Lei Tian

Xuechen Zhao, Jiaying Zou, Zhong Zhang et al.

Zero-shot stance detection is challenging because it requires detecting the stance of previously unseen targets in the inference phase. The ability to learn transferable target-invariant features is critical for zero-shot stance detection. In this work, we propose a stance detection approach that can efficiently adapt to unseen targets, the core of which is to capture target-invariant syntactic expression patterns as transferable knowledge. Specifically, we first augment the data by masking the topic words of sentences, and then feed the augmented data to an unsupervised contrastive learning module to capture transferable features. Then, to fit a specific target, we encode the raw texts as target-specific features. Finally, we adopt an attention mechanism, which combines syntactic expression patterns with target-specific features to obtain enhanced features for predicting previously unseen targets. Experiments demonstrate that our model outperforms competitive baselines on four benchmark datasets.

Lei Tian, Yongqiang Tang, Liangchen Hu et al.

Domain adaptation manages to transfer the knowledge of well-labeled source data to unlabeled target data. Many recent efforts focus on improving the prediction accuracy of target pseudo-labels to reduce conditional distribution shift. In this paper, we propose a novel domain adaptation method, which infers target pseudo-labels through cross-domain label propagation, such that the underlying manifold structure of two domain data can be explored. Unlike existing cross-domain label propagation methods that separate domain-invariant feature learning, affinity matrix constructing and target labels inferring into three independent stages, we propose to integrate them into a unified optimization framework. In such way, these three parts can boost each other from an iterative optimization perspective and thus more effective knowledge transfer can be achieved. Furthermore, to construct a high-quality affinity matrix, we propose a discriminative graph self-learning strategy, which can not only adaptively capture the inherent similarity of the data from two domains but also effectively exploit the discriminative information contained in well-labeled source data and pseudo-labeled target data. An efficient iterative optimization algorithm is designed to solve the objective function of our proposal. Notably, the proposed method can be extended to semi-supervised domain adaptation in a simple but effective way and the corresponding optimization problem can be solved with the identical algorithm. Extensive experiments on six standard datasets verify the significant superiority of our proposal in both unsupervised and semi-supervised domain adaptation settings.

Yuanhang Li, Qi Mao, Lan Chen et al.

Recent advances in text-to-video (T2V) generation with diffusion models have garnered significant attention. However, they typically perform well in scenes with a single object and motion, struggling in compositional scenarios with multiple objects and distinct motions to accurately reflect the semantic content of text prompts. To address these challenges, we propose \textbf{StarVid}, a plug-and-play, training-free method that improves semantic alignment between multiple subjects, their motions, and text prompts in T2V models. StarVid first leverages the spatial reasoning capabilities of large language models (LLMs) for two-stage motion trajectory planning based on text prompts. Such trajectories serve as spatial priors, guiding a spatial-aware loss to refocus cross-attention (CA) maps into distinctive regions. Furthermore, we propose a syntax-guided contrastive constraint to strengthen the correlation between the CA maps of verbs and their corresponding nouns, enhancing motion-subject binding. Both qualitative and quantitative evaluations demonstrate that the proposed framework significantly outperforms baseline methods, delivering videos of higher quality with improved semantic consistency.

Renhao Liu, Yu Sun, Jiabei Zhu et al.

Intensity diffraction tomography (IDT) refers to a class of optical microscopy techniques for imaging the 3D refractive index (RI) distribution of a sample from a set of 2D intensity-only measurements. The reconstruction of artifact-free RI maps is a fundamental challenge in IDT due to the loss of phase information and the missing cone problem. Neural fields (NF) has recently emerged as a new deep learning (DL) approach for learning continuous representations of physical fields. NF uses a coordinate-based neural network to represent the field by mapping the spatial coordinates to the corresponding physical quantities, in our case the complex-valued refractive index values. We present DeCAF as the first NF-based IDT method that can learn a high-quality continuous representation of a RI volume from its intensity-only and limited-angle measurements. The representation in DeCAF is learned directly from the measurements of the test sample by using the IDT forward model, without any ground-truth RI maps. We qualitatively and quantitatively evaluate DeCAF on the simulated and experimental biological samples. Our results show that DeCAF can generate high-contrast and artifact-free RI maps and lead to up to 2.1 times reduction in MSE over existing methods.

Alex Matlock, Lei Tian

Recovering 3D phase features of complex, multiple-scattering biological samples traditionally sacrifices computational efficiency and processing time for physical model accuracy and reconstruction quality. This trade-off hinders the rapid analysis of living, dynamic biological samples that are often of greatest interest to biological research. Here, we overcome this bottleneck by combining annular intensity diffraction tomography (aIDT) with an approximant-guided deep learning framework. Using a novel physics model simulator-based learning strategy trained entirely on natural image datasets, we show our network can robustly reconstruct complex 3D biological samples of arbitrary size and structure. This approach highlights that large-scale multiple-scattering models can be leveraged in place of acquiring experimental datasets for achieving highly generalizable deep learning models. We devise a new model-based data normalization pre-processing procedure for homogenizing the sample contrast and achieving uniform prediction quality regardless of scattering strength. To achieve highly efficient training and prediction, we implement a lightweight 2D network structure that utilizes a multi-channel input for encoding the axial information. We demonstrate this framework's capabilities on experimental measurements of epithelial buccal cells and Caenorhabditis elegans worms. We highlight the robustness of this approach by evaluating dynamic samples on a living worm video, and we emphasize our approach's generalizability by recovering algae samples evaluated with different experimental setups. To assess the prediction quality, we develop a novel quantitative evaluation metric and show that our predictions are consistent with our experimental measurements and multiple-scattering physics.

Yu Sun, Shiqi Xu, Yunzhe Li et al.

The plug-and-play priors (PnP) framework has been recently shown to achieve state-of-the-art results in regularized image reconstruction by leveraging a sophisticated denoiser within an iterative algorithm. In this paper, we propose a new online PnP algorithm for Fourier ptychographic microscopy (FPM) based on the fast iterative shrinkage/threshold algorithm (FISTA). Specifically, the proposed algorithm uses only a subset of measurements, which makes it scalable to a large set of measurements. We validate the algorithm by showing that it can lead to significant performance gains on both simulated and experimental data.

Zihao Wang, Leonidas Spinoulas, Kuan He et al.

Compressed sensing has been discussed separately in spatial and temporal domains. Compressive holography has been introduced as a method that allows 3D tomographic reconstruction at different depths from a single 2D image. Coded exposure is a temporal compressed sensing method for high speed video acquisition. In this work, we combine compressive holography and coded exposure techniques and extend the discussion to 4D reconstruction in space and time from one coded captured image. In our prototype, digital in-line holography was used for imaging macroscopic, fast moving objects. The pixel-wise temporal modulation was implemented by a digital micromirror device. In this paper we demonstrate $10\times$ temporal super resolution with multiple depths recovery from a single image. Two examples are presented for the purpose of recording subtle vibrations and tracking small particles within 5 ms.

Li-Hao Yeh, Lei Tian, Laura Waller

Structured illumination microscopy (SIM) improves resolution by down-modulating high-frequency information of an object to fit within the passband of the optical system. Generally, the reconstruction process requires prior knowledge of the illumination patterns, which implies a well-calibrated and aberration-free system. Here, we propose a new \textit{algorithmic self-calibration} strategy for SIM that does not need to know the exact patterns {\it a priori}, but only their covariance. The algorithm, termed PE-SIMS, includes a Pattern-Estimation (PE) step requiring the uniformity of the sum of the illumination patterns and a SIM reconstruction procedure using a Statistical prior (SIMS). Additionally, we perform a pixel reassignment process (SIMS-PR) to enhance the reconstruction quality. We achieve 2$\times$ better resolution than a conventional widefield microscope, while remaining insensitive to aberration-induced pattern distortion and robust against parameter tuning.