针对稀疏动物图像数据，设计自适应频域过滤网络提升分类精度。
Frequency-Adaptive Discrete Cosine-ViT-ResNet Architecture for Sparse-Data Vision
- 引入自适应频域分割机制，动态选择适合模型的低中高频边界。
- 在50类野生动物数据集上实现极端样本稀缺下的最优分类准确率。
- 适合小样本、频域特征敏感的视觉任务，如濒危物种识别。
稀有动物图像分类面临数据稀缺难题，许多物种仅拥有少量标注样本。为此，我们设计了一种混合深度学习框架，包含新型自适应DCT预处理模块、ViT-B16与ResNet50主干网络，以及贝叶斯线性分类头。据我们所知，首次提出自适应频率域选择机制，可学习适配后续主干网络的低、中、高频边界。网络首先通过自适应DCT划分捕获图像频域特征，将滤波后的频率特征输入ViT-B16以建模全局上下文关系，同时ResNet50从原始图像中并行提取局部多尺度空间表征。采用跨层级融合策略整合频域与空间域嵌入，融合特征经贝叶斯线性分类器输出最终类别预测。在自建的50类野生动物数据集上，该方法优于传统CNN和固定频段DCT流程，在极端样本稀缺条件下达到当前最优准确率。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。