In recent years, domain adaptation methods have been widely applied in fault diagnosis. However, these methods are typically based on the assumption that the source and target domains have identical fault modes. In real-world industrial scenarios, unknown fault modes may occur in mechanical equipment, resulting in limitations in existing diagnostic methods. To address these issues, a dual-level entropy-aware consensus domain adversarial framework (DECDAF) is proposed for open set fault diagnosis. First, a dual-level entropy-aware module is constructed that employs unified entropy metrics at the sample-level and domain-level, which dynamically weights samples and adjusts decision boundaries. Then, for supervised learning, an auxiliary classifier module is employed to enhance the alignment of known classes; for unsupervised learning, a self-supervised clustering module is introduced to explore the intrinsic structure of the target domain and disambiguate marginal samples. Finally, a consensus domain adversarial module is designed that integrates the outputs of multiple modules to ensure consistent recognition of known classes and enhance domain alignment through adversarial learning. Comprehensive experimental results on two datasets demonstrate the effectiveness of this approach in solving the open set fault diagnosis and demonstrate its usability through real-world condition applications.

In this work, we present STOPNet, a framework for 6-DoF object suction detection on production lines, with a focus on but not limited to transparent objects, which is an important and challenging problem in robotic systems and modern industry. Current methods requiring depth input fail on transparent objects due to depth cameras’ deficiency in sensing their geometry, while we proposed a novel framework to reconstruct the scene on the production line depending only on RGB input, based on multiview stereo. Compared to existing works, our method not only reconstructs the whole 3D scene in order to obtain high-quality 6-DoF suction poses in real time but also generalizes to novel environments, novel arrangements and novel objects, including challenging transparent objects, both in simulation and the real world. Extensive experiments in simulation and the real world show that our method significantly surpasses the baselines and has better generalizability, which caters to practical industrial needs.

Recent methods for neural surface representation and rendering, for example NeuS [59], have demonstrated the remarkably high-quality reconstruction of static scenes. However, the training of NeuS takes an extremely long time (8 hours), which makes it almost impossible to apply them to dynamic scenes with thousands of frames. We propose a fast neural surface reconstruction approach, called NeuS2, which achieves two orders of magnitude improvement in terms of acceleration without compromising reconstruction quality. To accelerate the training process, we parameterize a neural surface representation by multi-resolution hash encodings and present a novel lightweight calculation of second-order derivatives tailored to our networks to leverage CUDA parallelism, achieving a factor two speed up. To further stabilize and expedite training, a progressive learning strategy is proposed to optimize multi-resolution hash encodings from coarse to fine. We extend our method for fast training of dynamic scenes, with a proposed incremental training strategy and a novel global transformation prediction component, which allow our method to handle challenging long sequences with large movements and deformations. Our experiments on various datasets demonstrate that NeuS2 significantly outperforms the state-of-the-arts in both surface reconstruction accuracy and training speed for both static and dynamic scenes. The code is available at our website: https://vcai.mpi-inf.mpg.de/projects/NeuS2/.

We propose Edit-History Vis, a visual analytics system designed to facilitate interactive exploration on Wikipedia edit history at a fine-grained level. The examination of detailed changes in Wikipedia articles is crucial for understanding how authors’ perspectives vary and conflict during the collaborative editing process. However, it is challenging to reveal the details while preserving the heterogeneous attributes of revisions, namely the time, content, and editor. The Edit-History Vis system integrates editor and textual changes of revisions by utilizing a force-directed revision graph that groups revisions based on standpoints. Through this revision graph, users can identify and analyze editing events such as edit wars, vandalism, repair, and normal updates. The effectiveness of the system in analyzing the edit history is validated through a qualitative comparison with prior work and a quantitative rating from a user study.

Hardware specialization is a promising trend to sustain performance growth. Spatial hardware accelerators that employ specialized and hierarchical computation and memory resources have recently shown high performance gains for tensor applications such as deep learning, scientific computing, and data mining. To harness the power of these hardware accelerators, programmers have to use specialized instructions with certain hardware constraints. However, these hardware accelerators and instructions are quite new and there is a lack of understanding of the hardware abstraction, performance optimization space, and automatic methodologies to explore the space. Existing compilers use hand-tuned computation implementations and optimization templates, resulting in sub-optimal performance and heavy development costs.