The success of data mixing augmentations in image classification tasks has been well-received. However, these techniques cannot be readily applied to object detection due to challenges such as spatial misalignment, foreground/background distinction, and plurality of instances. To tackle these issues, we first introduce a novel conceptual framework called Supervision Interpolation (SI), which offers a fresh perspective on interpolation-based augmentations by relaxing and generalizing Mixup. Based on SI, we propose LossMix, a simple yet versatile and effective regularization that enhances the performance and robustness of object detectors and more. Our key insight is that we can effectively regularize the training on mixed data by interpolating their loss errors instead of ground truth labels. Empirical results on the PASCAL VOC and MS COCO datasets demonstrate that LossMix can consistently outperform state-of-the-art methods widely adopted for detection. Furthermore, by jointly leveraging LossMix with unsupervised domain adaptation, we successfully improve existing approaches and set a new state of the art for cross-domain object detection.

In recent years, impressive results have been achieved in robotic manipulation. While many efforts focus on generating collision-free reference signals, few allow safe contact between the robot bodies and the environment. However, in human's daily manipulation, contact between arms and obstacles is prevalent and even necessary. This paper investigates the benefit of allowing safe contact during robotic manipulation and advocates generating and tracking compliance reference signals in both operational and null spaces. In addition, to optimize the collision-allowed trajectories, we present a hybrid solver that integrates sampling- and gradient-based approaches. We evaluate the proposed method on a goal-reaching task in five simulated and real-world environments with different collisional conditions. We show that allowing safe contact improves goal-reaching efficiency and provides feasible solutions in highly collisional scenarios where collision-free constraints cannot be enforced. Moreover, we demonstrate that planning in null space, in addition to operational space, improves trajectory safety. Further information is available at https://rolandzhu.github.io/ContactReach/.

In multi-sensor fusion, the Dempster–Shafer theory is frequently used for fault diagnosis and other decision-making problems. However, if the information collected from various sensors exhibits uncertainty and high conflict, the classical Dempster’s Combination Rule may produce a counter-intuitive result. Various studies were conducted by Ghosh and other scholars to solve this problem, and good results were achieved. This work provides a novel idea which uses the Markov chain to model the uncertainty information in evidence theory, explore the ordered rules in random evidence, and then obtain the evidence support degree, thereby reducing the effect of high-conflict evidence. Considering the information amount of evidence combined with the evidence support degree, the final credibility of evidence is obtained, and the weighted summation is used to obtain new evidence. Finally, the classical Dempster combination rule is used to process new evidence and make the final decision. Through numerical examples and case studies , the proposed method’s superior efficiency and robustness over the existing multisensor fault diagnosis methods are illustrated.

Many applications of unpaired image-to-image translation require the input contents to be preserved semantically during translations. Unaware of the inherently unmatched semantics distributions between source and target domains, existing distribution matching methods (i.e., GAN-based) can give undesired solutions. In particular, although producing visually reasonable outputs, the learned models usually flip the semantics of the inputs. To tackle this without using extra supervisions, we propose to enforce the translated outputs to be semantically invariant w.r.t. small perceptual variations of the inputs, a property we call "semantic robustness". By optimizing a robustness loss w.r.t. multi-scale feature space perturbations of the inputs, our method effectively reduces semantics flipping and produces translations that outperform existing methods both quantitatively and qualitatively.

We present a novel semi-supervised semantic segmentation method which jointly achieves two desiderata of segmentation model regularities: the label-space consistency property between image augmentations and the feature-space contrastive property among different pixels. We lever-age the pixel-level ℓ2loss and the pixel contrastive loss for the two purposes respectively. To address the computational efficiency issue and the false negative noise issue involved in the pixel contrastive loss, we further introduce and investigate several negative sampling techniques. Extensive experiments demonstrate the state-of-the-art performance of our method (PC2Seg) with the DeepLab-v3+ architecture, in several challenging semi-supervised settings derived from the VOC, Cityscapes, and COCO datasets.

The decision and planning system for autonomous driving in urban environments is hard to design. Most current methods manually design the driving policy, which can be expensive to develop and maintain at scale. Instead, with imitation learning we only need to collect data and the computer will learn and improve the driving policy automatically. However, existing imitation learning methods for autonomous driving are hardly performing well for complex urban scenarios. Moreover, the safety is not guaranteed when we use a deep neural network policy. In this paper, we proposed a framework to learn the driving policy in urban scenarios efficiently given offline connected driving data, with a safety controller incorporated to guarantee safety at test time. The experiments show that our method can achieve high performance in realistic simulations of urban driving scenarios.

Selective Laser Melting (SLM) is a metal additive manufacturing technique. The lack of SLM process repeatability is a barrier for industrial progression. SLM product quality is hard to control, even when using fixed system settings. Thus SLM could benefit from a monitoring system that provides quality assessments in real-time. Since there is no publicly available SLM dataset, we ran experiments to collect over one thousand videos, measured the physical output via height map images, and applied a proposed image processing algorithm to them to produce a dataset for semi-supervised learning. Then we trained convolutional neural networks (CNNs) to recognize desired quality metrics from videos. Experimental results demonstrate our the effectiveness of our proposed monitoring approach and also show that the semi-supervised model can mitigate the time and expense of labeling an entire SLM dataset.

To address the problem of incorrect labels in training data for deep learning, we propose a novel and simple training strategy, Iterative Cross Learning (ICL), that significantly improves the classification accuracy of neural networks with training data that has noisy labels. We randomly partition the noisy training data into multiple separate subsets, each of which is used to train an independent network. After these independent networks predict labels for the original data, if the labels agree, we update the label with the predicted result for that data point, but otherwise we update the label with a random label, a key to the success of our proposed method. The process is repeated, possibly with several stages, to gradually improve the performance. Testing our method on MNIST and CIFAR-10 with partially shuffled labels, ICL significantly improves the classification accuracy of existing methods when the data labels have noise, especially in heavy noise situations. Moreover, the proposed method doesn't require any change to the underlying neural networks' structure or loss function, so it can also easily be combined with other existing methods that address noisy labels, improving their performance.