# Making a Bird AI Expert Work for You and Me

arXiv: https://arxiv.org/abs/2112.02747 · HTML: https://mlsanity.com/paper/2112.02747/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 50 of its 96 references that are in the map.
- First posted on arXiv 6 Dec 2021.

## Builds on (most cited first, 30 of 50)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Fine-Grained Visual Classification of Aircraft](https://mlsanity.com/paper/1306.5151/) (2013)
- [SmoothGrad: removing noise by adding noise](https://mlsanity.com/paper/1706.03825/) (2017)
- [When Does Label Smoothing Help?](https://mlsanity.com/paper/1906.02629/) (2019)
- [This Looks Like That: Deep Learning for Interpretable Image Recognition](https://mlsanity.com/paper/1806.10574/) (2018)
- [Transformer Interpretability Beyond Attention Visualization](https://mlsanity.com/paper/2012.09838/) (2020)
- [Interpretable Explanations of Black Boxes by Meaningful Perturbation](https://mlsanity.com/paper/1704.03296/) (2017)
- [Counterfactual Visual Explanations](https://mlsanity.com/paper/1904.07451/) (2019)
- [Bilinear CNNs for Fine-grained Visual Recognition](https://mlsanity.com/paper/1504.07889/) (2015)
- [Neural Prototype Trees for Interpretable Fine-grained Image Recognition](https://mlsanity.com/paper/2012.02046/) (2020)
- [Learning Deep Representations of Fine-grained Visual Descriptions](https://mlsanity.com/paper/1605.05395/) (2016)
- [Explaining Image Classifiers by Counterfactual Generation](https://mlsanity.com/paper/1807.08024/) (2018)
- [Fine-Grained Image Analysis with Deep Learning: A Survey](https://mlsanity.com/paper/2111.06119/) (2021)
- [TransFG: A Transformer Architecture for Fine-grained Recognition](https://mlsanity.com/paper/2103.07976/) (2021)
- [Attention-based Dropout Layer for Weakly Supervised Object Localization](https://mlsanity.com/paper/1908.10028/) (2019)
- [TS-CAM: Token Semantic Coupled Attention Map for Weakly Supervised Object Localization](https://mlsanity.com/paper/2103.14862/) (2021)
- [HashNet: Deep Learning to Hash by Continuation](https://mlsanity.com/paper/1702.00758/) (2017)
- [Rethinking Soft Labels for Knowledge Distillation: A Bias-Variance Tradeoff Perspective](https://mlsanity.com/paper/2102.00650/) (2021)
- [Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identification](https://mlsanity.com/paper/2108.08728/) (2021)
- [Restricting the Flow: Information Bottlenecks for Attribution](https://mlsanity.com/paper/2001.00396/) (2020)
- [Part-based R-CNNs for Fine-grained Category Detection](https://mlsanity.com/paper/1407.3867/) (2014)

## Built on by (most cited first, 6 of 6)

- [Controllable-Continuous Color Editing in Diffusion Model via Color Mapping](https://mlsanity.com/paper/2509.13756/) (2025)
- [Multi-head Uncertainty Inference for Adversarial Attack Detection](https://mlsanity.com/paper/2212.10006/) (2022)
- [Super-Resolution Information Enhancement For Crowd Counting](https://mlsanity.com/paper/2303.06925/) (2023)
- [Robust and Explainable Fine-Grained Visual Classification with Transfer Learning: A Dual-Carriageway Framework](https://mlsanity.com/paper/2405.05853/) (2024)
- [L-WISE: Boosting Human Visual Category Learning Through Model-Based Image Selection and Enhancement](https://mlsanity.com/paper/2412.09765/) (2024)
- [Seeing as Experts Do: A Knowledge-Augmented Agent for Open-Set Fine-Grained Visual Understanding](https://mlsanity.com/paper/2603.03762/) (2026)

## Abstract (arXiv)

As powerful as fine-grained visual classification (FGVC) is, responding your query with a bird name of "Whip-poor-will" or "Mallard" probably does not make much sense. This however commonly accepted in the literature, underlines a fundamental question interfacing AI and human -- what constitutes transferable knowledge for human to learn from AI? This paper sets out to answer this very question using FGVC as a test bed. Specifically, we envisage a scenario where a trained FGVC model (the AI expert) functions as a knowledge provider in enabling average people (you and me) to become better domain experts ourselves, i.e. those capable in distinguishing between "Whip-poor-will" and "Mallard". Fig. 1 lays out our approach in answering this question. Assuming an AI expert trained using expert human labels, we ask (i) what is the best transferable knowledge we can extract from AI, and (ii) what is the most practical means to measure the gains in expertise given that knowledge? On the former, we propose to represent knowledge as highly discriminative visual regions that are expert-exclusive. For that, we devise a multi-stage learning framework, which starts with modelling visual attention of domain experts and novices before discriminatively distilling their differences to acquire the expert exclusive knowledge. For the latter, we simulate the evaluation process as book guide to best accommodate the learning practice of what is accustomed to humans. A comprehensive human study of 15,000 trials shows our method is able to consistently improve people of divergent bird expertise to recognise once unrecognisable birds. Interestingly, our approach also leads to improved conventional FGVC performance when the extracted knowledge defined is utilised as means to achieve discriminative localisation. Codes are available at: https://github.com/PRIS-CV/Making-a-Bird-AI-Expert-Work-for-You-and-Me