Recently, the source-free domain adaptation (SFDA) problem has attracted much attention, where the pre-trained model for the source domain is adapted to the target domain in the absence of source data. However, due to domain shift, the negative alignment usually exists between samples from the same class, which may lower intra-class feature similarity. To address this issue, we present a self-supervised representation learning strategy for SFDA, named as neighborhood-aware mutual information (NAMI), which maximizes the mutual information (MI) between the representations of target samples and their corresponding neighbors. Moreover, we theoretically demonstrate that NAMI can be decomposed into a weighted sum of local MI, which suggests that the weighted terms can better estimate NAMI. To this end, we introduce neighborhood consensus score over the set of weakly and strongly augmented views and point-wise density based on neighborhood, both of which determine the weights of local MI for NAMI by leveraging the neighborhood information of samples. The proposed method can significantly handle domain shift and adaptively reduce the noise in the neighborhood of each target sample. In combination with the consistency loss over views, NAMI leads to consistent improvement over existing state-of-the-art methods on three popular SFDA benchmarks.
13 February 2025 in IEEE Transactions on Instrumentation and Measurement
Surface defect recognition (SDR) with limited data is a common challenge in industrial production. Recent methods generally utilize generative adversarial networks (GANs) to generate defect samples as training data for improving the performance of SDR. However, the instability of GAN training often results in uncontrollable and low-quality samples under severe data constraints, making it difficult for the existing methods to effectively handle SDR tasks with different granularities. To address the issue, this article proposes a human-guided data augmentation method under extremely limited data. Its core idea is to introduce human feedback into a diffusion model for synthesizing controllable and high-quality defect samples by reinforcement learning (RL), aiming to improve various-granularity SDR tasks such as defect classification and segmentation. First, a conditional diffusion model (CDM) is constructed to generate controllable defect samples using semantic labels, which learn defect distribution from a small number of annotated defect samples. Then, a reward model is designed to evaluate the outcome of the CDM by human feedback. Next, based on the trained reward model, the CDM is further optimized by proximal policy optimization (PPO). Finally, the refined CDM is used to generate high-quality defect samples as training data for enhancing defect classification and segmentation. Extensive experiments on NEU-Seg, magnetic-tile (MT), and the collected Tire datasets demonstrate that our method outperforms the state-of-the-art generative methods in terms of generated image quality. Furthermore, the performance of defect classification and segmentation has also shown significant enhancements based on the generated samples, with a maximum improvement of 16.90% in accuracy and 12.85% in mean intersection over union (mIoU) compared to results obtained without data augmentation.
The Embodied AI is the current frontier direction in the field of AI and is regarded as a research leading to general artificial intelligence. Embodied AI refers to the study and development of artificial agents that can perceive, reason, and interact with the environment with the capabilities and limitations of a physical body. Object goal navigation is one of the fundamental problems in this field. This paper provides a simplified version of review on object goal navigation. In this paper, we review the definition, evaluation metrics, and recent research methods on this task. We analyze the advantages and disadvantages of various methods, and give potential directions that we think can be further studied in the future.
An embedded intelligent optimization scheme based on artificial fish model was proposed for the nonlinear, stochastic and modeless characteristics of complex systems. The artificial fish model can have cognitive ability which consisted of basic reaction layer and advanced intelligence layer, and it can adapt to the system environment and interact with its mates, then the individual embedded optimization scheme and the colony embedded optimization scheme came into being. The optimization scheme takes the benefit of swarm intelligence of bionic agents. The intelligent model can describe the modeless factors, and has no special requirement to the system model's property. Furthermore, the artificial fish model can combine with the modern and classical calculation methods to improve its behavior and decision ability. As a result, a powerful calculation system for complex system's optimizing and solving can be formed