Abstract:Data augmentation is a critical regularization technique for deep neural networks, particularly in medical image classification. Popular data augmentation approaches include image transformation-based methods, generative data augmentation, and automatic data augmentation. However, these approaches encounter notable limitations: image transformation-based and automated data augmentation techniques cannot implement semantic transformations, leading to a constrained variety of augmented samples, and generative data augmentation methods are computationally expensive. In response to these challenges, we proposed Bayesian Random Semantic Data Augmentation (BRSDA), a novel, efficient, and plug-and-play semantic data augmentation method. BRSDA is motivated by a simple translation in the feature space along specific directions that can effectuate semantic transformations. When given a feature, we define its augmentable semantic magnitude as a random variable and estimate its distribution using variational Bayesian, then sample semantic magnitude and add to the randomly selected semantic direction to achieve semantic data augmentation. We demonstrate the effectiveness of BRSDA on five 2D and six 3D medical image datasets covering nine modalities. We also test BRSDA with mainstream neural network architectures, showcasing its robustness. Furthermore, combining BRSDA with other leading data augmentation methods achieves superior performance. Code is available online at \url{https://github.com/YaoyaoZhu19/BRSDA}.
Abstract:Radiation therapy serves as an effective and standard method for cancer treatment. Excellent radiation therapy plans always rely on high-quality dose distribution maps obtained through repeated trial and error by experienced experts. However, due to individual differences and complex clinical situations, even seasoned expert teams may need help to achieve the best treatment plan every time quickly. Many automatic dose distribution prediction methods have been proposed recently to accelerate the radiation therapy planning process and have achieved good results. However, these results suffer from over-smoothing issues, with the obtained dose distribution maps needing more high-frequency details, limiting their clinical application. To address these limitations, we propose a dose prediction diffusion model based on SwinTransformer and a projector, SP-DiffDose. To capture the direct correlation between anatomical structure and dose distribution maps, SP-DiffDose uses a structural encoder to extract features from anatomical images, then employs a conditional diffusion process to blend noise and anatomical images at multiple scales and gradually map them to dose distribution maps. To enhance the dose prediction distribution for organs at risk, SP-DiffDose utilizes SwinTransformer in the deeper layers of the network to capture features at different scales in the image. To learn good representations from the fused features, SP-DiffDose passes the fused features through a designed projector, improving dose prediction accuracy. Finally, we evaluate SP-DiffDose on an internal dataset. The results show that SP-DiffDose outperforms existing methods on multiple evaluation metrics, demonstrating the superiority and generalizability of our method.
Abstract:Talking face generation has a wide range of potential applications in the field of virtual digital humans. However, rendering high-fidelity facial video while ensuring lip synchronization is still a challenge for existing audio-driven talking face generation approaches. To address this issue, we propose HyperLips, a two-stage framework consisting of a hypernetwork for controlling lips and a high-resolution decoder for rendering high-fidelity faces. In the first stage, we construct a base face generation network that uses the hypernetwork to control the encoding latent code of the visual face information over audio. First, FaceEncoder is used to obtain latent code by extracting features from the visual face information taken from the video source containing the face frame.Then, HyperConv, which weighting parameters are updated by HyperNet with the audio features as input, will modify the latent code to synchronize the lip movement with the audio. Finally, FaceDecoder will decode the modified and synchronized latent code into visual face content. In the second stage, we obtain higher quality face videos through a high-resolution decoder. To further improve the quality of face generation, we trained a high-resolution decoder, HRDecoder, using face images and detected sketches generated from the first stage as input.Extensive quantitative and qualitative experiments show that our method outperforms state-of-the-art work with more realistic, high-fidelity, and lip synchronization. Project page: https://semchan.github.io/HyperLips Project/
Abstract:In autonomous driving tasks, scene understanding is the first step towards predicting the future behavior of the surrounding traffic participants. Yet, how to represent a given scene and extract its features are still open research questions. In this study, we propose a novel text-based representation of traffic scenes and process it with a pre-trained language encoder. First, we show that text-based representations, combined with classical rasterized image representations, lead to descriptive scene embeddings. Second, we benchmark our predictions on the nuScenes dataset and show significant improvements compared to baselines. Third, we show in an ablation study that a joint encoder of text and rasterized images outperforms the individual encoders confirming that both representations have their complementary strengths.
Abstract:Cone Beam CT (CBCT) plays a crucial role in Adaptive Radiation Therapy (ART) by accurately providing radiation treatment when organ anatomy changes occur. However, CBCT images suffer from scatter noise and artifacts, making relying solely on CBCT for precise dose calculation and accurate tissue localization challenging. Therefore, there is a need to improve CBCT image quality and Hounsfield Unit (HU) accuracy while preserving anatomical structures. To enhance the role and application value of CBCT in ART, we propose an energy-guided diffusion model (EGDiff) and conduct experiments on a chest tumor dataset to generate synthetic CT (sCT) from CBCT. The experimental results demonstrate impressive performance with an average absolute error of 26.87$\pm$6.14 HU, a structural similarity index measurement of 0.850$\pm$0.03, a peak signal-to-noise ratio of the sCT of 19.83$\pm$1.39 dB, and a normalized cross-correlation of the sCT of 0.874$\pm$0.04. These results indicate that our method outperforms state-of-the-art unsupervised synthesis methods in accuracy and visual quality, producing superior sCT images.
Abstract:Relying on large-scale training data with pixel-level labels, previous edge detection methods have achieved high performance. However, it is hard to manually label edges accurately, especially for large datasets, and thus the datasets inevitably contain noisy labels. This label-noise issue has been studied extensively for classification, while still remaining under-explored for edge detection. To address the label-noise issue for edge detection, this paper proposes to learn Pixel-level NoiseTransitions to model the label-corruption process. To achieve it, we develop a novel Pixel-wise Shift Learning (PSL) module to estimate the transition from clean to noisy labels as a displacement field. Exploiting the estimated noise transitions, our model, named PNT-Edge, is able to fit the prediction to clean labels. In addition, a local edge density regularization term is devised to exploit local structure information for better transition learning. This term encourages learning large shifts for the edges with complex local structures. Experiments on SBD and Cityscapes demonstrate the effectiveness of our method in relieving the impact of label noise. Codes will be available at github.
Abstract:Automated anesthesia promises to enable more precise and personalized anesthetic administration and free anesthesiologists from repetitive tasks, allowing them to focus on the most critical aspects of a patient's surgical care. Current research has typically focused on creating simulated environments from which agents can learn. These approaches have demonstrated good experimental results, but are still far from clinical application. In this paper, Policy Constraint Q-Learning (PCQL), a data-driven reinforcement learning algorithm for solving the problem of learning anesthesia strategies on real clinical datasets, is proposed. Conservative Q-Learning was first introduced to alleviate the problem of Q function overestimation in an offline context. A policy constraint term is added to agent training to keep the policy distribution of the agent and the anesthesiologist consistent to ensure safer decisions made by the agent in anesthesia scenarios. The effectiveness of PCQL was validated by extensive experiments on a real clinical anesthesia dataset. Experimental results show that PCQL is predicted to achieve higher gains than the baseline approach while maintaining good agreement with the reference dose given by the anesthesiologist, using less total dose, and being more responsive to the patient's vital signs. In addition, the confidence intervals of the agent were investigated, which were able to cover most of the clinical decisions of the anesthesiologist. Finally, an interpretable method, SHAP, was used to analyze the contributing components of the model predictions to increase the transparency of the model.
Abstract:Contrastive learning (CL) has shown great potential in image-to-image translation (I2I). Current CL-based I2I methods usually re-exploit the encoder of the generator to maximize the mutual information between the input and generated images, which does not exert an active effect on the decoder part. In addition, though negative samples play a crucial role in CL, most existing methods adopt a random sampling strategy, which may be less effective. In this paper, we rethink the CL paradigm in the unpaired I2I tasks from two perspectives and propose a new one-sided image translation framework called EnCo. First, we present an explicit constraint on the multi-scale pairwise features between the encoder and decoder of the generator to guarantee the semantic consistency of the input and generated images. Second, we propose a discriminative attention-guided negative sampling strategy to replace the random negative sampling, which significantly improves the performance of the generative model with an almost negligible computational overhead. Compared with existing methods, EnCo acts more effective and efficient. Extensive experiments on several popular I2I datasets demonstrate the effectiveness and advantages of our proposed approach, and we achieve several state-of-the-art compared to previous methods.
Abstract:This paper investigates the consistency problem of EKF-based cooperative localization (CL) from the perspective of Kalman decomposition, which decomposes the observable and unobservable states and allows treating them individually. The factors causing the dimension reduction of the unobservable subspace, termed error discrepancy items, are explicitly isolated and identified in the state propagation and measurement Jacobians for the first time. We prove that the error discrepancy items lead to the global orientation being erroneously observable, which in turn causes the state estimation to be inconsistent. A CL algorithm, called Kalman decomposition-based EKF (KD-EKF), is proposed to improve consistency. The key idea is to perform state estimation using the Kalman observable canonical form in the transformed coordinates. By annihilating the error discrepancy items, proper observability properties are guaranteed. More importantly, the modified state propagation and measurement Jacobians are exactly equivalent to linearizing the nonlinear CL system at current best state estimates. Consequently, the inconsistency caused by the erroneous dimension reduction of the unobservable subspace is completely eliminated. The KD-EKF CL algorithm has been extensively verified in both Monte Carlo simulations and real-world experiments and shown to achieve better performance than state-of-the-art algorithms in terms of accuracy and consistency.
Abstract:Increasing investment in computing technologies and the advancements in silicon technology has fueled rapid growth in advanced driver assistance systems (ADAS) and corresponding SoC developments. An ADAS SoC represents a heterogeneous architecture that consists of CPUs, GPUs and artificial intelligence (AI) accelerators. In order to guarantee its safety and reliability, it must process massive amount of raw data collected from multiple redundant sources such as high-definition video cameras, Radars, and Lidars to recognize objects correctly and to make the right decisions promptly. A domain specific memory architecture is essential to achieve the above goals. We present a shared memory architecture that enables high data throughput among multiple parallel accesses native to the ADAS applications. It also provides deterministic access latency with proper isolation under the stringent real-time QoS constraints. A prototype is built and analyzed. The results validate that the proposed architecture provides close to 100\% throughput for both read and write accesses generated simultaneously by many accessing masters with full injection rate. It can also provide consistent QoS to the domain specific payloads while enabling the scalability and modularity of the design.