# Bilinear CNNs for Fine-grained Visual Recognition

arXiv: https://arxiv.org/abs/1504.07889 · HTML: https://mlsanity.com/paper/1504.07889/

## Key facts

- Cited by 228 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Apr 2015.

## Built on by (most cited first, 30 of 228)

- [Fine-Grained Image Analysis with Deep Learning: A Survey](https://mlsanity.com/paper/2111.06119/) (2021)
- [Deformable ProtoPNet: An Interpretable Image Classifier Using Deformable Prototypes](https://mlsanity.com/paper/2111.15000/) (2021)
- [METransformer: Radiology Report Generation by Transformer with Multiple Learnable Expert Tokens](https://mlsanity.com/paper/2304.02211/) (2023)
- [Changer: Feature Interaction is What You Need for Change Detection](https://mlsanity.com/paper/2209.08290/) (2022)
- [Natural Language Understanding and Inference with MLLM in Visual Question Answering: A Survey](https://mlsanity.com/paper/2411.17558/) (2024)
- [Differentiable Patch Selection for Image Recognition](https://mlsanity.com/paper/2104.03059/) (2021)
- [Unsupervised Part Discovery from Contrastive Reconstruction](https://mlsanity.com/paper/2111.06349/) (2021)
- [PnP-DETR: Towards Efficient Visual Analysis with Transformers](https://mlsanity.com/paper/2109.07036/) (2021)
- [A Medical Semantic-Assisted Transformer for Radiographic Report Generation](https://mlsanity.com/paper/2208.10358/) (2022)
- [VSR: A Unified Framework for Document Layout Analysis combining Vision, Semantics and Relations](https://mlsanity.com/paper/2105.06220/) (2021)
- [Learning Support and Trivial Prototypes for Interpretable Image Classification](https://mlsanity.com/paper/2301.04011/) (2023)
- [Visual Attention Methods in Deep Learning: An In-Depth Survey](https://mlsanity.com/paper/2204.07756/) (2022)
- [Continual Learning for Blind Image Quality Assessment](https://mlsanity.com/paper/2102.09717/) (2021)
- [DualVGR: A Dual-Visual Graph Reasoning Unit for Video Question Answering](https://mlsanity.com/paper/2107.04768/) (2021)
- [RAMS-Trans: Recurrent Attention Multi-scale Transformer forFine-grained Image Recognition](https://mlsanity.com/paper/2107.08192/) (2021)
- [Webly Supervised Fine-Grained Recognition: Benchmark Datasets and An Approach](https://mlsanity.com/paper/2108.02399/) (2021)
- [Boosting Few-shot Fine-grained Recognition with Background Suppression and Foreground Alignment](https://mlsanity.com/paper/2210.01439/) (2022)
- [MetaFormer: A Unified Meta Framework for Fine-Grained Recognition](https://mlsanity.com/paper/2203.02751/) (2022)
- [Bilinear MLPs enable weight-based mechanistic interpretability](https://mlsanity.com/paper/2410.08417/) (2024)
- [Danish Fungi 2020 -- Not Just Another Image Recognition Dataset](https://mlsanity.com/paper/2103.10107/) (2021)
- [Few-shot Keypoint Detection with Uncertainty Learning for Unseen Species](https://mlsanity.com/paper/2112.06183/) (2021)
- [Continual Learning with Bayesian Model based on a Fixed Pre-trained Feature Extractor](https://mlsanity.com/paper/2204.13349/) (2022)
- [Teacher-Student Architecture for Knowledge Distillation: A Survey](https://mlsanity.com/paper/2308.04268/) (2023)
- [Democratizing Fine-grained Visual Recognition with Large Language Models](https://mlsanity.com/paper/2401.13837/) (2024)
- [Why Approximate Matrix Square Root Outperforms Accurate SVD in Global Covariance Pooling?](https://mlsanity.com/paper/2105.02498/) (2021)
- [CMW-Net: Learning a Class-Aware Sample Weighting Mapping for Robust Deep Learning](https://mlsanity.com/paper/2202.05613/) (2022)
- [Fine-Grained Object Classification via Self-Supervised Pose Alignment](https://mlsanity.com/paper/2203.15987/) (2022)
- [Object Detection with Transformers: A Review](https://mlsanity.com/paper/2306.04670/) (2023)
- [Domain Generalization via Frequency-domain-based Feature Disentanglement and Interaction](https://mlsanity.com/paper/2201.08029/) (2022)
- [Robust Differentiable SVD](https://mlsanity.com/paper/2104.03821/) (2021)

## Abstract (arXiv)

We present a simple and effective architecture for fine-grained visual recognition called Bilinear Convolutional Neural Networks (B-CNNs). These networks represent an image as a pooled outer product of features derived from two CNNs and capture localized feature interactions in a translationally invariant manner. B-CNNs belong to the class of orderless texture representations but unlike prior work they can be trained in an end-to-end manner. Our most accurate model obtains 84.1%, 79.4%, 86.9% and 91.3% per-image accuracy on the Caltech-UCSD birds [67], NABirds [64], FGVC aircraft [42], and Stanford cars [33] dataset respectively and runs at 30 frames-per-second on a NVIDIA Titan X GPU. We then present a systematic analysis of these networks and show that (1) the bilinear features are highly redundant and can be reduced by an order of magnitude in size without significant loss in accuracy, (2) are also effective for other image classification tasks such as texture and scene recognition, and (3) can be trained from scratch on the ImageNet dataset offering consistent improvements over the baseline architecture. Finally, we present visualizations of these models on various datasets using top activations of neural units and gradient-based inversion techniques. The source code for the complete system is available at http://vis-www.cs.umass.edu/bcnn.