Error propagation is a general but crucial problem in online semi-supervised video object segmentation. We aim to suppress error propagation through a correction mechanism with high reliability. The key insight is to disentangle the correction from the conventional mask propagation process with reliable cues. We introduce two modulators, propagation and correction modulators, to separately perform channel-wise re-calibration on the target frame embeddings according to local temporal correlations and reliable references respectively. Specifically, we assemble the modulators with a cascaded propagation-correction scheme. This avoids overriding the effects of the reliable correction modulator by the propagation modulator. Although the reference frame with the ground truth label provides reliable cues, it could be very different from the target frame and introduce uncertain or incomplete correlations. We augment the reference cues by supplementing reliable feature patches to a maintained pool, thus offering more comprehensive and expressive object representations to the modulators. In addition, a reliability filter is designed to retrieve reliable patches and pass them in subsequent frames. Our model achieves state-of-the-art performance on YouTube-VOS18/19 and DAVIS17-Val/Test benchmarks. Extensive experiments demonstrate that the correction mechanism provides considerable performance gain by fully utilizing reliable guidance. Code is available at: https://github.com/JerryX1110/RPCMVOS.
Recently, transformer-based image segmentation methods have achieved notable success against previous solutions. While for video domains, how to effectively model temporal context with the attention of object instances across frames remains an open problem. In this paper, we propose an online video instance segmentation framework with a novel instance-aware temporal fusion method. We first leverages the representation, i.e., a latent code in the global context (instance code) and CNN feature maps to represent instance- and pixel-level features. Based on this representation, we introduce a cropping-free temporal fusion approach to model the temporal consistency between video frames. Specifically, we encode global instance-specific information in the instance code and build up inter-frame contextual fusion with hybrid attentions between the instance codes and CNN feature maps. Inter-frame consistency between the instance codes are further enforced with order constraints. By leveraging the learned hybrid temporal consistency, we are able to directly retrieve and maintain instance identities across frames, eliminating the complicated frame-wise instance matching in prior methods. Extensive experiments have been conducted on popular VIS datasets, i.e. Youtube-VIS-19/21. Our model achieves the best performance among all online VIS methods. Notably, our model also eclipses all offline methods when using the ResNet-50 backbone.
This paper introduces differentiable higher-order control barrier functions (CBF) that are end-to-end trainable together with learning systems. CBFs are usually overly conservative, while guaranteeing safety. Here, we address their conservativeness by softening their definitions using environmental dependencies without loosing safety guarantees, and embed them into differentiable quadratic programs. These novel safety layers, termed a BarrierNet, can be used in conjunction with any neural network-based controller, and can be trained by gradient descent. BarrierNet allows the safety constraints of a neural controller be adaptable to changing environments. We evaluate them on a series of control problems such as traffic merging and robot navigations in 2D and 3D space, and demonstrate their effectiveness compared to state-of-the-art approaches.
Instance segmentation is a challenging task aiming at classifying and segmenting all object instances of specific classes. While two-stage box-based methods achieve top performances in the image domain, they cannot easily extend their superiority into the video domain. This is because they usually deal with features or images cropped from the detected bounding boxes without alignment, failing to capture pixel-level temporal consistency. We embrace the observation that bottom-up methods dealing with box-free features could offer accurate spacial correlations across frames, which can be fully utilized for object and pixel level tracking. We first propose our bottom-up framework equipped with a temporal context fusion module to better encode inter-frame correlations. Intra-frame cues for semantic segmentation and object localization are simultaneously extracted and reconstructed by corresponding decoders after a shared backbone. For efficient and robust tracking among instances, we introduce an instance-level correspondence across adjacent frames, which is represented by a center-to-center flow, termed as instance flow, to assemble messy dense temporal correspondences. Experiments demonstrate that the proposed method outperforms the state-of-the-art online methods (taking image-level input) on the challenging Youtube-VIS dataset.
Seismic data fault detection has recently been regarded as a 3D image segmentation task. The nature of fault structures in seismic image makes it difficult to manually label faults. Manual labeling often has many false negative labels (abnormal labels), which will seriously harm the training process. In this work, we find that region-based loss significantly outperforms distribution-based loss when dealing with falsenegative labels, therefore we propose Mask Dice loss (MD loss), which is the first reported region-based loss function for training 3D image segmentation models using sparse 2D slice labels. In addition, fault is an edge feature, and the current network widely used for fault segmentation downsamples the features multiple times, which is not conducive to edge characterization and thus requires many parameters and computational effort to preserve the features. We propose Fault-Net, which always maintains the high-resolution features of seismic images, and the inference process preserves the edge information of faults and performs effective feature fusion to achieve high-quality fault segmentation with only a few parameters and computational effort. Experimental results show that MD loss can clearly weaken the effect of anomalous labels. The Fault-Net parameter is only 0.42MB, support up to 528^3(1.5x10^8, Float32) size cuboid inference on 16GB video ram, and its inference speed on CPU and GPU is significantly faster than other networks, but the result of our method is the state-of-the-art in the FORCE fault identification competition.
We study the random reshuffling (RR) method for smooth nonconvex optimization problems with a finite-sum structure. Though this method is widely utilized in practice such as the training of neural networks, its convergence behavior is only understood in several limited settings. In this paper, under the well-known Kurdyka-Lojasiewicz (KL) inequality, we establish strong limit-point convergence results for RR with appropriate diminishing step sizes, namely, the whole sequence of iterates generated by RR is convergent and converges to a single stationary point in an almost sure sense. In addition, we derive the corresponding rate of convergence, depending on the KL exponent and the suitably selected diminishing step sizes. When the KL exponent lies in $[0,\frac12]$, the convergence is at a rate of $\mathcal{O}(t^{-1})$ with $t$ counting the iteration number. When the KL exponent belongs to $(\frac12,1)$, our derived convergence rate is of the form $\mathcal{O}(t^{-q})$ with $q\in (0,1)$ depending on the KL exponent. The standard KL inequality-based convergence analysis framework only applies to algorithms with a certain descent property. Remarkably, we conduct convergence analysis for the non-descent RR with diminishing step sizes based on the KL inequality, which generalizes the standard KL analysis framework. We summarize our main steps and core ideas in an analysis framework, which is of independent interest. As a direct application of this framework, we also establish similar strong limit-point convergence results for the shuffled proximal point method.
We aim for domestic robots to operate indoor for long-term service. Under the object-level scene dynamics induced by human daily activities, a robot needs to robustly localize itself in the environment subject to scene uncertainties. Previous works have addressed visual-based localization in static environments, yet the object-level scene dynamics challenge existing methods on long-term deployment of the robot. This paper proposes SEmantic understANding Network (SeanNet) that enables robots to measure the similarity between two scenes on both visual and semantic aspects. We further develop a similarity-based localization method based on SeanNet for monitoring the progress of visual navigation tasks. In our experiments, we benchmarked SeanNet against baselines methods on scene similarity measures, as well as visual navigation performance once integrated with a visual navigator. We demonstrate that SeanNet outperforms all baseline methods, by robustly localizing the robot under object dynamics, thus reliably informing visual navigation about the task status.
In this paper, we introduce a set-theoretic approach for mobile robot localization with infrastructure-based sensing. The proposed method computes sets that over-bound the robot body and orientation under an assumption of known noise bounds on the sensor and robot motion model. We establish theoretical properties and computational approaches for this set-theoretic localization approach and illustrate its application to an automated valet parking example in simulations and to omnidirectional robot localization problems in real-world experiments. We demonstrate that the set-theoretic localization method can perform robustly against uncertainty set initialization and sensor noises compared to the FastSLAM.
In strong line-of-sight millimeter-wave (mmWave) wireless systems, the rank-deficient channel severely hampers spatial multiplexing. To address this inherent deficiency, distributed reconfigurable intelligent surfaces (RISs) are introduced in this study to customize the wireless channel. Capitalizing on the ability of the RIS to reshape electromagnetic waves, we theoretically show that a favorable channel with an arbitrary tunable rank and a minimized truncated condition number can be established by elaborately designing the placement and reflection matrix of RISs. Different from existing works on distributed RISs, the number of elements needed for each RIS to combat the path loss and the limited phase control is also considered in this research. On the basis of the proposed channel customization, a joint transmitter-RISs-receiver (Tx-RISs-Rx) design under a hybrid mmWave system is investigated to maximize the downlink spectral efficiency. Using the proposed scheme, the optimal singular value decomposition-based hybrid beamforming at the Tx and Rx can be easily obtained without matrix decomposition for the digital and analog beamforming. The bottoms of the sub-channel mode in the water-filling power allocation algorithm, which are conventionally uncontrollable when the noise power is fixed, are proven to be independently adjustable by RISs. Moreover, the transmit power required for realizing multi-stream transmission is derived. Numerical results are presented to verify our theoretical analysis and exhibit substantial gains over systems without RISs.
A reconfigurable intelligent surface (RIS) is capable of manipulating electromagnetic waves with its flexibly configurable unit cells, thus is an appealing technology to resist fast fading caused by multi-path in wireless communications. In this paper, a two-path propagation model for RIS-assisted wireless communications is proposed by considering both the direct path from the transmitter to the receiver and the assisted path provided by the RIS. The proposed propagation model unveils that the phase shifts of RISs can be optimized by appropriate configuration for multi-path fading mitigation. In particular, four types of RISs with different configuration capabilities are introduced and their performances on improving received signal power in virtue of the assisted path to resist fast fading are compared through extensive simulation results. In addition, an RIS operating at 35 GHz is used for experimental measurement. The experimental results verify that an RIS has the ability to combat fast fading and thus improves the receiving performance, which may lay a foundation for further researches.