ExchangeDEX+

Buy Crypto Markets Spot FuturesXAUT Earn Events

This section provides an algorithm overview for the proposed Instance-Incremental Learning method and details the creation of its benchmarksThis section provides an algorithm overview for the proposed Instance-Incremental Learning method and details the creation of its benchmarks

Algorithm and Data Imbalance: Implementing the New IIL Benchmarks

Author: Hackernoon

Source: Hackernoon

2025/11/08 00:00

Table of Links

Abstract and 1 Introduction

Related works
Problem setting
Methodology

4.1. Decision boundary-aware distillation

4.2. Knowledge consolidation
Experimental results and 5.1. Experiment Setup

5.2. Comparison with SOTA methods

5.3. Ablation study
Conclusion and future work and References

\

Supplementary Material

Details of the theoretical analysis on KCEMA mechanism in IIL
Algorithm overview
Dataset details
Implementation details
Visualization of dusted input images
More experimental results

8. Algorithm overview

The whole process of the proposed method is illustrated in Algorithm 1. Codes will be released to public upon publication.

9. Dataset details

Corresponding to the definition of our new increment-alinstance learning (IIL) task, we reorganize the public dataset Cifar-100 [11] and ImageNet-100 [24] to establish the benchmark in this research topic.

\ Figure 8. Number of images in each class in the base set and incremental sets of Cifar-100. “D0” means the base set and “Di” denotes the incremental set in task i.

\ As can be seen, the base dataset has a more balance sample distribution, where the largest class is class 6 with 279 images. The smallest class is class 29 and has 215 images. Incremental dataset “D5” has the most imbalance number of samples between classes, where the maximum number is 40 in class 58 and the minimum number is 12 in class 76. That is, the highest imbalance ratio is 3.33 : 1.

:::info Authors:

(1) Qiang Nie, Hong Kong University of Science and Technology (Guangzhou);

(2) Weifu Fu, Tencent Youtu Lab;

(3) Yuhuan Lin, Tencent Youtu Lab;

(4) Jialin Li, Tencent Youtu Lab;

(5) Yifeng Zhou, Tencent Youtu Lab;

(6) Yong Liu, Tencent Youtu Lab;

(7) Qiang Nie, Hong Kong University of Science and Technology (Guangzhou);

(8) Chengjie Wang, Tencent Youtu Lab.

:::

:::info This paper is available on arxiv under CC BY-NC-ND 4.0 Deed (Attribution-Noncommercial-Noderivs 4.0 International) license.

:::

Disclaimer: The articles reposted on this site are sourced from public platforms and are provided for informational purposes only. They do not necessarily reflect the views of MEXC. All rights remain with the original authors. If you believe any content infringes on third-party rights, please contact service@support.mexc.com for removal. MEXC makes no guarantees regarding the accuracy, completeness, or timeliness of the content and is not responsible for any actions taken based on the information provided. The content does not constitute financial, legal, or other professional advice, nor should it be considered a recommendation or endorsement by MEXC.