# Fine-Grained Scene Image Classification with Modality-Agnostic Adapter

arXiv: https://arxiv.org/abs/2407.02769 · HTML: https://mlsanity.com/paper/2407.02769/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 37 references that are in the map.
- First posted on arXiv 3 Jul 2024.

## Builds on (most cited first, 22 of 22)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [Efficient Estimation of Word Representations in Vector Space](https://mlsanity.com/paper/1301.3781/) (2013)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [Enriching Word Vectors with Subword Information](https://mlsanity.com/paper/1607.04606/) (2016)
- [Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering](https://mlsanity.com/paper/1707.07998/) (2017)
- [ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision](https://mlsanity.com/paper/2102.03334/) (2021)
- [Multi-modal Transformer for Video Retrieval](https://mlsanity.com/paper/2007.10639/) (2020)
- [Knowledge Enhanced Contextual Word Representations](https://mlsanity.com/paper/1909.04164/) (2019)
- [Use What You Have: Video Retrieval Using Representations From Collaborative Experts](https://mlsanity.com/paper/1907.13487/) (2019)
- [Uni-Perceiver: Pre-training Unified Architecture for Generic Perception for Zero-shot and Few-shot Tasks](https://mlsanity.com/paper/2112.01522/) (2021)
- [E2E-VLP: End-to-End Vision-Language Pre-training Enhanced by Visual Learning](https://mlsanity.com/paper/2106.01804/) (2021)
- [DeepSolo: Let Transformer Decoder with Explicit Points Solo for Text Spotting](https://mlsanity.com/paper/2211.10772/) (2022)
- [CNN: Single-label to Multi-label](https://mlsanity.com/paper/1406.5726/) (2014)
- [E2E-MLT - an Unconstrained End-to-End Method for Multi-Language Scene Text](https://mlsanity.com/paper/1801.09919/) (2018)
- [Multi-Modal Reasoning Graph for Scene-Text Based Fine-Grained Image Classification and Retrieval](https://mlsanity.com/paper/2009.09809/) (2020)
- [Knowledge Mining with Scene Text for Fine-Grained Recognition](https://mlsanity.com/paper/2203.14215/) (2022)
- [Integrating Scene Text and Visual Appearance for Fine-Grained Image Classification](https://mlsanity.com/paper/1704.04613/) (2017)
- [Fine-grained Image Classification and Retrieval by Combining Visual and Locally Pooled Textual Features](https://mlsanity.com/paper/2001.04732/) (2020)

## Abstract (arXiv)

When dealing with the task of fine-grained scene image classification, most previous works lay much emphasis on global visual features when doing multi-modal feature fusion. In other words, models are deliberately designed based on prior intuitions about the importance of different modalities. In this paper, we present a new multi-modal feature fusion approach named MAA (Modality-Agnostic Adapter), trying to make the model learn the importance of different modalities in different cases adaptively, without giving a prior setting in the model architecture. More specifically, we eliminate the modal differences in distribution and then use a modality-agnostic Transformer encoder for a semantic-level feature fusion. Our experiments demonstrate that MAA achieves state-of-the-art results on benchmarks by applying the same modalities with previous methods. Besides, it is worth mentioning that new modalities can be easily added when using MAA and further boost the performance. Code is available at https://github.com/quniLcs/MAA.