Weichuan Zhang

Weiwei Wang, Meijia Wang, Haoyi Wang et al.

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.

Ziyue Kang, Weichuan Zhang

A major challenge in rare animal image classification is the scarcity of data, as many species usually have only a small number of labeled samples. To address this challenge, we designed a hybrid deep-learning framework comprising a novel adaptive DCT preprocessing module, ViT-B16 and ResNet50 backbones, and a Bayesian linear classification head. To our knowledge, we are the first to introduce an adaptive frequency-domain selection mechanism that learns optimal low-, mid-, and high-frequency boundaries suited to the subsequent backbones. Our network first captures image frequency-domain cues via this adaptive DCT partitioning. The adaptively filtered frequency features are then fed into ViT-B16 to model global contextual relationships, while ResNet50 concurrently extracts local, multi-scale spatial representations from the original image. A cross-level fusion strategy seamlessly integrates these frequency- and spatial-domain embeddings, and the fused features are passed through a Bayesian linear classifier to output the final category predictions. On our self-built 50-class wildlife dataset, this approach outperforms conventional CNN and fixed-band DCT pipelines, achieving state-of-the-art accuracy under extreme sample scarcity.