# Efficient Multi-Model Fusion with Adversarial Complementary Representation Learning

arXiv: https://arxiv.org/abs/2404.15704 · HTML: https://mlsanity.com/paper/2404.15704/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 18 of its 44 references that are in the map.
- First posted on arXiv 24 Apr 2024.

## Builds on (most cited first, 18 of 18)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Unsupervised Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1409.7495/) (2014)
- [Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networks](https://mlsanity.com/paper/1710.11063/) (2017)
- [ECAPA-TDNN: Emphasized Channel Attention, Propagation and Aggregation in TDNN Based Speaker Verification](https://mlsanity.com/paper/2005.07143/) (2020)
- [Ensemble deep learning: A review](https://mlsanity.com/paper/2104.02395/) (2021)
- [Adversarial Complementary Learning for Weakly Supervised Object Localization](https://mlsanity.com/paper/1804.06962/) (2018)
- [Grad-CAM: Why did you say that?](https://mlsanity.com/paper/1611.07450/) (2016)
- [What Makes Multi-modal Learning Better than Single (Provably)](https://mlsanity.com/paper/2106.04538/) (2021)
- [MEAL: Multi-Model Ensemble via Adversarial Learning](https://mlsanity.com/paper/1812.02425/) (2018)
- [Audio Deepfake Detection: A Survey](https://mlsanity.com/paper/2308.14970/) (2023)
- [Diversity Matters When Learning From Ensembles](https://mlsanity.com/paper/2110.14149/) (2021)
- [The SpeakIn System for VoxCeleb Speaker Recognition Challange 2021](https://mlsanity.com/paper/2109.01989/) (2021)
- [The 2021 NIST Speaker Recognition Evaluation](https://mlsanity.com/paper/2204.10242/) (2022)
- [VoxSRC 2022: The Fourth VoxCeleb Speaker Recognition Challenge](https://mlsanity.com/paper/2302.10248/) (2023)
- [SpeechEQ: Speech Emotion Recognition based on Multi-scale Unified Datasets and Multitask Learning](https://mlsanity.com/paper/2206.13101/) (2022)
- [Adapting Image Super-Resolution State-of-the-arts and Learning Multi-model Ensemble for Video Super-Resolution](https://mlsanity.com/paper/1905.02462/) (2019)

## Abstract (arXiv)

Single-model systems often suffer from deficiencies in tasks such as speaker verification (SV) and image classification, relying heavily on partial prior knowledge during decision-making, resulting in suboptimal performance. Although multi-model fusion (MMF) can mitigate some of these issues, redundancy in learned representations may limits improvements. To this end, we propose an adversarial complementary representation learning (ACoRL) framework that enables newly trained models to avoid previously acquired knowledge, allowing each individual component model to learn maximally distinct, complementary representations. We make three detailed explanations of why this works and experimental results demonstrate that our method more efficiently improves performance compared to traditional MMF. Furthermore, attribution analysis validates the model trained under ACoRL acquires more complementary knowledge, highlighting the efficacy of our approach in enhancing efficiency and robustness across tasks.