Cracks are among the most common, most likely, and earliest of all pavement distresses. Detecting and repairing cracks as early as possible can help extend the service life of pavements. However, Detecting cracks with precision can be challenging due to their varied structural characteristics and complex background interference. In this paper, a new convolutional neural network architecture, OUR-Net, is designed to more efficiently treat both high-and low-frequency visual image features. An Ocatve Convolution is incorporated into the proposed network as an enhancement to conventional convolution. In particular, an Octave Convolution Residual Block (OCRB) is embedded in the encoder to replace the convolutional layer of the classical encoder. Moerover, we propose Octave Max Unpooling (OMU) as the upsampling operation of the decoder, enabling the neural network to learn how to decode multi-spatial frequency features. Compared with models using traditional convolution, OUR-Net has better capability of processing multi-scale information, thus simultaneously improving model performance while saving computational costs by reducing spatial redundancy. We evaluate the superiority of the proposed method by comparing it to state-of-the-art crack segmentation methods on four public datasets (CrackLS315, CFD, Crack200, DeepCrack), which encompass cracks of various widths. Comprehensive experimental results reveal that the proposed method performs excellently, which achieves F1-score and mIoU of 0.9112, 0.9271, 0.8106, 0.9318, and 0.8369, 0.8644, 0.6815, 0.8723, respectively, on the four datasets. A lightweight version of the proposed network is constructed using depthwise separable convolution that achieves excellent performance with only 0.88M parameters.

Video semantic segmentation aims to generate an accurate semantic map for each frame in a video. For such a task, conducting per-frame image segmentation is generally unacceptable in practice due to high computation cost. To address this issue, many works perform the flow-based feature propagation to reuse the features of previous frames, which essentially exploits the content continuity of consecutive frames. However, the estimated optical flow would inevitably suffer inaccuracy and then make the propagated features distorted. In this paper, we propose a distortion-aware feature correction method with the goal of improving video segmentation performance at a low price. Our core idea is to correct the features on distorted regions using the current frame while reserving the propagated features for other regions. In this way, a lightweight network is enough for achieving promising segmentation results. In particular, we propose to predict the distorted regions by utilizing the consistency of distortion patterns in images and features, such that the high-cost feature extraction from current frames can be avoided. We conduct extensive experiments on Cityscapes, CamVid, and UAVid, and the results show that our proposed method significantly outperforms previous methods and achieves the state-of-the-art performance on both segmentation accuracy and speed. Code and pretrained models are available at https://github.com/jfzhuang/DAVSS.

Domain adaptive semantic segmentation aims to exploit the pixel-level annotated samples on source domain to assist the segmentation of unlabeled samples on target domain. For such a task, the key is to construct reliable supervision signals on target domain. However, existing methods can only provide unreliable supervision signals constructed by segmentation model (SegNet) that are generally domain-sensitive. In this work, we try to find a domain-robust clue to construct more reliable supervision signals. Particularly, we experimentally observe the domain-robustness of optical flow in video tasks as it mainly represents the motion characteristics of scenes. However, optical flow cannot be directly used as supervision signals of semantic segmentation since both of them essentially represent different information. To tackle this issue, we first propose a novel Segmentation-to-Flow Module (SFM) that converts semantic segmentation maps to optical flows, named the segmentation-based flow (SF), and then propose a Segmentation-based Flow Consistency (SFC) method to impose consistency between SF and optical flow, which can implicitly supervise the training of segmentation model. The extensive experiments on two challenging benchmarks demonstrate the effectiveness of our method, and it outperforms previous state-of-the-art methods with considerable performance improvement. Our code is available at https://github.com/EdenHazardan/SFC.

Deep-reinforcement-learning-based multi-UAV collision avoidance and navigation methods have made significant progress. However, the fundamental challenge of those methods is their restricted capability to generalize beyond the specific scenario in which they are trained on. We find that the cause of the generalization failures is attributed to spurious correlation. To solve this generalization problem, we propose a causal representation learning method to identify the causal representations from images. Specifically, our method can neglect factors of variation that are irrelevant to the deep reinforcement learning task through causal intervention. Subsequently, the causal representations are fed into the policy network for action prediction. Extensive testing reveals that our proposed method exhibits better generalization results compared to state-of-the-art methods in different testing scenes.