Current state-of-the-art 6d pose estimation is too compute intensive to be deployed on edge devices, such as Microsoft HoloLens (2) or Apple iPad, both used for an increasing number of augmented reality applications. The quality of AR is greatly dependent on its capabilities to detect and overlay geometry within the scene. We propose a synthetically trained client-server-based augmented reality application, demonstrating state-of-the-art object pose estimation of metallic and texture-less industry objects on edge devices. Synthetic data enables training without real photographs, i.e. for yet-to-be-manufactured objects. Our qualitative evaluation on an AR-assisted sorting task, and quantitative evaluation on both renderings, as well as real-world data recorded on HoloLens 2, sheds light on its real-world applicability.
相關內容
Cross-modal retrieval (CMR) aims to establish interaction between different modalities, among which supervised CMR is emerging due to its flexibility in learning semantic category discrimination. Despite the remarkable performance of previous supervised CMR methods, much of their success can be attributed to the well-annotated data. However, even for unimodal data, precise annotation is expensive and time-consuming, and it becomes more challenging with the multimodal scenario. In practice, massive multimodal data are collected from the Internet with coarse annotation, which inevitably introduces noisy labels. Training with such misleading labels would bring two key challenges -- enforcing the multimodal samples to \emph{align incorrect semantics} and \emph{widen the heterogeneous gap}, resulting in poor retrieval performance. To tackle these challenges, this work proposes UOT-RCL, a Unified framework based on Optimal Transport (OT) for Robust Cross-modal Retrieval. First, we propose a semantic alignment based on partial OT to progressively correct the noisy labels, where a novel cross-modal consistent cost function is designed to blend different modalities and provide precise transport cost. Second, to narrow the discrepancy in multi-modal data, an OT-based relation alignment is proposed to infer the semantic-level cross-modal matching. Both of these two components leverage the inherent correlation among multi-modal data to facilitate effective cost function. The experiments on three widely-used cross-modal retrieval datasets demonstrate that our UOT-RCL surpasses the state-of-the-art approaches and significantly improves the robustness against noisy labels.
Knowledge graphs (KGs) have become vitally important in modern recommender systems, effectively improving performance and interpretability. Fundamentally, recommender systems aim to identify user interests based on historical interactions and recommend suitable items. However, existing works overlook two key challenges: (1) an interest corresponds to a potentially large set of related items, and (2) the lack of explicit, fine-grained exploitation of KG information and interest connectivity. This leads to an inability to reflect distinctions between entities and interests when modeling them in a single way. Additionally, the granularity of concepts in the knowledge graphs used for recommendations tends to be coarse, failing to match the fine-grained nature of user interests. This homogenization limits the precise exploitation of knowledge graph data and interest connectivity. To address these limitations, we introduce a novel embedding-based model called InBox. Specifically, various knowledge graph entities and relations are embedded as points or boxes, while user interests are modeled as boxes encompassing interaction history. Representing interests as boxes enables containing collections of item points related to that interest. We further propose that an interest comprises diverse basic concepts, and box intersection naturally supports concept combination. Across three training steps, InBox significantly outperforms state-of-the-art methods like HAKG and KGIN on recommendation tasks. Further analysis provides meaningful insights into the variable value of different KG data for recommendations. In summary, InBox advances recommender systems through box-based interest and concept modeling for sophisticated knowledge graph exploitation.
Stability and optimal convergence analysis of a non-uniform implicit-explicit L1 finite element method (IMEX-L1-FEM) is studied for a class of time-fractional linear partial differential/integro-differential equations with non-self-adjoint elliptic part having (space-time) variable coefficients. The proposed scheme is based on a combination of an IMEX-L1 method on graded mesh in the temporal direction and a finite element method in the spatial direction. With the help of a discrete fractional Gr\"{o}nwall inequality, global almost optimal error estimates in $L^2$- and $H^1$-norms are derived for the problem with initial data $u_0 \in H_0^1(\Omega)\cap H^2(\Omega)$. The novelty of our approach is based on managing the interaction of the L1 approximation of the fractional derivative and the time discrete elliptic operator to derive the optimal estimate in $H^1$-norm directly. Furthermore, a super convergence result is established when the elliptic operator is self-adjoint with time and space varying coefficients, and as a consequence, an $L^\infty$ error estimate is obtained for 2D problems that too with the initial condition is in $ H_0^1(\Omega)\cap H^2(\Omega)$. All results proved in this paper are valid uniformly as $\alpha\longrightarrow 1^{-}$, where $\alpha$ is the order of the Caputo fractional derivative. Numerical experiments are presented to validate our theoretical findings.
The assumption of a static environment is common in many geometric computer vision tasks like SLAM but limits their applicability in highly dynamic scenes. Since these tasks rely on identifying point correspondences between input images within the static part of the environment, we propose a graph neural network-based sparse feature matching network designed to perform robust matching under challenging conditions while excluding keypoints on moving objects. We employ a similar scheme of attentional aggregation over graph edges to enhance keypoint representations as state-of-the-art feature-matching networks but augment the graph with epipolar and temporal information and vastly reduce the number of graph edges. Furthermore, we introduce a self-supervised training scheme to extract pseudo labels for image pairs in dynamic environments from exclusively unprocessed visual-inertial data. A series of experiments show the superior performance of our network as it excludes keypoints on moving objects compared to state-of-the-art feature matching networks while still achieving similar results regarding conventional matching metrics. When integrated into a SLAM system, our network significantly improves performance, especially in highly dynamic scenes.
Parallel self-assembly is an efficient approach to accelerate the assembly process for modular robots. However, these approaches cannot accommodate complicated environments with obstacles, which restricts their applications. This paper considers the surrounding stationary obstacles and proposes a parallel self-assembly planning algorithm named SAPOA. With this algorithm, modular robots can avoid immovable obstacles when performing docking actions, which adapts the parallel self-assembly process to complex scenes. To validate the efficiency and scalability, we have designed 25 distinct grid maps with different obstacle configurations to simulate the algorithm. From the results compared to the existing parallel self-assembly algorithms, our algorithm shows a significantly higher success rate, which is more than 80%. For verification in real-world applications, a multi-agent hardware testbed system is developed. The algorithm is successfully deployed on four omnidirectional unmanned surface vehicles, CuBoats. The navigation strategy that translates the discrete planner, SAPOA, to the continuous controller on the CuBoats is presented. The algorithm's feasibility and flexibility were demonstrated through successful self-assembly experiments on 5 maps with varying obstacle configurations.
Differentially private mechanisms achieving worst-case optimal error bounds (e.g., the classical Laplace mechanism) are well-studied in the literature. However, when typical data are far from the worst case, \emph{instance-specific} error bounds -- which depend on the largest value in the dataset -- are more meaningful. For example, consider the sum estimation problem, where each user has an integer $x_i$ from the domain $\{0,1,\dots,U\}$ and we wish to estimate $\sum_i x_i$. This has a worst-case optimal error of $O(U/\varepsilon)$, while recent work has shown that the clipping mechanism can achieve an instance-optimal error of $O(\max_i x_i \cdot \log\log U /\varepsilon)$. Under the shuffle model, known instance-optimal protocols are less communication-efficient. The clipping mechanism also works in the shuffle model, but requires two rounds: Round one finds the clipping threshold, and round two does the clipping and computes the noisy sum of the clipped data. In this paper, we show how these two seemingly sequential steps can be done simultaneously in one round using just $1+o(1)$ messages per user, while maintaining the instance-optimal error bound. We also extend our technique to the high-dimensional sum estimation problem and sparse vector aggregation (a.k.a. frequency estimation under user-level differential privacy). Our experiments show order-of-magnitude improvements of our protocols in terms of error compared with prior work.
Counterspeech, defined as a response to mitigate online hate speech, is increasingly used as a non-censorial solution. Addressing hate speech effectively involves dispelling the stereotypes, prejudices, and biases often subtly implied in brief, single-sentence statements or abuses. These implicit expressions challenge language models, especially in seq2seq tasks, as model performance typically excels with longer contexts. Our study introduces CoARL, a novel framework enhancing counterspeech generation by modeling the pragmatic implications underlying social biases in hateful statements. CoARL's first two phases involve sequential multi-instruction tuning, teaching the model to understand intents, reactions, and harms of offensive statements, and then learning task-specific low-rank adapter weights for generating intent-conditioned counterspeech. The final phase uses reinforcement learning to fine-tune outputs for effectiveness and non-toxicity. CoARL outperforms existing benchmarks in intent-conditioned counterspeech generation, showing an average improvement of 3 points in intent-conformity and 4 points in argument-quality metrics. Extensive human evaluation supports CoARL's efficacy in generating superior and more context-appropriate responses compared to existing systems, including prominent LLMs like ChatGPT.
Foundation models, such as Large language Models (LLMs), have attracted significant amount of interest due to their large number of applications. Existing works show that appropriate prompt design, such as Chain-of-Thoughts, can unlock LLM's powerful capacity in diverse areas. However, when handling tasks involving repetitive sub-tasks and/or deceptive contents, such as arithmetic calculation and article-level fake news detection, existing prompting strategies either suffers from insufficient expressive power or intermediate errors triggered by hallucination. To make LLM more discerning to such intermediate errors, we propose to guide LLM with a Divide-and-Conquer program that simultaneously ensures superior expressive power and disentangles task decomposition, sub-task resolution, and resolution assembly process. Theoretic analysis reveals that our strategy can guide LLM to extend the expressive power of fixed-depth Transformer. Experiments indicate that our proposed method can achieve better performance than typical prompting strategies in tasks bothered by intermediate errors and deceptive contents, such as large integer multiplication, hallucination detection and misinformation detection.
Although measuring held-out accuracy has been the primary approach to evaluate generalization, it often overestimates the performance of NLP models, while alternative approaches for evaluating models either focus on individual tasks or on specific behaviors. Inspired by principles of behavioral testing in software engineering, we introduce CheckList, a task-agnostic methodology for testing NLP models. CheckList includes a matrix of general linguistic capabilities and test types that facilitate comprehensive test ideation, as well as a software tool to generate a large and diverse number of test cases quickly. We illustrate the utility of CheckList with tests for three tasks, identifying critical failures in both commercial and state-of-art models. In a user study, a team responsible for a commercial sentiment analysis model found new and actionable bugs in an extensively tested model. In another user study, NLP practitioners with CheckList created twice as many tests, and found almost three times as many bugs as users without it.
Within the rapidly developing Internet of Things (IoT), numerous and diverse physical devices, Edge devices, Cloud infrastructure, and their quality of service requirements (QoS), need to be represented within a unified specification in order to enable rapid IoT application development, monitoring, and dynamic reconfiguration. But heterogeneities among different configuration knowledge representation models pose limitations for acquisition, discovery and curation of configuration knowledge for coordinated IoT applications. This paper proposes a unified data model to represent IoT resource configuration knowledge artifacts. It also proposes IoT-CANE (Context-Aware recommendatioN systEm) to facilitate incremental knowledge acquisition and declarative context driven knowledge recommendation.
小貼士
登錄享
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191