# Introspective Learning : A Two-Stage Approach for Inference in Neural Networks

arXiv: https://arxiv.org/abs/2209.08425 · HTML: https://mlsanity.com/paper/2209.08425/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- Builds on 43 of its 81 references that are in the map.
- First posted on arXiv 17 Sep 2022.

## Builds on (most cited first, 30 of 43)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [Benchmarking Neural Network Robustness to Common Corruptions and Perturbations](https://mlsanity.com/paper/1903.12261/) (2019)
- [A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks](https://mlsanity.com/paper/1610.02136/) (2016)
- [Describing Textures in the Wild](https://mlsanity.com/paper/1311.3618/) (2013)
- [LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop](https://mlsanity.com/paper/1506.03365/) (2015)
- [Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networks](https://mlsanity.com/paper/1706.02690/) (2017)
- [AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty](https://mlsanity.com/paper/1912.02781/) (2019)
- [Deep Bayesian Active Learning with Image Data](https://mlsanity.com/paper/1703.02910/) (2017)
- [A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challenges](https://mlsanity.com/paper/2011.06225/) (2020)
- [Evidential Deep Learning to Quantify Classification Uncertainty](https://mlsanity.com/paper/1806.01768/) (2018)
- [Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Bounds](https://mlsanity.com/paper/1906.03671/) (2019)
- [Variational Dropout and the Local Reparameterization Trick](https://mlsanity.com/paper/1506.02557/) (2015)
- [VisDA: The Visual Domain Adaptation Challenge](https://mlsanity.com/paper/1710.06924/) (2017)
- [Examining the Impact of Blur on Recognition by Convolutional Networks](https://mlsanity.com/paper/1611.05760/) (2016)
- [Robust Out-of-distribution Detection for Neural Networks](https://mlsanity.com/paper/2003.09711/) (2020)
- [Gradients as a Measure of Uncertainty in Neural Networks](https://mlsanity.com/paper/2008.08030/) (2020)
- [Backpropagated Gradient Representations for Anomaly Detection](https://mlsanity.com/paper/2007.09507/) (2020)
- [Efficient Per-Example Gradient Computations](https://mlsanity.com/paper/1510.01799/) (2015)
- [CURE-TSR: Challenging Unreal and Real Environments for Traffic Sign Recognition](https://mlsanity.com/paper/1712.02463/) (2017)
- [Gradients as Features for Deep Representation Learning](https://mlsanity.com/paper/2004.05529/) (2020)
- [Contrastive Explanations in Neural Networks](https://mlsanity.com/paper/2008.00178/) (2020)
- [CURE-OR: Challenging Unreal and Real Environments for Object Recognition](https://mlsanity.com/paper/1810.08293/) (2018)
- [Novelty Detection Through Model-Based Characterization of Neural Networks](https://mlsanity.com/paper/2008.06094/) (2020)

## Built on by (most cited first, 20 of 20)

- [Explain Before You Answer: A Survey on Compositional Visual Reasoning](https://mlsanity.com/paper/2508.17298/) (2025)
- [Gaussian Switch Sampling: A Second Order Approach to Active Learning](https://mlsanity.com/paper/2302.12018/) (2023)
- [Probing the Purview of Neural Networks via Gradient Analysis](https://mlsanity.com/paper/2304.02834/) (2023)
- [FOCAL: A Cost-Aware Video Dataset for Active Learning](https://mlsanity.com/paper/2311.10591/) (2023)
- [Janus-Pro-R1: Advancing Collaborative Visual Comprehension and Generation via Reinforcement Learning](https://mlsanity.com/paper/2506.01480/) (2025)
- [Hierarchical and Multimodal Data for Daily Activity Understanding](https://mlsanity.com/paper/2504.17696/) (2025)
- [Exploiting the Distortion-Semantic Interaction in Fisheye Data](https://mlsanity.com/paper/2305.00079/) (2023)
- [Designing explainable artificial intelligence with active inference: A framework for transparent introspection and decision-making](https://mlsanity.com/paper/2306.04025/) (2023)
- [Transitional Uncertainty with Layered Intermediate Predictions](https://mlsanity.com/paper/2405.17494/) (2024)
- [Intelligent Multi-View Test Time Augmentation](https://mlsanity.com/paper/2406.08593/) (2024)
- [A Large-scale Benchmark on Geological Fault Delineation Models: Domain Shift, Training Dynamics, Generalizability, Evaluation and Inferential Behavior](https://mlsanity.com/paper/2505.08585/) (2025)
- [On the Ramifications of Human Label Uncertainty](https://mlsanity.com/paper/2211.05871/) (2022)
- [VOICE: Variance of Induced Contrastive Explanations to quantify Uncertainty in Neural Network Interpretability](https://mlsanity.com/paper/2406.00573/) (2024)
- [Stochastic Surprisal: An inferential measurement of Free Energy in Neural Networks](https://mlsanity.com/paper/2302.05776/) (2023)
- [Perceptual Quality-based Model Training under Annotator Label Uncertainty](https://mlsanity.com/paper/2403.10190/) (2024)
- [Counterfactual Gradients-based Quantification of Prediction Trust in Neural Networks](https://mlsanity.com/paper/2405.13758/) (2024)
- [A unified framework for evaluating the robustness of machine-learning interpretability for prospect risking](https://mlsanity.com/paper/2602.14430/) (2026)
- [BALD-SAM: Disagreement-based Active Prompting in Interactive Segmentation](https://mlsanity.com/paper/2603.10828/) (2026)
- [Effective Data Selection for Seismic Interpretation through Disagreement](https://mlsanity.com/paper/2406.05149/) (2024)
- [Building LLM Agent Systems the Deep Learning Way: From Modular Design to Architecture Search](https://mlsanity.com/paper/2610.04961/) (2026)

## Abstract (arXiv)

In this paper, we advocate for two stages in a neural network's decision making process. The first is the existing feed-forward inference framework where patterns in given data are sensed and associated with previously learned patterns. The second stage is a slower reflection stage where we ask the network to reflect on its feed-forward decision by considering and evaluating all available choices. Together, we term the two stages as introspective learning. We use gradients of trained neural networks as a measurement of this reflection. A simple three-layered Multi Layer Perceptron is used as the second stage that predicts based on all extracted gradient features. We perceptually visualize the post-hoc explanations from both stages to provide a visual grounding to introspection. For the application of recognition, we show that an introspective network is 4% more robust and 42% less prone to calibration errors when generalizing to noisy data. We also illustrate the value of introspective networks in downstream tasks that require generalizability and calibration including active learning, out-of-distribution detection, and uncertainty estimation. Finally, we ground the proposed machine introspection to human introspection for the application of image quality assessment.