This paper reviews the first NTIRE challenge on quality enhancement of compressed video, with a focus on the proposed methods and results. In this challenge, the new Large-scale Diverse Video (LDV) dataset is employed. The challenge has three tracks. Tracks 1 and 2 aim at enhancing the videos compressed by HEVC at a fixed QP, while Track 3 is designed for enhancing the videos compressed by x265 at a fixed bit-rate. Besides, the quality enhancement of Tracks 1 and 3 targets at improving the fidelity (PSNR), and Track 2 targets at enhancing the perceptual quality. The three tracks totally attract 482 registrations. In the test phase, 12 teams, 8 teams and 11 teams submitted the final results of Tracks 1, 2 and 3, respectively. The proposed methods and solutions gauge the state-of-the-art of video quality enhancement. The homepage of the challenge: https://github.com/RenYang-home/NTIRE21_VEnh
Weakly supervised object localization (WSOL) is a challenging problem when given image category labels but requires to learn object localization models. Optimizing a convolutional neural network (CNN) for classification tends to activate local discriminative regions while ignoring complete object extent, causing the partial activation issue. In this paper, we argue that partial activation is caused by the intrinsic characteristics of CNN, where the convolution operations produce local receptive fields and experience difficulty to capture long-range feature dependency among pixels. We introduce the token semantic coupled attention map (TS-CAM) to take full advantage of the self-attention mechanism in visual transformer for long-range dependency extraction. TS-CAM first splits an image into a sequence of patch tokens for spatial embedding, which produce attention maps of long-range visual dependency to avoid partial activation. TS-CAM then re-allocates category-related semantics for patch tokens, enabling each of them to be aware of object categories. TS-CAM finally couples the patch tokens with the semantic-agnostic attention map to achieve semantic-aware localization. Experiments on the ILSVRC/CUB-200-2011 datasets show that TS-CAM outperforms its CNN-CAM counterparts by 7.1%/27.1% for WSOL, achieving state-of-the-art performance.
In this paper, we explore generalizable, perception-to-action robotic manipulation for precise, contact-rich tasks. In particular, we contribute a framework for closed-loop robotic manipulation that automatically handles a category of objects, despite potentially unseen object instances and significant intra-category variations in shape, size and appearance. Previous approaches typically build a feedback loop on top of a real-time 6-DOF pose estimator. However, representing an object with a parameterized transformation from a fixed geometric template does not capture large intra-category shape variation. Hence we adopt the keypoint-based object representation proposed in kPAM for category-level pick-and-place, and extend it to closed-loop manipulation policies with contact-rich tasks. We first augment keypoints with local orientation information. Using the oriented keypoints, we propose a novel object-centric action representation in terms of regulating the linear/angular velocity or force/torque of these oriented keypoints. This formulation is surprisingly versatile -- we demonstrate that it can accomplish contact-rich manipulation tasks that require precision and dexterity for a category of objects with different shapes, sizes and appearances, such as peg-hole insertion for pegs and holes with significant shape variation and tight clearance. With the proposed object and action representation, our framework is also agnostic to the robot grasp pose and initial object configuration, making it flexible for integration and deployment.
Convergence of the diffusion RLS (DRLS) algorithm to steady-state has been extensively studied in the literature, whereas no analysis of its transient convergence behavior has been reported yet. In this letter, we conduct a theoretical analysis of the transient behavior of the DRLS algorithm for cyclostationary colored inputs, in the mean and mean-square error sense. The resulting analytical models allows us to thoroughly investigate the convergence behavior of the algorithm over adaptive networks in such complex scenarios. Simulation results support the accuracy and correctness of the theoretical findings.
Collaborative learning has gained great popularity due to its benefit of data privacy protection: participants can jointly train a Deep Learning model without sharing their training sets. However, recent works discovered that an adversary can fully recover the sensitive training samples from the shared gradients. Such reconstruction attacks pose severe threats to collaborative learning. Hence, effective mitigation solutions are urgently desired. In this paper, we propose to leverage data augmentation to defeat reconstruction attacks: by preprocessing sensitive images with carefully-selected transformation policies, it becomes infeasible for the adversary to extract any useful information from the corresponding gradients. We design a novel search method to automatically discover qualified policies. We adopt two new metrics to quantify the impacts of transformations on data privacy and model usability, which can significantly accelerate the search speed. Comprehensive evaluations demonstrate that the policies discovered by our method can defeat existing reconstruction attacks in collaborative learning, with high efficiency and negligible impact on the model performance.
Fusing vision, Inertial Measurement Unit (IMU) and Global Navigation Satellite System (GNSS) information is a promising solution for accurate global positioning in complex urban scenes, because of the complementarity of the different sensors. Unlike the loose coupling approaches and the EKF-based approaches in the literature, we propose an optimization-based visual-inertial SLAM tightly coupled with raw GNSS measurements, including pseudoranges and Doppler shift, which is the first of such approaches to our knowledge. Reprojection error, IMU pre-integration error and raw GNSS measurement error are jointly optimized using bundle adjustment in a sliding window, and the asynchronism between images and raw GNSS measurements is considered. Marginalization is performed in the sliding window, and some methods dealing with noisy measurements and vulnerable situations are employed. Experimental results on public dataset in complex urban scenes prove that our proposed approach outperforms state-of-the-art visual-inertial SLAM, GNSS single point positioning, as well as a loose coupling approach, both in the scenes that mainly contain low-rise buildings and the scenes that contain urban canyons.
In this paper, we propose a point cloud classification method based on graph neural network and manifold learning. Different from the conventional point cloud analysis methods, this paper uses manifold learning algorithms to embed point cloud features for better considering the geometric continuity on the surface. Then, the nature of point cloud can be acquired in low dimensional space, and after being concatenated with features in the original three-dimensional (3D)space, both the capability of feature representation and the classification network performance can be improved. We pro-pose two manifold learning modules, where one is based on locally linear embedding algorithm, and the other is a non-linear projection method based on neural network architecture. Both of them can obtain better performances than the state-of-the-art baseline. Afterwards, the graph model is constructed by using the k nearest neighbors algorithm, where the edge features are effectively aggregated for the implementation of point cloud classification. Experiments show that the proposed point cloud classification methods obtain the mean class accuracy (mA) of 90.2% and the overall accuracy (oA)of 93.2%, which reach competitive performances compared with the existing state-of-the-art related methods.
A U-Net is trained to recover acoustic interference striations (AISs) from distorted ones. A random mode-coupling matrix model is introduced to generate a large number of training data quickly, which are used to train the U-Net. The performance of AIS recovery of the U-Net is tested in range-dependent waveguides with nonlinear internal waves (NLIWs). Although the random mode-coupling matrix model is not an accurate physical model, the test results show that the U-Net successfully recovers AISs under different signal-to-noise ratios (SNRs) and different amplitudes and widths of NLIWs for different shapes.