Earticle

초록

영어

Little attention appears to have been paid to the relevance of learning a good representation function in solving long tail tasks. Therefore, we propose a new loss function to ensure a good representation is learnt while learning to classify. We call this loss function Triplet Class-Wise Difficulty-Based (TriCDB-CE) Loss. It is a combination of the Triplet Loss and Class-wise Difficulty-Based Cross-Entropy (CDB-CE) Loss. We prove its effectiveness empirically by performing experiments on three benchmark datasets. We find improvement in accuracy after comparing with some baseline methods. For instance, in the CIFAR-10-LT, 7 percentage points (pp) increase relative to the CDB-CE Loss was recorded. There is more room for improvement on Places-LT.

목차

Abstract
1. INTRODUCTION
2. RELATED WORK
3. THEORY
3.1 CLASS-WISE DIFFICULTY-BASED WEIGHTING
3.2 CLASS-WISE DIFFICULTY-BASED CROSS-ENTROPY LOSS
3.3 TRIPLET LOSS
3.4 TRIPLET CLASS-WISE DIFFICULTY-BASED CROSS-ENTROPY LOSS
4. EXPERIMENTS
5. RESULTS AND DISCUSSION
6. CONCLUSION
Acknowledgement
References

키워드

저자

• Yaw Darkwah Jnr [ Master’s Student, Department of Computer Engineering, Dongseo University ]
• Dae-Ki Kang [ Professor, Department of Computer Engineering, Dongseo University ] Corresponding Author

참고문헌

발행기관

간행물

표지보기 관심저널 등록

• 간행물명

  International Journal of Internet, Broadcasting and Communication

• 간기

  계간

• pISSN

  2288-4920

• eISSN

  2288-4939

• 수록기간

  2009~2025

• 십진분류

  KDC 326 DDC 380