Chao Li

Yingzhi Zhang, Taiguo Li, Chao Li et al.

Driver distraction causes a significant number of traffic accidents every year, resulting in economic losses and casualties. Currently, the level of automation in commercial vehicles is far from completely unmanned, and drivers still play an important role in operating and controlling the vehicle. Therefore, driver distraction behavior detection is crucial for road safety. At present, driver distraction detection primarily relies on traditional convolutional neural networks (CNN) and supervised learning methods. However, there are still challenges such as the high cost of labeled datasets, limited ability to capture high-level semantic information, and weak generalization performance. In order to solve these problems, this paper proposes a new self-supervised learning method based on masked image modeling for driver distraction behavior detection. Firstly, a self-supervised learning framework for masked image modeling (MIM) is introduced to solve the serious human and material consumption issues caused by dataset labeling. Secondly, the Swin Transformer is employed as an encoder. Performance is enhanced by reconfiguring the Swin Transformer block and adjusting the distribution of the number of window multi-head self-attention (W-MSA) and shifted window multi-head self-attention (SW-MSA) detection heads across all stages, which leads to model more lightening. Finally, various data augmentation strategies are used along with the best random masking strategy to strengthen the model's recognition and generalization ability. Test results on a large-scale driver distraction behavior dataset show that the self-supervised learning method proposed in this paper achieves an accuracy of 99.60%, approximating the excellent performance of advanced supervised learning methods. Our code is publicly available at github.com/Rocky1salady-killer/SL-DDBD.

Jinwei Zhang, Pascal Spincemaille, Hang Zhang et al.

Quantitative susceptibility mapping (QSM) involves acquisition and reconstruction of a series of images at multi-echo time points to estimate tissue field, which prolongs scan time and requires specific reconstruction technique. In this paper, we present our new framework, called Learned Acquisition and Reconstruction Optimization (LARO), which aims to accelerate the multi-echo gradient echo (mGRE) pulse sequence for QSM. Our approach involves optimizing a Cartesian multi-echo k-space sampling pattern with a deep reconstruction network. Next, this optimized sampling pattern was implemented in an mGRE sequence using Cartesian fan-beam k-space segmenting and ordering for prospective scans. Furthermore, we propose to insert a recurrent temporal feature fusion module into the reconstruction network to capture signal redundancies along echo time. Our ablation studies show that both the optimized sampling pattern and proposed reconstruction strategy help improve the quality of the multi-echo image reconstructions. Generalization experiments show that LARO is robust on the test data with new pathologies and different sequence parameters. Our code is available at https://github.com/Jinwei1209/LARO.git.

Junhao Chen, Peng Rong, Jingbo Sun et al.

Image style transfer occupies an important place in both computer graphics and computer vision. However, most current methods require reference to stylized images and cannot individually stylize specific objects. To overcome this limitation, we propose the "Soulstyler" framework, which allows users to guide the stylization of specific objects in an image through simple textual descriptions. We introduce a large language model to parse the text and identify stylization goals and specific styles. Combined with a CLIP-based semantic visual embedding encoder, the model understands and matches text and image content. We also introduce a novel localized text-image block matching loss that ensures that style transfer is performed only on specified target objects, while non-target regions remain in their original style. Experimental results demonstrate that our model is able to accurately perform style transfer on target objects according to textual descriptions without affecting the style of background regions. Our code will be available at https://github.com/yisuanwang/Soulstyler.

Ranran Huang, Jiancheng Cai, Chao Li et al.

The performance of local feature descriptors degrades in the presence of large rotation variations. To address this issue, we present an efficient approach to learning rotation invariant descriptors. Specifically, we propose Rotated Kernel Fusion (RKF) which imposes rotations on the convolution kernel to improve the inherent nature of CNN. Since RKF can be processed by the subsequent re-parameterization, no extra computational costs will be introduced in the inference stage. Moreover, we present Multi-oriented Feature Aggregation (MOFA) which aggregates features extracted from multiple rotated versions of the input image and can provide auxiliary knowledge for the training of RKF by leveraging the distillation strategy. We refer to the distilled RKF model as DRKF. Besides the evaluation on a rotation-augmented version of the public dataset HPatches, we also contribute a new dataset named DiverseBEV which is collected during the drone's flight and consists of bird's eye view images with large viewpoint changes and camera rotations. Extensive experiments show that our method can outperform other state-of-the-art techniques when exposed to large rotation variations.

Moule Lin, Weipeng Jing, Chao Li et al.

The building planar graph reconstruction, a.k.a. footprint reconstruction, which lies in the domain of computer vision and geoinformatics, has been long afflicted with the challenge of redundant parameters in conventional convolutional models. Therefore, in this letter, we proposed an advanced and adaptive shift architecture, namely the Switch operator, which incorporates non-exponential growth parameters while retaining analogous functionalities to integrate local feature spatial information, resembling a high-dimensional convolution operation. The Switch operator, cross-channel operation, architecture implements the XOR operation to alternately exchange adjacent or diagonal features, and then blends alternating channels through a 1x1 convolution operation to consolidate information from different channels. The SwitchNN architecture, on the other hand, incorporates a group-based parameter-sharing mechanism inspired by the convolutional neural network process and thereby significantly reducing the number of parameters. We validated our proposed approach through experiments on the SpaceNet corpus, a publicly available dataset annotated with 2,001 buildings across the cities of Los Angeles, Las Vegas, and Paris. Our results demonstrate the effectiveness of this innovative architecture in building planar graph reconstruction from 2D building images.

Chao Li, Yanan You, Wenli Zhou

Feature detection is an important procedure for image matching, where unsupervised feature detection methods are the detection approaches that have been mostly studied recently, including the ones that are based on repeatability requirement to define loss functions, and the ones that attempt to use descriptor matching to drive the optimization of the pipelines. For the former type, mean square error (MSE) is usually used which cannot provide strong constraint for training and can make the model easy to be stuck into the collapsed solution. For the later one, due to the down sampling operation and the expansion of receptive fields, the details can be lost for local descriptors can be lost, making the constraint not fine enough. Considering the issues above, we propose to combine both ideas, which including three aspects. 1) We propose to achieve fine constraint based on the requirement of repeatability while coarse constraint with guidance of deep convolution features. 2) To address the issue that optimization with MSE is limited, entropy-based cost function is utilized, both soft cross-entropy and self-information. 3) With the guidance of convolution features, we define the cost function from both positive and negative sides. Finally, we study the effect of each modification proposed and experiments demonstrate that our method achieves competitive results over the state-of-the-art approaches.

Binghua Li, Jie Mao, Zhe Sun et al.

Automated diagnosis with artificial intelligence has emerged as a promising area in the realm of medical imaging, while the interpretability of the introduced deep neural networks still remains an urgent concern. Although contemporary works, such as XProtoNet and MProtoNet, has sought to design interpretable prediction models for the issue, the localization precision of their resulting attribution maps can be further improved. To this end, we propose a Multi-scale Attentive Prototypical part Network, termed MAProtoNet, to provide more precise maps for attribution. Specifically, we introduce a concise multi-scale module to merge attentive features from quadruplet attention layers, and produces attribution maps. The proposed quadruplet attention layers can enhance the existing online class activation mapping loss via capturing interactions between the spatial and channel dimension, while the multi-scale module then fuses both fine-grained and coarse-grained information for precise maps generation. We also apply a novel multi-scale mapping loss for supervision on the proposed multi-scale module. Compared to existing interpretable prototypical part networks in medical imaging, MAProtoNet can achieve state-of-the-art performance in localization on brain tumor segmentation (BraTS) datasets, resulting in approximately 4% overall improvement on activation precision score (with a best score of 85.8%), without using additional annotated labels of segmentation. Our code will be released in https://github.com/TUAT-Novice/maprotonet.

Guang Lin, Chao Li, Jianhai Zhang et al.

The deep neural networks are known to be vulnerable to well-designed adversarial attacks. The most successful defense technique based on adversarial training (AT) can achieve optimal robustness against particular attacks but cannot generalize well to unseen attacks. Another effective defense technique based on adversarial purification (AP) can enhance generalization but cannot achieve optimal robustness. Meanwhile, both methods share one common limitation on the degraded standard accuracy. To mitigate these issues, we propose a novel pipeline to acquire the robust purifier model, named Adversarial Training on Purification (AToP), which comprises two components: perturbation destruction by random transforms (RT) and purifier model fine-tuned (FT) by adversarial loss. RT is essential to avoid overlearning to known attacks, resulting in the robustness generalization to unseen attacks, and FT is essential for the improvement of robustness. To evaluate our method in an efficient and scalable way, we conduct extensive experiments on CIFAR-10, CIFAR-100, and ImageNette to demonstrate that our method achieves optimal robustness and exhibits generalization ability against unseen attacks.

Zhenpeng Huang, Chao Li, Hao Chen et al.

In this paper, we present a new data-efficient voxel-based self-supervised learning method for event cameras. Our pre-training overcomes the limitations of previous methods, which either sacrifice temporal information by converting event sequences into 2D images for utilizing pre-trained image models or directly employ paired image data for knowledge distillation to enhance the learning of event streams. In order to make our pre-training data-efficient, we first design a semantic-uniform masking method to address the learning imbalance caused by the varying reconstruction difficulties of different regions in non-uniform data when using random masking. In addition, we ease the traditional hybrid masked modeling process by explicitly decomposing it into two branches, namely local spatio-temporal reconstruction and global semantic reconstruction to encourage the encoder to capture local correlations and global semantics, respectively. This decomposition allows our selfsupervised learning method to converge faster with minimal pre-training data. Compared to previous approaches, our self-supervised learning method does not rely on paired RGB images, yet enables simultaneous exploration of spatial and temporal cues in multiple scales. It exhibits excellent generalization performance and demonstrates significant improvements across various tasks with fewer parameters and lower computational costs.

Hao Chen, Hongrun Zhang, U Wang Chan et al.

Single domain generalization aims to address the challenge of out-of-distribution generalization problem with only one source domain available. Feature distanglement is a classic solution to this purpose, where the extracted task-related feature is presumed to be resilient to domain shift. However, the absence of references from other domains in a single-domain scenario poses significant uncertainty in feature disentanglement (ill-posedness). In this paper, we propose a new framework, named \textit{Domain Game}, to perform better feature distangling for medical image segmentation, based on the observation that diagnostic relevant features are more sensitive to geometric transformations, whilist domain-specific features probably will remain invariant to such operations. In domain game, a set of randomly transformed images derived from a singular source image is strategically encoded into two separate feature sets to represent diagnostic features and domain-specific features, respectively, and we apply forces to pull or repel them in the feature space, accordingly. Results from cross-site test domain evaluation showcase approximately an ~11.8% performance boost in prostate segmentation and around ~10.5% in brain tumor segmentation compared to the second-best method.

Jinwei Zhang, Alexey Dimov, Chao Li et al.

Purpose: To improve the generalization ability of deep learning based predictions of quantitative susceptibility mapping (QSM) from high-pass filtered phase (HPFP) data. Methods: A network fine-tuning step called HP-FINE is proposed, which is based on the high-pass filtering forward model with low-frequency preservation regularization. Several comparisons were conducted: 1. HP-FINE with and without low-frequency regularization, 2. three 3D network architectures (Unet, Progressive Unet, and Big Unet), 3. two types of network output (recovered field and susceptibility), and 4. pre-training with and without the filtering augmentation. HPFP datasets with diverse high-pass filters, another acquisition voxel size, and prospective acquisition were used to assess the accuracy of QSM predictions. In the retrospective datasets, quantitative metrics (PSNR, SSIM, RMSE and HFEN) were used for evaluation. In the prospective dataset, statistics of ROI linear regression and Bland-Altman analysis were used for evaluation. Results: In the retrospective datasets, adding low-frequency regularization in HP-FINE substantially improved prediction accuracy compared to the pre-trained results, especially when combined with the filtering augmentation and recovered field output. In the prospective datasets, HP-FINE with low-frequency regularization and recovered field output demonstrated the preservation of ROI values, a result that was not achieved when using susceptibility as the output. Furthermore, Progressive Unet pre-trained with a combination of multiple losses outperformed both Unet and Progressive Unet pre-trained with a single loss in terms of preserving ROI values.

Shanzhi Yin, Chao Li, Youneng Bao et al.

Recently, Learning-based image compression has reached comparable performance with traditional image codecs(such as JPEG, BPG, WebP). However, computational complexity and rate flexibility are still two major challenges for its practical deployment. To tackle these problems, this paper proposes two universal modules named Energy-based Channel Gating(ECG) and Bit-rate Modulator(BM), which can be directly embedded into existing end-to-end image compression models. ECG uses dynamic pruning to reduce FLOPs for more than 50\% in convolution layers, and a BM pair can modulate the latent representation to control the bit-rate in a channel-wise manner. By implementing these two modules, existing learning-based image codecs can obtain ability to output arbitrary bit-rate with a single model and reduced computation.

Balagopal Unnikrishnan, Cuong Nguyen, Shafa Balaram et al.

Deep learning models achieve strong performance for radiology image classification, but their practical application is bottlenecked by the need for large labeled training datasets. Semi-supervised learning (SSL) approaches leverage small labeled datasets alongside larger unlabeled datasets and offer potential for reducing labeling cost. In this work, we introduce NoTeacher, a novel consistency-based SSL framework which incorporates probabilistic graphical models. Unlike Mean Teacher which maintains a teacher network updated via a temporal ensemble, NoTeacher employs two independent networks, thereby eliminating the need for a teacher network. We demonstrate how NoTeacher can be customized to handle a range of challenges in radiology image classification. Specifically, we describe adaptations for scenarios with 2D and 3D inputs, uni and multi-label classification, and class distribution mismatch between labeled and unlabeled portions of the training data. In realistic empirical evaluations on three public benchmark datasets spanning the workhorse modalities of radiology (X-Ray, CT, MRI), we show that NoTeacher achieves over 90-95% of the fully supervised AUROC with less than 5-15% labeling budget. Further, NoTeacher outperforms established SSL methods with minimal hyperparameter tuning, and has implications as a principled and practical option for semisupervised learning in radiology applications.

Chao Li, Wenjian Huang, Xi Chen et al.

We present an Expectation-Maximization (EM) Regularized Deep Learning (EMReDL) model for weakly supervised tumor segmentation. The proposed framework is tailored to glioblastoma, a type of malignant tumor characterized by its diffuse infiltration into the surrounding brain tissue, which poses significant challenge to treatment target and tumor burden estimation using conventional structural MRI. Although physiological MRI provides more specific information regarding tumor infiltration, the relatively low resolution hinders a precise full annotation. This has motivated us to develop a weakly supervised deep learning solution that exploits the partial labelled tumor regions. EMReDL contains two components: a physiological prior prediction model and EM-regularized segmentation model. The physiological prior prediction model exploits the physiological MRI by training a classifier to generate a physiological prior map. This map is passed to the segmentation model for regularization using the EM algorithm. We evaluated the model on a glioblastoma dataset with the pre-operative multiparametric and recurrence MRI available. EMReDL showed to effectively segment the infiltrated tumor from the partially labelled region of potential infiltration. The segmented core tumor and infiltrated tumor demonstrated high consistency with the tumor burden labelled by experts. The performance comparisons showed that EMReDL achieved higher accuracy than published state-of-the-art models. On MR spectroscopy, the segmented region displayed more aggressive features than other partial labelled region. The proposed model can be generalized to other segmentation tasks that rely on partial labels, with the CNN architecture flexible in the framework.

Wei He, Quanming Yao, Chao Li et al.

Non-local low-rank tensor approximation has been developed as a state-of-the-art method for hyperspectral image (HSI) restoration, which includes the tasks of denoising, compressed HSI reconstruction and inpainting. Unfortunately, while its restoration performance benefits from more spectral bands, its runtime also substantially increases. In this paper, we claim that the HSI lies in a global spectral low-rank subspace, and the spectral subspaces of each full band patch group should lie in this global low-rank subspace. This motivates us to propose a unified paradigm combining the spatial and spectral properties for HSI restoration. The proposed paradigm enjoys performance superiority from the non-local spatial denoising and light computation complexity from the low-rank orthogonal basis exploration. An efficient alternating minimization algorithm with rank adaptation is developed. It is done by first solving a fidelity term-related problem for the update of a latent input image, and then learning a low-dimensional orthogonal basis and the related reduced image from the latent input image. Subsequently, non-local low-rank denoising is developed to refine the reduced image and orthogonal basis iteratively. Finally, the experiments on HSI denoising, compressed reconstruction, and inpainting tasks, with both simulated and real datasets, demonstrate its superiority with respect to state-of-the-art HSI restoration methods.

Erkun Yang, Cheng Deng, Chao Li et al.

With explosive growth of data volume and ever-increasing diversity of data modalities, cross-modal similarity search, which conducts nearest neighbor search across different modalities, has been attracting increasing interest. This paper presents a deep compact code learning solution for efficient cross-modal similarity search. Many recent studies have proven that quantization-based approaches perform generally better than hashing-based approaches on single-modal similarity search. In this paper, we propose a deep quantization approach, which is among the early attempts of leveraging deep neural networks into quantization-based cross-modal similarity search. Our approach, dubbed shared predictive deep quantization (SPDQ), explicitly formulates a shared subspace across different modalities and two private subspaces for individual modalities, and representations in the shared subspace and the private subspaces are learned simultaneously by embedding them to a reproducing kernel Hilbert space, where the mean embedding of different modality distributions can be explicitly compared. In addition, in the shared subspace, a quantizer is learned to produce the semantics preserving compact codes with the help of label alignment. Thanks to this novel network architecture in cooperation with supervised quantization training, SPDQ can preserve intramodal and intermodal similarities as much as possible and greatly reduce quantization error. Experiments on two popular benchmarks corroborate that our approach outperforms state-of-the-art methods.

Chao Li, Cheng Deng, Lei Wang et al.

In recent years, hashing has attracted more and more attention owing to its superior capacity of low storage cost and high query efficiency in large-scale cross-modal retrieval. Benefiting from deep leaning, continuously compelling results in cross-modal retrieval community have been achieved. However, existing deep cross-modal hashing methods either rely on amounts of labeled information or have no ability to learn an accuracy correlation between different modalities. In this paper, we proposed Unsupervised coupled Cycle generative adversarial Hashing networks (UCH), for cross-modal retrieval, where outer-cycle network is used to learn powerful common representation, and inner-cycle network is explained to generate reliable hash codes. Specifically, our proposed UCH seamlessly couples these two networks with generative adversarial mechanism, which can be optimized simultaneously to learn representation and hash codes. Extensive experiments on three popular benchmark datasets show that the proposed UCH outperforms the state-of-the-art unsupervised cross-modal hashing methods.

Chao Li, Cheng Deng, Ning Li et al.

Thanks to the success of deep learning, cross-modal retrieval has made significant progress recently. However, there still remains a crucial bottleneck: how to bridge the modality gap to further enhance the retrieval accuracy. In this paper, we propose a self-supervised adversarial hashing (\textbf{SSAH}) approach, which lies among the early attempts to incorporate adversarial learning into cross-modal hashing in a self-supervised fashion. The primary contribution of this work is that two adversarial networks are leveraged to maximize the semantic correlation and consistency of the representations between different modalities. In addition, we harness a self-supervised semantic network to discover high-level semantic information in the form of multi-label annotations. Such information guides the feature learning process and preserves the modality relationships in both the common semantic space and the Hamming space. Extensive experiments carried out on three benchmark datasets validate that the proposed SSAH surpasses the state-of-the-art methods.