arXiv subjects

Meijia Wang

Publications and source records attributed to Meijia Wang.

6 recordsLinked to original sources

arXiv2026

Frequency-Enhanced Dual-Subspace Networks for Few-Shot Fine-Grained Image Classification

Few-shot fine-grained image classification aims to recognize subcategories with high visual similarity using only a limited number of annotated samples. Existing metric learning-based methods typically rely solely on spatial domain features. Confined to this single perspective, models inevitably suffer from inherent texture biases, entangling essential structural details with high-frequency background noise. Furthermore, lacking cross-view geometric constraints, single-view metrics tend to overfit this noise, resulting in structural instability under few-shot conditions. To address these issues, this paper proposes the Frequency-Enhanced Dual-Subspace Network (FEDSNet). Specifically, FEDSNet utilizes the Discrete Cosine Transform (DCT) and a low-pass filtering mechanism to explicitly isolate low-frequency global structural components from spatial features, thereby suppressing background interference. Truncated Singular Value Decomposition (SVD) is employed to construct independent, low-rank linear subspaces for both spatial texture and frequency structural features. An adaptive gating mechanism is designed to dynamically fuse the projection distances from these dual views. This strategy leverages the structural stability of the frequency subspace to prevent the spatial subspace from overfitting to background features. Extensive experiments on four benchmark datasets - CUB-200-2011, Stanford Cars, Stanford Dogs, and FGVC-Aircraft - demonstrate that FEDSNet exhibits excellent classification performance and robustness, achieving highly competitive results compared to existing metric learning algorithms. Complexity analysis further confirms that the proposed network achieves a favorable balance between high accuracy and computational efficiency, providing an effective new paradigm for few-shot fine-grained visual recognition.

cs.CV↗

arXiv2026

Brain-inspired AI for Edge Intelligence: a systematic review

While Spiking Neural Networks (SNNs) promise to circumvent the severe Size, Weight, and Power (SWaP) constraints of edge intelligence, the field currently faces a "Deployment Paradox" where theoretical energy gains are frequently negated by the inefficiencies of mapping asynchronous, event-driven dynamics onto traditional von Neumann substrates. Transcending the reductionism of algorithm-only reviews, this survey adopts a rigorous system-level hardware-software co-design perspective to examine the 2020-2025 trajectory, specifically targeting the "last mile" technologies - from quantization methodologies to hybrid architectures - that translate biological plausibility into silicon reality. We critically dissect the interplay between training complexity (the dichotomy of direct learning vs. conversion), the "memory wall" bottlenecking stateful neuronal updates, and the critical software gap in neuromorphic compilation toolchains. Finally, we envision a roadmap to reconcile the fundamental "Sync-Async Mismatch," proposing the development of a standardized Neuromorphic OS as the foundational layer for realizing a ubiquitous, energy-autonomous Green Cognitive Substrate.

cs.NE↗

arXiv2025

Feature Complementation Architecture for Visual Place Recognition

Visual place recognition (VPR) plays a crucial role in robotic localization and navigation. The key challenge lies in constructing feature representations that are robust to environmental changes. Existing methods typically adopt convolutional neural networks (CNNs) or vision Transformers (ViTs) as feature extractors. However, these architectures excel in different aspects -- CNNs are effective at capturing local details. At the same time, ViTs are better suited for modeling global context, making it difficult to leverage the strengths of both. To address this issue, we propose a local-global feature complementation network (LGCN) for VPR which integrates a parallel CNN-ViT hybrid architecture with a dynamic feature fusion module (DFM). The DFM performs dynamic feature fusion through joint modeling of spatial and channel-wise dependencies. Furthermore, to enhance the expressiveness and adaptability of the ViT branch for VPR tasks, we introduce lightweight frequency-to-spatial fusion adapters into the frozen ViT backbone. These adapters enable task-specific adaptation with controlled parameter overhead. Extensive experiments on multiple VPR benchmark datasets demonstrate that the proposed LGCN consistently outperforms existing approaches in terms of localization accuracy and robustness, validating its effectiveness and generalizability.

cs.CV↗

arXiv2024

Modified BART for Learning Heterogeneous Effects in Regression Discontinuity Designs

This paper introduces BART-RDD, a sum-of-trees regression model built around a novel regression tree prior, which incorporates the special covariate structure of regression discontinuity designs. Specifically, the tree splitting process is constrained to ensure overlap within a narrow band surrounding the running variable cutoff value, where the treatment effect is identified. It is shown that unmodified BART-based models estimate RDD treatment effects poorly, while our modified model accurately recovers treatment effects at the cutoff. Specifically, BART-RDD is perhaps the first RDD method that effectively learns conditional average treatment effects. The new method is investigated in thorough simulation studies as well as an empirical application looking at the effect of academic probation on student performance in subsequent terms (Lindo et al., 2010).

stat.ME↗

arXiv2024

LongBet: Heterogeneous Treatment Effect Estimation in Panel Data

This paper introduces a novel approach for estimating heterogeneous treatment effects of binary treatment in panel data, particularly focusing on short panel data with large cross-sectional data and observed confoundings. In contrast to traditional literature in difference-in-differences method that often relies on the parallel trend assumption, our proposed model does not necessitate such an assumption. Instead, it leverages observed confoundings to impute potential outcomes and identify treatment effects. The method presented is a Bayesian semi-parametric approach based on the Bayesian causal forest model, which is extended here to suit panel data settings. The approach offers the advantage of the Bayesian approach to provides uncertainty quantification on the estimates. Simulation studies demonstrate its performance with and without the presence of parallel trend. Additionally, our proposed model enables the estimation of conditional average treatment effects, a capability that is rarely available in panel data settings.

stat.ME↗

arXiv2018

AURORA: Auditing PageRank on Large Graphs

Ranking on large-scale graphs plays a fundamental role in many high-impact application domains, ranging from information retrieval, recommender systems, sports team management, biology to neuroscience and many more. PageRank, together with many of its random walk based variants, has become one of the most well-known and widely used algorithms, due to its mathematical elegance and the superior performance across a variety of application domains. Important as it might be, state-of-the-art lacks an intuitive way to explain the ranking results by PageRank (or its variants), e.g., why it thinks the returned top-k webpages are most important ones in the entire graph; why it gives a higher rank to actor John than actor Smith in terms of their relevance w.r.t. a particular movie? In order to answer these questions, this paper proposes a paradigm shift for PageRank, from identifying which nodes are most important to understanding why the ranking algorithm gives a particular ranking result. We formally define the PageRank auditing problem, whose central idea is to identify a set of key graph elements (e.g., edges, nodes, subgraphs) with the highest influence on the ranking results. We formulate it as an optimization problem and propose a family of effective and scalable algorithms (AURORA) to solve it. Our algorithms measure the influence of graph elements and incrementally select influential elements w.r.t. their gradients over the ranking results. We perform extensive empirical evaluations on real-world datasets, which demonstrate that the proposed methods (AURORA) provide intuitive explanations with a linear scalability.

cs.SI↗