We introduce a new neural architecture for solving visual abstract reasoning tasks inspired by human cognition, specifically by observations that human abstract reasoning often interleaves perceptual and conceptual processing as part of a flexible, iterative, and dynamic cognitive process. Inspired by this principle, our architecture models visual abstract reasoning as an iterative, self-contrasting learning process that pursues consistency between perceptual and conceptual processing of visual stimuli. We explain how this new Contrastive Perceptual-Conceptual Network (CPCNet) works using matrix reasoning problems in the style of the well-known Raven's Progressive Matrices intelligence test. Experiments on the machine learning dataset RAVEN show that CPCNet achieves higher accuracy than all previously published models while also using the weakest inductive bias. We also point out a substantial and previously unremarked class imbalance in the original RAVEN dataset, and we propose a new variant of RAVEN -- AB-RAVEN -- that is more balanced in terms of abstract concepts.
相關內容
This work presents a novel tactile perception-based method, named T-NT, for performing the needle-threading task, an application of deformable linear object (DLO) manipulation. This task is divided into two main stages: Tail-end Finding and Tail-end Insertion. In the first stage, the agent traces the contour of the thread twice using vision-based tactile sensors mounted on the gripper fingers. The two-run tracing is to locate the tail-end of the thread. In the second stage, it employs a tactile-guided reinforcement learning (RL) model to drive the robot to insert the thread into the target needle eyelet. The RL model is trained in a Unity-based simulated environment. The simulation environment supports tactile rendering which can produce realistic tactile images and thread modeling. During insertion, the position of the poke point and the center of the eyelet are obtained through a pre-trained segmentation model, Grounded-SAM, which predicts the masks for both the needle eye and thread imprints. These positions are then fed into the reinforcement learning model, aiding in a smoother transition to real-world applications. Extensive experiments on real robots are conducted to demonstrate the efficacy of our method. More experiments and videos can be found in the supplementary materials and on the website: //sites.google.com/view/tac-needlethreading.
The modeling and simulation of coupled neuromusculoskeletal-exoskeletal systems play a crucial role in human biomechanical analysis, as well as in the design and control of exoskeletons. However, conventional dynamic simulation frameworks have limitations due to their reliance on experimental data and their inability to capture comprehensive biomechanical signals and dynamic responses. To address these challenges, we introduce an optimization-based dynamic simulation framework that integrates a complete neuromusculoskeletal feedback loop, rigid-body dynamics, human-exoskeleton interaction, and foot-ground contact. Without relying on experimental measurements or empirical data, our framework employs a stepwise optimization process to determine muscle reflex parameters, taking into account multidimensional criteria. This allows the framework to generate a full range of kinematic and biomechanical signals, including muscle activations, muscle forces, joint torques, etc., which are typically challenging to measure experimentally. To validate the effectiveness of the framework, we compare the simulated results with experimental data obtained from a healthy subject wearing an exoskeleton while walking at different speeds (0.9, 1.0, and 1.1 m/s) and terrains (flat and uphill). The results demonstrate that our framework can effectively and accurately capture the qualitative differences in muscle activity associated with different functions, as well as the evolutionary patterns of muscle activity and kinematic signals under varying walking conditions. The simulation framework we propose has the potential to facilitate gait analysis and performance evaluation of coupled human-exoskeleton systems, as well as enable efficient and cost-effective testing of novel exoskeleton designs and control strategies.
This study examines the adaptation of the problem-solving studio to computer science education by combining it with pair programming. Pair programming is a software engineering practice in industry, but has seen mixed results in the classroom. Recent research suggests that pair programming has promise and potential to be an effective pedagogical tool, however what constitutes good instructional design and implementation for pair programming in the classroom is not clear. We developed a framework for instructional design for pair programming by adapting the problem-solving studio (PSS), a pedagogy originally from biomedical engineering. PSS involves teams of students solving open-ended problems with real-time feedback given by the instructor. Notably, PSS uses problems of adjustable difficulty to keep students of all levels engaged and functioning within the zone of proximal development. The course structure has three stages, first starting with demonstration, followed by a PSS session, then finishing with a debrief. We studied the combination of PSS and pair programming in a CS1 class over three years. Surveys of the students report a high level of engagement, learning, and motivation.
This paper introduces a two-stage framework designed to enhance long-tail class incremental learning, enabling the model to progressively learn new classes, while mitigating catastrophic forgetting in the context of long-tailed data distributions. Addressing the challenge posed by the under-representation of tail classes in long-tail class incremental learning, our approach achieves classifier alignment by leveraging global variance as an informative measure and class prototypes in the second stage. This process effectively captures class properties and eliminates the need for data balancing or additional layer tuning. Alongside traditional class incremental learning losses in the first stage, the proposed approach incorporates mixup classes to learn robust feature representations, ensuring smoother boundaries. The proposed framework can seamlessly integrate as a module with any class incremental learning method to effectively handle long-tail class incremental learning scenarios. Extensive experimentation on the CIFAR-100 and ImageNet-Subset datasets validates the approach's efficacy, showcasing its superiority over state-of-the-art techniques across various long-tail CIL settings.
In this paper, a stochastic geometry based analytical framework is proposed for secure simultaneous transmitting and reflecting reconfigurable intelligent surface (STAR-RIS) assisted non-orthogonal multiple access (NOMA) transmissions, where legitimate users (LUs) and eavesdroppers are randomly distributed. Both the time-switching protocol (TS) and energy splitting (ES) protocol are considered for the STAR-RIS. To characterize system performance, the channel statistics are first provided, and the Gamma approximation is adopted for general cascaded $\kappa$-$\mu$ fading. Afterward, the closed-form expressions for both the secrecy outage probability (SOP) and average secrecy capacity (ASC) are derived. To obtain further insights, the asymptotic performance for the secrecy diversity order and the secrecy slope are deduced. The theoretical results show that 1) the secrecy diversity orders of the strong LU and the weak LU depend on the path loss exponent and the distribution of the received signal-to-noise ratio, respectively; 2) the secrecy slope of the ES protocol achieves the value of one, higher than the slope of the TS protocol which is the mode operation parameter of TS. The numerical results demonstrate that: 1) there is an optimal STAR-RIS mode operation parameter to maximize the secrecy performance; 2) the STAR-RIS-NOMA significantly outperforms the STAR-RIS-orthogonal multiple access.
With the development of multimodality and large language models, the deep learning-based technique for medical image captioning holds the potential to offer valuable diagnostic recommendations. However, current generic text and image pre-trained models do not yield satisfactory results when it comes to describing intricate details within medical images. In this paper, we present a novel medical image captioning method guided by the segment anything model (SAM) to enable enhanced encoding with both general and detailed feature extraction. In addition, our approach employs a distinctive pre-training strategy with mixed semantic learning to simultaneously capture both the overall information and finer details within medical images. We demonstrate the effectiveness of this approach, as it outperforms the pre-trained BLIP2 model on various evaluation metrics for generating descriptions of medical images.
The development of trustworthy conversational information-seeking systems relies on dialogue models that can generate faithful and accurate responses based on relevant knowledge texts. However, two main challenges hinder this task. Firstly, language models may generate hallucinations due to data biases present in their pretraining corpus. Secondly, knowledge texts often contain redundant and irrelevant information that distracts the model's attention from the relevant text span. Previous works use additional data annotations on the knowledge texts to learn a knowledge identification module in order to bypass irrelevant information, but collecting such high-quality span annotations can be costly. In this work, we leverage reinforcement learning algorithms to overcome the above challenges by introducing a novel reward function. Our reward function combines an accuracy metric and a faithfulness metric to provide a balanced quality judgment of generated responses, which can be used as a cost-effective approximation to a human preference reward model when only a few preference annotations are available. Empirical experiments on two conversational information-seeking datasets demonstrate that our method can compete with other strong supervised learning baselines.
Despite the recent progress in deep learning, most approaches still go for a silo-like solution, focusing on learning each task in isolation: training a separate neural network for each individual task. Many real-world problems, however, call for a multi-modal approach and, therefore, for multi-tasking models. Multi-task learning (MTL) aims to leverage useful information across tasks to improve the generalization capability of a model. This thesis is concerned with multi-task learning in the context of computer vision. First, we review existing approaches for MTL. Next, we propose several methods that tackle important aspects of multi-task learning. The proposed methods are evaluated on various benchmarks. The results show several advances in the state-of-the-art of multi-task learning. Finally, we discuss several possibilities for future work.
Data augmentation, the artificial creation of training data for machine learning by transformations, is a widely studied research field across machine learning disciplines. While it is useful for increasing the generalization capabilities of a model, it can also address many other challenges and problems, from overcoming a limited amount of training data over regularizing the objective to limiting the amount data used to protect privacy. Based on a precise description of the goals and applications of data augmentation (C1) and a taxonomy for existing works (C2), this survey is concerned with data augmentation methods for textual classification and aims to achieve a concise and comprehensive overview for researchers and practitioners (C3). Derived from the taxonomy, we divided more than 100 methods into 12 different groupings and provide state-of-the-art references expounding which methods are highly promising (C4). Finally, research perspectives that may constitute a building block for future work are given (C5).
Human doctors with well-structured medical knowledge can diagnose a disease merely via a few conversations with patients about symptoms. In contrast, existing knowledge-grounded dialogue systems often require a large number of dialogue instances to learn as they fail to capture the correlations between different diseases and neglect the diagnostic experience shared among them. To address this issue, we propose a more natural and practical paradigm, i.e., low-resource medical dialogue generation, which can transfer the diagnostic experience from source diseases to target ones with a handful of data for adaptation. It is capitalized on a commonsense knowledge graph to characterize the prior disease-symptom relations. Besides, we develop a Graph-Evolving Meta-Learning (GEML) framework that learns to evolve the commonsense graph for reasoning disease-symptom correlations in a new disease, which effectively alleviates the needs of a large number of dialogues. More importantly, by dynamically evolving disease-symptom graphs, GEML also well addresses the real-world challenges that the disease-symptom correlations of each disease may vary or evolve along with more diagnostic cases. Extensive experiment results on the CMDD dataset and our newly-collected Chunyu dataset testify the superiority of our approach over state-of-the-art approaches. Besides, our GEML can generate an enriched dialogue-sensitive knowledge graph in an online manner, which could benefit other tasks grounded on knowledge graph.
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