# Frequency-Adaptive Discrete Cosine-ViT-ResNet Architecture for Sparse-Data Vision

arXiv: https://arxiv.org/abs/2505.22701 · HTML: https://mlsanity.com/paper/2505.22701/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 18 of its 32 references that are in the map.
- First posted on arXiv 28 May 2025.

## Builds on (most cited first, 18 of 18)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [CBAM: Convolutional Block Attention Module](https://mlsanity.com/paper/1807.06521/) (2018)
- [A Comprehensive Survey on Transfer Learning](https://mlsanity.com/paper/1911.02685/) (2019)
- [Recognition in Terra Incognita](https://mlsanity.com/paper/1807.04975/) (2018)
- [Global Filter Networks for Image Classification](https://mlsanity.com/paper/2107.00645/) (2021)
- [Learning in the Frequency Domain](https://mlsanity.com/paper/2002.12416/) (2020)
- [BioCLIP: A Vision Foundation Model for the Tree of Life](https://mlsanity.com/paper/2311.18803/) (2023)
- [Efficient Pipeline for Camera Trap Image Review](https://mlsanity.com/paper/1907.06772/) (2019)
- [Towards Automatic Wild Animal Monitoring: Identification of Animal Species in Camera-trap Images using Very Deep Convolutional Neural Networks](https://mlsanity.com/paper/1603.06169/) (2016)
- [Bag of Tricks for Long-Tail Visual Recognition of Animal Species in Camera-Trap Images](https://mlsanity.com/paper/2206.12458/) (2022)
- [Discrete Cosine Transform Based Decorrelated Attention for Vision Transformers](https://mlsanity.com/paper/2405.13901/) (2024)
- [Feature-Aware Noise Contrastive Learning for Unsupervised Red Panda Re-Identification](https://mlsanity.com/paper/2405.00468/) (2024)
- [DCT-HistoTransformer: Efficient Lightweight Vision Transformer with DCT Integration for histopathological image analysis](https://mlsanity.com/paper/2410.19166/) (2024)
- [Spatial and Frequency Domain Adaptive Fusion Network for Image Deblurring](https://mlsanity.com/paper/2502.14209/) (2025)

## Abstract (arXiv)

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.