Ultrasound is the primary modality to examine fetal growth during pregnancy, while the image quality could be affected by various factors. Quality assessment is essential for controlling the quality of ultrasound images to guarantee both the perceptual and diagnostic values. Existing automated approaches often require heavy structural annotations and the predictions may not necessarily be consistent with the assessment results by human experts. Furthermore, the overall quality of a scan and the correlation between the quality of frames should not be overlooked. In this work, we propose a reinforcement learning framework powered by two hierarchical agents that collaboratively learn to perform both frame-level and video-level quality assessments. It is equipped with a specially-designed reward mechanism that considers temporal dependency among frame quality and only requires sparse binary annotations to train. Experimental results on a challenging fetal brain dataset verify that the proposed framework could perform dual-level quality assessment and its predictions correlate well with the subjective assessment results.
Contemporary image rescaling aims at embedding a high-resolution (HR) image into a low-resolution (LR) thumbnail image that contains embedded information for HR image reconstruction. Unlike traditional image super-resolution, this enables high-fidelity HR image restoration faithful to the original one, given the embedded information in the LR thumbnail. However, state-of-the-art image rescaling methods do not optimize the LR image file size for efficient sharing and fall short of real-time performance for ultra-high-resolution (e.g., 6K) image reconstruction. To address these two challenges, we propose a novel framework (HyperThumbnail) for real-time 6K rate-distortion-aware image rescaling. Our framework first embeds an HR image into a JPEG LR thumbnail by an encoder with our proposed quantization prediction module, which minimizes the file size of the embedding LR JPEG thumbnail while maximizing HR reconstruction quality. Then, an efficient frequency-aware decoder reconstructs a high-fidelity HR image from the LR one in real time. Extensive experiments demonstrate that our framework outperforms previous image rescaling baselines in rate-distortion performance and can perform 6K image reconstruction in real time.
Recurrent All-Pairs Field Transforms (RAFT) has shown great potentials in matching tasks. However, all-pairs correlations lack non-local geometry knowledge and have difficulties tackling local ambiguities in ill-posed regions. In this paper, we propose Iterative Geometry Encoding Volume (IGEV-Stereo), a new deep network architecture for stereo matching. The proposed IGEV-Stereo builds a combined geometry encoding volume that encodes geometry and context information as well as local matching details, and iteratively indexes it to update the disparity map. To speed up the convergence, we exploit GEV to regress an accurate starting point for ConvGRUs iterations. Our IGEV-Stereo ranks $1^{st}$ on KITTI 2015 and 2012 (Reflective) among all published methods and is the fastest among the top 10 methods. In addition, IGEV-Stereo has strong cross-dataset generalization as well as high inference efficiency. We also extend our IGEV to multi-view stereo (MVS), i.e. IGEV-MVS, which achieves competitive accuracy on DTU benchmark. Code is available at https://github.com/gangweiX/IGEV.
The proliferation of IoT and mobile devices equipped with heterogeneous sensors has enabled new applications that rely on the fusion of time-series data generated by multiple sensors with different modalities. While there are promising deep neural network architectures for multimodal fusion, their performance falls apart quickly in the presence of consecutive missing data and noise across multiple modalities/sensors, the issues that are prevalent in real-world settings. We propose Centaur, a multimodal fusion model for human activity recognition (HAR) that is robust to these data quality issues. Centaur combines a data cleaning module, which is a denoising autoencoder with convolutional layers, and a multimodal fusion module, which is a deep convolutional neural network with the self-attention mechanism to capture cross-sensor correlation. We train Centaur using a stochastic data corruption scheme and evaluate it on three datasets that contain data generated by multiple inertial measurement units. Centaur's data cleaning module outperforms 2 state-of-the-art autoencoder-based models and its multimodal fusion module outperforms 4 strong baselines. Compared to 2 related robust fusion architectures, Centaur is more robust, achieving 11.59-17.52% higher accuracy in HAR, especially in the presence of consecutive missing data in multiple sensor channels.
Scene flow estimation, which predicts the 3D motion of scene points from point clouds, is a core task in autonomous driving and many other 3D vision applications. Existing methods either suffer from structure distortion due to ignorance of rigid motion consistency or require explicit pose estimation and 3D object segmentation. Errors of estimated poses and segmented objects would yield inaccurate rigidity constraints and in turn mislead scene flow estimation. In this paper, we propose a novel weight-sharing aggregation (WSA) method for feature and scene flow up-sampling. WSA does not rely on estimated poses and segmented objects, and can implicitly enforce rigidity constraints to avoid structure distortion in scene flow estimation. To further exploit geometric information and preserve local structure, we design a moving cost volume aim to keep the local region invariance. We modify the PointPWC-Net and integrate the proposed WSA and moving cost volume into the enhanced PointPWC-Net to derive an end-to-end scene flow estimation network, called WSAFlowNet. Extensive experimental results on the FlyingThings3D [19] and KITTI [21]datasets demonstrate that our WSAFlowNet achieves the state-ofthe-art performance and outperforms previous methods by a large margin. We will release the source code at https://github.com/wangyunlhr/WSAFlowNet.git
LiDAR-inertial odometry and mapping (LIOAM), which fuses complementary information of a LiDAR and an Inertial Measurement Unit (IMU), is an attractive solution for pose estimation and mapping. In LI-OAM, both pose and velocity are regarded as state variables that need to be solved. However, the widely-used Iterative Closest Point (ICP) algorithm can only provide constraint for pose, while the velocity can only be constrained by IMU pre-integration. As a result, the velocity estimates inclined to be updated accordingly with the pose results. In this paper, we propose LIW-OAM, an accurate and robust LiDAR-inertial-wheel odometry and mapping system, which fuses the measurements from LiDAR, IMU and wheel encoder in a bundle adjustment (BA) based optimization framework. The involvement of a wheel encoder could provide velocity measurement as an important observation, which assists LI-OAM to provide a more accurate state prediction. In addition, constraining the velocity variable by the observation from wheel encoder in optimization can further improve the accuracy of state estimation. Experiment results on two public datasets demonstrate that our system outperforms all state-of-the-art LI-OAM systems in terms of smaller absolute trajectory error (ATE), and embedding a wheel encoder can greatly improve the performance of LI-OAM based on the BA framework.
People break up, miscarry, and lose loved ones. Their online streaming and shopping recommendations, however, do not necessarily update, and may serve as unhappy reminders of their loss. When users want to renege on their past actions, they expect the recommender platforms to erase selective data at the model level. Ideally, given any specified user history, the recommender can unwind or "forget", as if the record was not part of training. To that end, this paper focuses on simple but widely deployed bi-linear models for recommendations based on matrix completion. Without incurring the cost of re-training, and without degrading the model unnecessarily, we develop Unlearn-ALS by making a few key modifications to the fine-tuning procedure under Alternating Least Squares optimisation, thus applicable to any bi-linear models regardless of the training procedure. We show that Unlearn-ALS is consistent with retraining without \emph{any} model degradation and exhibits rapid convergence, making it suitable for a large class of existing recommenders.
As a crucial building block in vertical Federated Learning (vFL), Split Learning (SL) has demonstrated its practice in the two-party model training collaboration, where one party holds the features of data samples and another party holds the corresponding labels. Such method is claimed to be private considering the shared information is only the embedding vectors and gradients instead of private raw data and labels. However, some recent works have shown that the private labels could be leaked by the gradients. These existing attack only works under the classification setting where the private labels are discrete. In this work, we step further to study the leakage in the scenario of the regression model, where the private labels are continuous numbers (instead of discrete labels in classification). This makes previous attacks harder to infer the continuous labels due to the unbounded output range. To address the limitation, we propose a novel learning-based attack that integrates gradient information and extra learning regularization objectives in aspects of model training properties, which can infer the labels under regression settings effectively. The comprehensive experiments on various datasets and models have demonstrated the effectiveness of our proposed attack. We hope our work can pave the way for future analyses that make the vFL framework more secure.
In this paper, we propose CGI-Stereo, a novel neural network architecture that can concurrently achieve real-time performance, state-of-the-art accuracy, and strong generalization ability. The core of our CGI-Stereo is a Context and Geometry Fusion (CGF) block which adaptively fuses context and geometry information for more accurate and efficient cost aggregation and meanwhile provides feedback to feature learning to guide more effective contextual feature extraction. The proposed CGF can be easily embedded into many existing stereo matching networks, such as PSMNet, GwcNet and ACVNet. The resulting networks are improved in accuracy by a large margin. Specially, the model which integrates our CGF with ACVNet could rank 1st on the KITTI 2012 leaderboard among all the published methods. We further propose an informative and concise cost volume, named Attention Feature Volume (AFV), which exploits a correlation volume as attention weights to filter a feature volume. Based on CGF and AFV, the proposed CGI-Stereo outperforms all other published real-time methods on KITTI benchmarks and shows better generalization ability than other real-time methods. The code is available at https://github.com/gangweiX/CGI-Stereo.
The fidelity of Generative Adversarial Networks (GAN) inversion is impeded by Out-Of-Domain (OOD) areas (e.g., background, accessories) in the image. Detecting the OOD areas beyond the generation ability of the pretrained model and blending these regions with the input image can enhance fidelity. The ``invertibility mask" figures out these OOD areas, and existing methods predict the mask with the reconstruction error. However, the estimated mask is usually inaccurate due to the influence of the reconstruction error in the In-Domain (ID) area. In this paper, we propose a novel framework that enhances the fidelity of human face inversion by designing a new module to decompose the input images to ID and OOD partitions with invertibility masks. Unlike previous works, our invertibility detector is simultaneously learned with a spatial alignment module. We iteratively align the generated features to the input geometry and reduce the reconstruction error in the ID regions. Thus, the OOD areas are more distinguishable and can be precisely predicted. Then, we improve the fidelity of our results by blending the OOD areas from the input image with the ID GAN inversion results. Our method produces photo-realistic results for real-world human face image inversion and manipulation. Extensive experiments demonstrate our method's superiority over existing methods in the quality of GAN inversion and attribute manipulation.