Federated reinforcement learning (FRL) has emerged as a promising paradigm for reducing the sample complexity of reinforcement learning tasks by exploiting information from different agents. However, when each agent interacts with a potentially different environment, little to nothing is known theoretically about the non-asymptotic performance of FRL algorithms. The lack of such results can be attributed to various technical challenges and their intricate interplay: Markovian sampling, linear function approximation, multiple local updates to save communication, heterogeneity in the reward functions and transition kernels of the agents' MDPs, and continuous state-action spaces. Moreover, in the on-policy setting, the behavior policies vary with time, further complicating the analysis. In response, we introduce FedSARSA, a novel federated on-policy reinforcement learning scheme, equipped with linear function approximation, to address these challenges and provide a comprehensive finite-time error analysis. Notably, we establish that FedSARSA converges to a policy that is near-optimal for all agents, with the extent of near-optimality proportional to the level of heterogeneity. Furthermore, we prove that FedSARSA leverages agent collaboration to enable linear speedups as the number of agents increases, which holds for both fixed and adaptive step-size configurations.
Recent developments in text-to-image models, particularly Stable Diffusion, have marked significant achievements in various applications. With these advancements, there are growing safety concerns about the vulnerability of the model that malicious entities exploit to generate targeted harmful images. However, the existing methods in the vulnerability of the model mainly evaluate the alignment between the prompt and generated images, but fall short in revealing the vulnerability associated with targeted image generation. In this study, we formulate the problem of targeted adversarial attack on Stable Diffusion and propose a framework to generate adversarial prompts. Specifically, we design a gradient-based embedding optimization method to craft reliable adversarial prompts that guide stable diffusion to generate specific images. Furthermore, after obtaining successful adversarial prompts, we reveal the mechanisms that cause the vulnerability of the model. Extensive experiments on two targeted attack tasks demonstrate the effectiveness of our method in targeted attacks. The code can be obtained in https://github.com/datar001/Revealing-Vulnerabilities-in-Stable-Diffusion-via-Targeted-Attacks.
All-around, real-time navigation and sensing across the water environments by miniature soft robotics are promising, for their merits of small size, high agility and good compliance to the unstructured surroundings. In this paper, we propose and demonstrate a mantas-like soft aquatic robot which propels itself by flapping-fins using rolled dielectric elastomer actuators (DEAs) with bending motions. This robot exhibits fast-moving capabilities of swimming at 57mm/s or 1.25 body length per second (BL/s), skating on water surface at 64 mm/s (1.36 BL/s) and vertical ascending at 38mm/s (0.82 BL/s) at 1300 V, 17 Hz of the power supply. These results show the feasibility of adopting rolled DEAs for mesoscale aquatic robots with high motion performance in various water-related scenarios.
Efficiently monitoring the condition of civil infrastructures necessitates automating the structural condition assessment in visual inspection. This paper proposes an Attention-enhanced Co-interactive Fusion Network (ACF-Net) for automatic structural condition assessment in visual bridge inspection. The ACF-Net can simultaneously parse structural elements and segment surface defects on the elements in inspection images. It integrates two task-specific relearning subnets to extract task-specific features from an overall feature embedding and a co-interactive feature fusion module to capture the spatial correlation and facilitate information sharing between tasks. Experimental results demonstrate that the proposed ACF-Net outperforms the current state-of-the-art approaches, achieving promising performance with 92.11% mIoU for element parsing and 87.16% mIoU for corrosion segmentation on the new benchmark dataset Steel Bridge Condition Inspection Visual (SBCIV) testing set. An ablation study reveals the strengths of ACF-Net, and a case study showcases its capability to automate structural condition assessment. The code will be open-source after acceptance.
Autonomous ultrasound (US) scanning has attracted increased attention, and it has been seen as a potential solution to overcome the limitations of conventional US examinations, such as inter-operator variations. However, it is still challenging to autonomously and accurately transfer a planned scan trajectory on a generic atlas to the current setup for different patients, particularly for thorax applications with limited acoustic windows. To address this challenge, we proposed a skeleton graph-based non-rigid registration to adapt patient-specific properties using subcutaneous bone surface features rather than the skin surface. To this end, the self-organization mapping is successively used twice to unify the input point cloud and extract the key points, respectively. Afterward, the minimal spanning tree is employed to generate a tree graph to connect all extracted key points. To appropriately characterize the rib cartilage outline to match the source and target point cloud, the path extracted from the tree graph is optimized by maximally maintaining continuity throughout each rib. To validate the proposed approach, we manually extract the US cartilage point cloud from one volunteer and seven CT cartilage point clouds from different patients. The results demonstrate that the proposed graph-based registration is more effective and robust in adapting to the inter-patient variations than the ICP (distance error mean/SD: 5.0/1.9 mm vs 8.6/6.7 mm on seven CTs).
The vast network of bridges in the United States raises a high requirement for its maintenance and rehabilitation. The massive cost of manual visual inspection to assess the conditions of the bridges turns out to be a burden to some extent. Advanced robots have been leveraged to automate inspection data collection. Automating the segmentations of multiclass elements, as well as surface defects on the elements, in the large volume of inspection image data would facilitate an efficient and effective assessment of the bridge condition. Training separate single-task networks for element parsing (i.e., semantic segmentation of multiclass elements) and defect segmentation fails to incorporate the close connection between these two tasks in the inspection images where both recognizable structural elements and apparent surface defects are present. This paper is motivated to develop a multitask deep neural network that fully utilizes such interdependence between bridge elements and defects to boost the performance and generalization of the model. Furthermore, the effectiveness of the proposed network designs in improving the task performance was investigated, including feature decomposition, cross-talk sharing, and multi-objective loss function. A dataset with pixel-level labels of bridge elements and corrosion was developed for training and assessment of the models. Quantitative and qualitative results from evaluating the developed multitask deep neural network demonstrate that the recommended network outperforms the independent single-task networks not only in performance (2.59% higher mIoU on bridge parsing and 1.65% on corrosion segmentation) but also in computational time and implementation capability.
Aerial robots such as drones have been leveraged to perform bridge inspections. Inspection images with both recognizable structural elements and apparent surface defects can be collected by onboard cameras to provide valuable information for the condition assessment. This article aims to determine a suitable deep neural network (DNN) for parsing multiclass bridge elements in inspection images. An extensive set of quantitative evaluations along with qualitative examples show that High-Resolution Net (HRNet) possesses the desired ability. With data augmentation and a training sample of 130 images, a pre-trained HRNet is efficiently transferred to the task of structural element parsing and has achieved a 92.67% mean F1-score and 86.33% mean IoU.
Our commonsense knowledge about objects includes their typical visual attributes; we know that bananas are typically yellow or green, and not purple. Text and image corpora, being subject to reporting bias, represent this world-knowledge to varying degrees of faithfulness. In this paper, we investigate to what degree unimodal (language-only) and multimodal (image and language) models capture a broad range of visually salient attributes. To that end, we create the Visual Commonsense Tests (ViComTe) dataset covering 5 property types (color, shape, material, size, and visual co-occurrence) for over 5000 subjects. We validate this dataset by showing that our grounded color data correlates much better than ungrounded text-only data with crowdsourced color judgments provided by Paik et al. (2021). We then use our dataset to evaluate pretrained unimodal models and multimodal models. Our results indicate that multimodal models better reconstruct attribute distributions, but are still subject to reporting bias. Moreover, increasing model size does not enhance performance, suggesting that the key to visual commonsense lies in the data.
While Visual Question Answering (VQA) has progressed rapidly, previous works raise concerns about robustness of current VQA models. In this work, we study the robustness of VQA models from a novel perspective: visual context. We suggest that the models over-rely on the visual context, i.e., irrelevant objects in the image, to make predictions. To diagnose the model's reliance on visual context and measure their robustness, we propose a simple yet effective perturbation technique, SwapMix. SwapMix perturbs the visual context by swapping features of irrelevant context objects with features from other objects in the dataset. Using SwapMix we are able to change answers to more than 45 % of the questions for a representative VQA model. Additionally, we train the models with perfect sight and find that the context over-reliance highly depends on the quality of visual representations. In addition to diagnosing, SwapMix can also be applied as a data augmentation strategy during training in order to regularize the context over-reliance. By swapping the context object features, the model reliance on context can be suppressed effectively. Two representative VQA models are studied using SwapMix: a co-attention model MCAN and a large-scale pretrained model LXMERT. Our experiments on the popular GQA dataset show the effectiveness of SwapMix for both diagnosing model robustness and regularizing the over-reliance on visual context. The code for our method is available at https://github.com/vipulgupta1011/swapmix