The goal of this paper is to propose a new Q-learning algorithm with a dummy adversarial player, which is called dummy adversarial Q-learning (DAQ), that can effectively regulate the overestimation bias in standard Q-learning. With the dummy player, the learning can be formulated as a two-player zero-sum game. The proposed DAQ unifies several Q-learning variations to control overestimation biases, such as maxmin Q-learning and minmax Q-learning (proposed in this paper) in a single framework. The proposed DAQ is a simple but effective way to suppress the overestimation bias thourgh dummy adversarial behaviors and can be easily applied to off-the-shelf reinforcement learning algorithms to improve the performances. A finite-time convergence of DAQ is analyzed from an integrated perspective by adapting an adversarial Q-learning. The performance of the suggested DAQ is empirically demonstrated under various benchmark environments.
Nowadays neural-network-based image- and video-quality metrics show better performance compared to traditional methods. However, they also became more vulnerable to adversarial attacks that increase metrics' scores without improving visual quality. The existing benchmarks of quality metrics compare their performance in terms of correlation with subjective quality and calculation time. However, the adversarial robustness of image-quality metrics is also an area worth researching. In this paper, we analyse modern metrics' robustness to different adversarial attacks. We adopted adversarial attacks from computer vision tasks and compared attacks' efficiency against 15 no-reference image/video-quality metrics. Some metrics showed high resistance to adversarial attacks which makes their usage in benchmarks safer than vulnerable metrics. The benchmark accepts new metrics submissions for researchers who want to make their metrics more robust to attacks or to find such metrics for their needs. Try our benchmark using pip install robustness-benchmark.
Multivariate time series data for real-world applications typically contain a significant amount of missing values. The dominant approach for classification with such missing values is to impute them heuristically with specific values (zero, mean, values of adjacent time-steps) or learnable parameters. However, these simple strategies do not take the data generative process into account, and more importantly, do not effectively capture the uncertainty in prediction due to the multiple possibilities for the missing values. In this paper, we propose a novel probabilistic framework for classification with multivariate time series data with missing values. Our model consists of two parts; a deep generative model for missing value imputation and a classifier. Extending the existing deep generative models to better capture structures of time-series data, our deep generative model part is trained to impute the missing values in multiple plausible ways, effectively modeling the uncertainty of the imputation. The classifier part takes the time series data along with the imputed missing values and classifies signals, and is trained to capture the predictive uncertainty due to the multiple possibilities of imputations. Importantly, we show that na\"ively combining the generative model and the classifier could result in trivial solutions where the generative model does not produce meaningful imputations. To resolve this, we present a novel regularization technique that can promote the model to produce useful imputation values that help classification. Through extensive experiments on real-world time series data with missing values, we demonstrate the effectiveness of our method.
Magnetic Resonance Imaging (MRI) stands as a powerful modality in clinical diagnosis. However, it is known that MRI faces challenges such as long acquisition time and vulnerability to motion-induced artifacts. Despite the success of many existing motion correction algorithms, there has been limited research focused on correcting motion artifacts on the estimated coil sensitivity maps for fast MRI reconstruction. Existing methods might suffer from severe performance degradation due to error propagation resulting from the inaccurate coil sensitivity maps estimation. In this work, we propose to jointly estimate the motion parameters and coil sensitivity maps for under-sampled MRI reconstruction, referred to as JSMoCo. However, joint estimation of motion parameters and coil sensitivities results in a highly ill-posed inverse problem due to an increased number of unknowns. To address this, we introduce score-based diffusion models as powerful priors and leverage the MRI physical principles to efficiently constrain the solution space for this optimization problem. Specifically, we parameterize the rigid motion as three trainable variables and model coil sensitivity maps as polynomial functions. Leveraging the physical knowledge, we then employ Gibbs sampler for joint estimation, ensuring system consistency between sensitivity maps and desired images, avoiding error propagation from pre-estimated sensitivity maps to the reconstructed images. We conduct comprehensive experiments to evaluate the performance of JSMoCo on the fastMRI dataset. The results show that our method is capable of reconstructing high-quality MRI images from sparsely-sampled k-space data, even affected by motion. It achieves this by accurately estimating both motion parameters and coil sensitivities, effectively mitigating motion-related challenges during MRI reconstruction.
Vision Transformer (ViT) has emerged as a powerful architecture in the realm of modern computer vision. However, its application in certain imaging fields, such as microscopy and satellite imaging, presents unique challenges. In these domains, images often contain multiple channels, each carrying semantically distinct and independent information. Furthermore, the model must demonstrate robustness to sparsity in input channels, as they may not be densely available during training or testing. In this paper, we propose a modification to the ViT architecture that enhances reasoning across the input channels and introduce Hierarchical Channel Sampling (HCS) as an additional regularization technique to ensure robustness when only partial channels are presented during test time. Our proposed model, ChannelViT, constructs patch tokens independently from each input channel and utilizes a learnable channel embedding that is added to the patch tokens, similar to positional embeddings. We evaluate the performance of ChannelViT on ImageNet, JUMP-CP (microscopy cell imaging), and So2Sat (satellite imaging). Our results show that ChannelViT outperforms ViT on classification tasks and generalizes well, even when a subset of input channels is used during testing. Across our experiments, HCS proves to be a powerful regularizer, independent of the architecture employed, suggesting itself as a straightforward technique for robust ViT training. Lastly, we find that ChannelViT generalizes effectively even when there is limited access to all channels during training, highlighting its potential for multi-channel imaging under real-world conditions with sparse sensors. Our code is available at https://github.com/insitro/ChannelViT.
Recently, there has been an emergence of employing LLM-powered agents as believable human proxies, based on their remarkable decision-making capability. However, existing studies mainly focus on simulating human dialogue. Human non-verbal behaviors, such as item clicking in recommender systems, although implicitly exhibiting user preferences and could enhance the modeling of users, have not been deeply explored. The main reasons lie in the gap between language modeling and behavior modeling, as well as the incomprehension of LLMs about user-item relations. To address this issue, we propose AgentCF for simulating user-item interactions in recommender systems through agent-based collaborative filtering. We creatively consider not only users but also items as agents, and develop a collaborative learning approach that optimizes both kinds of agents together. Specifically, at each time step, we first prompt the user and item agents to interact autonomously. Then, based on the disparities between the agents' decisions and real-world interaction records, user and item agents are prompted to reflect on and adjust the misleading simulations collaboratively, thereby modeling their two-sided relations. The optimized agents can also propagate their preferences to other agents in subsequent interactions, implicitly capturing the collaborative filtering idea. Overall, the optimized agents exhibit diverse interaction behaviors within our framework, including user-item, user-user, item-item, and collective interactions. The results show that these agents can demonstrate personalized behaviors akin to those of real-world individuals, sparking the development of next-generation user behavior simulation.
Most Reinforcement Learning (RL) methods are traditionally studied in an active learning setting, where agents directly interact with their environments, observe action outcomes, and learn through trial and error. However, allowing partially trained agents to interact with real physical systems poses significant challenges, including high costs, safety risks, and the need for constant supervision. Offline RL addresses these cost and safety concerns by leveraging existing datasets and reducing the need for resource-intensive real-time interactions. Nevertheless, a substantial challenge lies in the demand for these datasets to be meticulously annotated with rewards. In this paper, we introduce Optimal Transport Reward (OTR) labelling, an innovative algorithm designed to assign rewards to offline trajectories, using a small number of high-quality expert demonstrations. The core principle of OTR involves employing Optimal Transport (OT) to calculate an optimal alignment between an unlabeled trajectory from the dataset and an expert demonstration. This alignment yields a similarity measure that is effectively interpreted as a reward signal. An offline RL algorithm can then utilize these reward signals to learn a policy. This approach circumvents the need for handcrafted rewards, unlocking the potential to harness vast datasets for policy learning. Leveraging the SurRoL simulation platform tailored for surgical robot learning, we generate datasets and employ them to train policies using the OTR algorithm. By demonstrating the efficacy of OTR in a different domain, we emphasize its versatility and its potential to expedite RL deployment across a wide range of fields.
Tracking microrobots is challenging, considering their minute size and high speed. As the field progresses towards developing microrobots for biomedical applications and conducting mechanistic studies in physiologically relevant media (e.g., collagen), this challenge is exacerbated by the dense surrounding environments with feature size and shape comparable to microrobots. Herein, we report Motion Enhanced Multi-level Tracker (MEMTrack), a robust pipeline for detecting and tracking microrobots using synthetic motion features, deep learning-based object detection, and a modified Simple Online and Real-time Tracking (SORT) algorithm with interpolation for tracking. Our object detection approach combines different models based on the object's motion pattern. We trained and validated our model using bacterial micro-motors in collagen (tissue phantom) and tested it in collagen and aqueous media. We demonstrate that MEMTrack accurately tracks even the most challenging bacteria missed by skilled human annotators, achieving precision and recall of 77% and 48% in collagen and 94% and 35% in liquid media, respectively. Moreover, we show that MEMTrack can quantify average bacteria speed with no statistically significant difference from the laboriously-produced manual tracking data. MEMTrack represents a significant contribution to microrobot localization and tracking, and opens the potential for vision-based deep learning approaches to microrobot control in dense and low-contrast settings. All source code for training and testing MEMTrack and reproducing the results of the paper have been made publicly available https://github.com/sawhney-medha/MEMTrack.
Owing to the capacity of performing full-time target search, cross-modality vehicle re-identification (Re-ID) based on unmanned aerial vehicle (UAV) is gaining more attention in both video surveillance and public security. However, this promising and innovative research has not been studied sufficiently due to the data inadequacy issue. Meanwhile, the cross-modality discrepancy and orientation discrepancy challenges further aggravate the difficulty of this task. To this end, we pioneer a cross-modality vehicle Re-ID benchmark named UAV Cross-Modality Vehicle Re-ID (UCM-VeID), containing 753 identities with 16015 RGB and 13913 infrared images. Moreover, to meet cross-modality discrepancy and orientation discrepancy challenges, we present a hybrid weights decoupling network (HWDNet) to learn the shared discriminative orientation-invariant features. For the first challenge, we proposed a hybrid weights siamese network with a well-designed weight restrainer and its corresponding objective function to learn both modality-specific and modality shared information. In terms of the second challenge, three effective decoupling structures with two pretext tasks are investigated to learn orientation-invariant feature. Comprehensive experiments are carried out to validate the effectiveness of the proposed method. The dataset and codes will be released at https://github.com/moonstarL/UAV-CM-VeID.
To pursue the goal of creating an open-ended agent in Minecraft, an open-ended game environment with unlimited possibilities, this paper introduces a task-centric framework named MCU for Minecraft agent evaluation. The MCU framework leverages the concept of atom tasks as fundamental building blocks, enabling the generation of diverse or even arbitrary tasks. Within the MCU framework, each task is measured with six distinct difficulty scores (time consumption, operational effort, planning complexity, intricacy, creativity, novelty). These scores offer a multi-dimensional assessment of a task from different angles, and thus can reveal an agent's capability on specific facets. The difficulty scores also serve as the feature of each task, which creates a meaningful task space and unveils the relationship between tasks. For efficient evaluation of Minecraft agents employing the MCU framework, we maintain a unified benchmark, namely SkillForge, which comprises representative tasks with diverse categories and difficulty distribution. We also provide convenient filters for users to select tasks to assess specific capabilities of agents. We show that MCU has the high expressivity to cover all tasks used in recent literature on Minecraft agent, and underscores the need for advancements in areas such as creativity, precise control, and out-of-distribution generalization under the goal of open-ended Minecraft agent development.