Search for: All records

Source-free domain adaptation (SFDA) aims to transfer knowledge from the well-trained source model and optimize it to adapt target data distribution. SFDA methods are suitable for medical image segmentation task due to its data-privacy protection and achieve promising performances. However, cross-domain distribution shift makes it difficult for the adapted model to provide accurate decisions on several hard instances and negatively affects model generalization. To overcome this limitation, a novel method `supportive negatives spectral augmentation' (SNSA) is presented in this work. Concretely, SNSA includes the instance selection mechanism to automatically discover a few hard samples for which source model produces incorrect predictions. And, active learning strategy is adopted to re-calibrate their predictive masks. Moreover, SNSA deploys the spectral augmentation between hard instances and others to encourage source model to gradually capture and adapt the attributions of target distribution. Considerable experimental studies demonstrate that annotating merely 4%~5% of negative instances from the target domain significantly improves segmentation performance over previous methods. 

Abstract Wave‐particle duality, intertwining two inherently contradictory properties of quantum systems, remains one of the most conceptually profound aspects of quantum mechanics. By using the concept of energy capacity, the ability of a quantum system to store and extract energy, a device‐independent uncertainty relation is derived for wave‐particle duality. This relation is shown to be independent of both the representation space and the measurement basis of the quantum system. Furthermore, it is experimentally validated that this wave‐particle duality relation using a photon‐based platform. 

Applications of multimodal neuroimaging techniques, including electroencephalography (EEG) and functional near-infrared spectroscopy (fNIRS) have gained prominence in recent years, and they are widely practiced in brain–computer interface (BCI) and neuro-pathological diagnosis applications. Most existing approaches assume observations are independent and identically distributed (i.i.d.), as shown in the top section of the right figure, yet ignore the difference among subjects. It has been challenging to model subject groups to maintain topological information (e.g., patient graphs) while fusing BCI signals for discriminant feature learning. In this article, we introduce a topology-aware graph-based multimodal fusion (TaGMF) framework to classify amyotrophic lateral sclerosis (ALS) and healthy subjects, illustrated in the lower section of the right image. Our framework is built on graph neural networks (GNNs) but with two unique contributions. First, a novel topology-aware graph (TaG) is proposed to model subject groups by considering: 1) intersubject; 2) intrasubject; and 3) intergroup relations. Second, the learned representation of EEG and fNIRS signals of each subject allows for explorations of different fusion strategies along with the TaGMF optimizations. Our analysis demonstrates the effectiveness of our graph-based fusion approach in multimodal classification by achieving a 22.6% performance improvement over classical approaches. 

Emerging wearable devices would benefit from integrating ductile photovoltaic light-harvesting power sources. In this work, we report a small-molecule acceptor (SMA), also known as a non–fullerene acceptor (NFA), designed for stretchable organic solar cell (s-OSC) blends with large mechanical compliance and performance. Blends of the organosilane-functionalized SMA BTP-Si4 with the polymer donor PNTB6-Cl achieved a power conversion efficiency (PCE) of >16% and ultimate strain (ε_u) of >95%. Typical SMAs suppress OSC blend ductility, but the addition of BTP-Si4 enhances it. Although BTP-Si4 is less crystalline than other SMAs, it retains considerable electron mobility and is highly miscible with PNTB6-Cl and is essential for enhancing ε_u. Thus,s-OSCs with PCE > 14% and operating normally under various deformations (>80% PCE retention under an 80% strain) were demonstrated. Analysis of several SMA-polymer blends revealed general molecular structure–miscibility–stretchability relationships for designing ductile blends.