Efficient Multi-Model Fusion with Adversarial Complementary Representation Learning | IEEE Conference Publication | IEEE Xplore

Efficient Multi-Model Fusion with Adversarial Complementary Representation Learning


Abstract:

Single-model systems often suffer from deficiencies in tasks such as speaker verification (SV) and image classification, relying heavily on partial prior knowledge during...Show More

Abstract:

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.
Date of Conference: 30 June 2024 - 05 July 2024
Date Added to IEEE Xplore: 09 September 2024
ISBN Information:

ISSN Information:

Conference Location: Yokohama, Japan

Funding Agency:


Contact IEEE to Subscribe

References

References is not available for this document.