers depth cues in areas missed by SAM through mask reversion, self-filtering, and self-attention operations, compensating for its defects in the COD domain. DSAM represents the first step towards the SAM-based RGB-D COD model. It maximizes the utilization of depth features while synergizing with RGB features to achieve multimodal complementarity, thereby overcoming the segmentation limitations of SAM and improving its accuracy in COD. Experimental results on COD benchmarks demonstrate that DSAM achieves excellent segmentation performance and reaches the state-of-the-art (SOTA) on COD benchmarks with less consumption of training resources. The code will be available at https://github.com/guobaoxiao/DSAM.

27 March 2020 in IEEE Access
Verified
Journal Article
Open access
LQLedan Qian
Ledan Qian
LHLibing Hu
Libing Hu
LZLi Zhao
Li Zhao
TWTao Wang
Tao Wang
RJRunhua Jiang
Runhua Jiang
Overfitting is a common problem for computer vision applications It is a problem that when training convolution neural networks and is caused by lack of training data or network complexity. The novel sequence-dropout (SD) method is proposed in this paper to alleviate the problem of overfitting when training networks. The SD method works by dropping out units (channels of feature) from the network in a sequence, replacing the traditional operation of random omitting. Sophisticated aggregation strategies are used to obtain the global information of feature channels, and channel-wise weights are produced by gating mechanism. The SD method then selectively drops out the feature channels according to the channelwise weights that represent the importance degree of each channel. The proposed SD block can be plugged into state-of-the-art backbone CNN models such as VGGNet and ResNet. The SD block is then evaluated on these models, demonstrating consistent performance gains over the baseline model on widely-used benchmark image classification datasets including MNIST, CIFAR-10, CIFAR-100, and ImageNet2012. Experimental results demonstrate that the superior performance of the SD block compared to other modern methods.

9 July 2019 in IEEE Transactions on Circuits and Systems for Video Technology
Verified
Journal Article
Closed access
XZXiaoqin Zhang
Xiaoqin Zhang
JZJingjing Zheng
Jingjing Zheng
DWDi Wang
Di Wang
LZLi Zhao
Li Zhao
Exemplar-based image denoising algorithms have shown great potential for image restoration with a multitude of existing models. In this paper, we interpret nonlocal similar patch-based denoising as a problem of low-rank recovery. This offers a physically plausible model and unifies several existing techniques in a single low-rank recovery framework. The framework can handle complex noise models, such as zero-mean Gaussian noise, impulse noise, and any other noise that can be approximated by mixing these two kinds of noise. Moreover, we introduce a new nonconvex surrogate for the l0-norm and find the optimal solution of the optimization problems when the new norm is applied to low-rank recovery. Experimental results with different kinds of noise confirm the effectiveness of the proposed low-rank recovery framework and the new norm.

20 March 2019 in IEEE Geoscience and Remote Sensing Letters
Verified
Journal Article
Closed access
XZXiaoqin Zhang
Xiaoqin Zhang
ZXZhiheng Xiao
Zhiheng Xiao
DLDongyang Li
Dongyang Li
MFMingyu Fan
Mingyu Fan
LZLi Zhao
Li Zhao

1 July 2021 in IEEE Transactions on Circuits and Systems for Video Technology
Verified
Journal Article
Closed access
XZXiaoqin Zhang
Xiaoqin Zhang
TWTao Wang
Tao Wang
RJRunhua Jiang
Runhua Jiang
LZLi Zhao
Li Zhao
YXYuewang Xu
Yuewang Xu
Video deblurring, which aims at restoring the sharp video from blurry video, is drawing increasing attention in the field of computer vision. In this paper, a method called Multi-Attention Convolutional Neural Network (MACNN) consisting of the temporal-spatial attention module, the frame channel attention module, and the feature extraction-reconstruction module is proposed. First, we use the temporal-spatial attention module and the frame channel attention module to capture features with temporal and spatial information existing across neighboring frames. Then, these captured features are fused and reconstructed to restore the sharp frame. Last but not least, we train MACNN together with a content loss and a perceptual loss in an end-to-end manner to recover realistic video details. Both quantitative and qualitative evaluation results on standard benchmarks demonstrate the proposed MACNN is superior to the state-of-the-art methods in terms of accuracy, efficiency, and visual effect.

22 March 2022 in IEEE Transactions on Industrial Informatics
Verified
Journal Article
Closed access
XZXiaoqin Zhang
Xiaoqin Zhang
CFChenxiang Fan
Chenxiang Fan
ZXZhiheng Xiao
Zhiheng Xiao
LZLi Zhao
Li Zhao
Huiling ChenHuiling Chen
Huiling Chen
XCXiaojun Chang
Xiaojun Chang
The goal of unpaired image-to-image translation is to learn a mapping from a source domain to a target domain without using any labeled examples of paired images. This problem can be solved by learning the conditional distribution of source images in the target domain. A major limitation of existing unpaired image-to-image translation algorithms is that they generate untruthful images which are over-colored and lack details, while the translation of realistic images must be rich in details. To address this limitation, we propose a random reconstructed unpaired image-to-image translation (RRUIT) framework by generative adversarial network, which uses random reconstruction to preserve the high-level features in the source and adopts an adversarial strategy to learn the distribution in the target. We update the proposed objective function with two loss functions. The auxiliary loss guides the generator to create a coarse image, while the coarse-to-fine block next to the generator block produces an image that obeys the distribution of the target domain. The coarse-to-fine block contains two sub-modules based on the densely connected atrous spatial pyramid pooling which enriches the details of generated images. We conduct extensive experiments on photorealistic stylization and artistic stylization. The experimental results confirm the superiority of the proposed RRUIT.