# Dynamic MLP for Fine-Grained Image Classification by Leveraging Geographical and Temporal Information

arXiv: https://arxiv.org/abs/2203.03253 · HTML: https://mlsanity.com/paper/2203.03253/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Builds on 42 of its 53 references that are in the map.
- First posted on arXiv 7 Mar 2022.

## Builds on (most cited first, 30 of 42)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Aggregated Residual Transformations for Deep Neural Networks](https://mlsanity.com/paper/1611.05431/) (2016)
- [Learning Deep Features for Discriminative Localization](https://mlsanity.com/paper/1512.04150/) (2015)
- [FiLM: Visual Reasoning with a General Conditioning Layer](https://mlsanity.com/paper/1709.07871/) (2017)
- [HyperNetworks](https://mlsanity.com/paper/1609.09106/) (2016)
- [Sparse R-CNN: End-to-End Object Detection with Learnable Proposals](https://mlsanity.com/paper/2011.12450/) (2020)
- [Res2Net: A New Multi-scale Backbone Architecture](https://mlsanity.com/paper/1904.01169/) (2019)
- [Selective Kernel Networks](https://mlsanity.com/paper/1903.06586/) (2019)
- [Multi-Modal Fusion Transformer for End-to-End Autonomous Driving](https://mlsanity.com/paper/2104.09224/) (2021)
- [Dynamic Convolution: Attention over Convolution Kernels](https://mlsanity.com/paper/1912.03458/) (2019)
- [Dynamic Filter Networks](https://mlsanity.com/paper/1605.09673/) (2016)
- [Conditional Convolutions for Instance Segmentation](https://mlsanity.com/paper/2003.05664/) (2020)
- [Stacked Attention Networks for Image Question Answering](https://mlsanity.com/paper/1511.02274/) (2015)
- [CondConv: Conditionally Parameterized Convolutions for Efficient Inference](https://mlsanity.com/paper/1904.04971/) (2019)
- [YFCC100M: The New Data in Multimedia Research](https://mlsanity.com/paper/1503.01817/) (2015)
- [Fixing the train-test resolution discrepancy](https://mlsanity.com/paper/1906.06423/) (2019)
- [MXNet: A Flexible and Efficient Machine Learning Library for Heterogeneous Distributed Systems](https://mlsanity.com/paper/1512.01274/) (2015)
- [Large Scale Fine-Grained Categorization and Domain-Specific Transfer Learning](https://mlsanity.com/paper/1806.06193/) (2018)
- [Benchmarking Representation Learning for Natural World Image Collections](https://mlsanity.com/paper/2103.16483/) (2021)
- [Evaluation of Output Embeddings for Fine-Grained Image Classification](https://mlsanity.com/paper/1409.8403/) (2014)
- [TransFG: A Transformer Architecture for Fine-grained Recognition](https://mlsanity.com/paper/2103.07976/) (2021)
- [Part-based R-CNNs for Fine-grained Category Detection](https://mlsanity.com/paper/1407.3867/) (2014)
- [Presence-Only Geographical Priors for Fine-Grained Image Classification](https://mlsanity.com/paper/1906.05272/) (2019)
- [Learning to Navigate for Fine-grained Classification](https://mlsanity.com/paper/1809.00287/) (2018)
- [Multi-Scale Representation Learning for Spatial Feature Distributions using Grid Cells](https://mlsanity.com/paper/2003.00824/) (2020)
- [Dynamic Multimodal Instance Segmentation guided by natural language queries](https://mlsanity.com/paper/1807.02257/) (2018)
- [The Application of Two-level Attention Models in Deep Convolutional Neural Network for Fine-grained Image Classification](https://mlsanity.com/paper/1411.6447/) (2014)
- [The Devil is in the Channels: Mutual-Channel Loss for Fine-Grained Image Classification](https://mlsanity.com/paper/2002.04264/) (2020)

## Built on by (most cited first, 15 of 15)

- [CSP: Self-Supervised Contrastive Spatial Pre-Training for Geospatial-Visual Representations](https://mlsanity.com/paper/2305.01118/) (2023)
- [HazyDet: Open-Source Benchmark for Drone-View Object Detection with Depth-Cues in Hazy Scenes](https://mlsanity.com/paper/2409.19833/) (2024)
- [MapFormer: Boosting Change Detection by Using Pre-change Information](https://mlsanity.com/paper/2303.17859/) (2023)
- [Fine-Grained Visual Classification using Self Assessment Classifier](https://mlsanity.com/paper/2205.10529/) (2022)
- [InsertNeRF: Instilling Generalizability into NeRF with HyperNet Modules](https://mlsanity.com/paper/2308.13897/) (2023)
- [LocDiff: Identifying Locations on Earth by Diffusing in the Hilbert Space](https://mlsanity.com/paper/2503.18142/) (2025)
- [Fusion Meets Diverse Conditions: A High-diversity Benchmark and Baseline for UAV-based Multimodal Object Detection with Condition Cues](https://mlsanity.com/paper/2510.13620/) (2025)
- [AuxDet: Auxiliary Metadata Matters for Omni-Domain Infrared Small Target Detection](https://mlsanity.com/paper/2505.15184/) (2025)
- [ExpNet: A unified network for Expert-Level Classification](https://mlsanity.com/paper/2211.15672/) (2022)
- [Cross-Level Multi-Instance Distillation for Self-Supervised Fine-Grained Visual Categorization](https://mlsanity.com/paper/2401.08860/) (2024)
- [MoCoLSK: Modality Conditioned High-Resolution Downscaling for Land Surface Temperature](https://mlsanity.com/paper/2409.19835/) (2024)
- [ZooplanktonBench: A Geo-Aware Zooplankton Recognition and Classification Dataset from Marine Observations](https://mlsanity.com/paper/2505.18477/) (2025)
- [Investigating Different Geo Priors for Image Classification](https://mlsanity.com/paper/2508.15946/) (2025)
- [Attention Is not Everything: Efficient Alternatives for Vision](https://mlsanity.com/paper/2604.17439/) (2026)
- [Spatial-Temporal Expert Learning for Video-based Person Re-identification](https://mlsanity.com/paper/2607.01353/) (2026)

## Abstract (arXiv)

Fine-grained image classification is a challenging computer vision task where various species share similar visual appearances, resulting in misclassification if merely based on visual clues. Therefore, it is helpful to leverage additional information, e.g., the locations and dates for data shooting, which can be easily accessible but rarely exploited. In this paper, we first demonstrate that existing multimodal methods fuse multiple features only on a single dimension, which essentially has insufficient help in feature discrimination. To fully explore the potential of multimodal information, we propose a dynamic MLP on top of the image representation, which interacts with multimodal features at a higher and broader dimension. The dynamic MLP is an efficient structure parameterized by the learned embeddings of variable locations and dates. It can be regarded as an adaptive nonlinear projection for generating more discriminative image representations in visual tasks. To our best knowledge, it is the first attempt to explore the idea of dynamic networks to exploit multimodal information in fine-grained image classification tasks. Extensive experiments demonstrate the effectiveness of our method. The t-SNE algorithm visually indicates that our technique improves the recognizability of image representations that are visually similar but with different categories. Furthermore, among published works across multiple fine-grained datasets, dynamic MLP consistently achieves SOTA results https://paperswithcode.com/dataset/inaturalist and takes third place in the iNaturalist challenge at FGVC8 https://www.kaggle.com/c/inaturalist-2021/leaderboard. Code is available at https://github.com/ylingfeng/DynamicMLP.git