New IIL Setting: Enhancing Deployed Models with Only New Data

This section defines a new, practical Instance-Incremental Learning (IIL) problem setting focused on cost-effective model promotion in deployed systems.


This content originally appeared on HackerNoon and was authored by Instancing

Abstract and 1 Introduction

  1. Related works

  2. Problem setting

  3. Methodology

    4.1. Decision boundary-aware distillation

    4.2. Knowledge consolidation

  4. Experimental results and 5.1. Experiment Setup

    5.2. Comparison with SOTA methods

    5.3. Ablation study

  5. Conclusion and future work and References

    \

Supplementary Material

  1. Details of the theoretical analysis on KCEMA mechanism in IIL
  2. Algorithm overview
  3. Dataset details
  4. Implementation details
  5. Visualization of dusted input images
  6. More experimental results

3. Problem setting

Illustration of the proposed IIL setting is shown in Fig. 1. As can be seen, data is generated continually and unpredictably in the data stream. Generally in real application, people incline to collect enough data first and train a strong model M0 for deployment. No matter how strong the model is, it inevitably will encounter out-of-distribution data and fail on it. These failed cases and other low-score new observations will be annotated to train the model from time to time. Retraining the model with all cumulate data every time leads to higher and higher cost in time and resource. Therefore, the new IIL aims to enhance the existing model with only the new data each time.

\

\ Figure 2. Decision boundaries (DB): (a) DB learned from old data and new data, respectively. With respect to the old DB, new data can be categorized into inner samples and outer samples. (b) ideal DB by jointly training on the old data and new data. (c) fine-tuning the model on the new data with one-hot labels suffers to CF. (d) learning with distillation on prototype exemplars causes overfitting to these exemplars and DB collapsing. (e) the DB achieved using our decision boundary-aware distillation (DBD).

\

:::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.

:::

\


This content originally appeared on HackerNoon and was authored by Instancing


Print Share Comment Cite Upload Translate Updates
APA

Instancing | Sciencx (2025-11-05T15:00:03+00:00) New IIL Setting: Enhancing Deployed Models with Only New Data. Retrieved from https://www.scien.cx/2025/11/05/new-iil-setting-enhancing-deployed-models-with-only-new-data/

MLA
" » New IIL Setting: Enhancing Deployed Models with Only New Data." Instancing | Sciencx - Wednesday November 5, 2025, https://www.scien.cx/2025/11/05/new-iil-setting-enhancing-deployed-models-with-only-new-data/
HARVARD
Instancing | Sciencx Wednesday November 5, 2025 » New IIL Setting: Enhancing Deployed Models with Only New Data., viewed ,<https://www.scien.cx/2025/11/05/new-iil-setting-enhancing-deployed-models-with-only-new-data/>
VANCOUVER
Instancing | Sciencx - » New IIL Setting: Enhancing Deployed Models with Only New Data. [Internet]. [Accessed ]. Available from: https://www.scien.cx/2025/11/05/new-iil-setting-enhancing-deployed-models-with-only-new-data/
CHICAGO
" » New IIL Setting: Enhancing Deployed Models with Only New Data." Instancing | Sciencx - Accessed . https://www.scien.cx/2025/11/05/new-iil-setting-enhancing-deployed-models-with-only-new-data/
IEEE
" » New IIL Setting: Enhancing Deployed Models with Only New Data." Instancing | Sciencx [Online]. Available: https://www.scien.cx/2025/11/05/new-iil-setting-enhancing-deployed-models-with-only-new-data/. [Accessed: ]
rf:citation
» New IIL Setting: Enhancing Deployed Models with Only New Data | Instancing | Sciencx | https://www.scien.cx/2025/11/05/new-iil-setting-enhancing-deployed-models-with-only-new-data/ |

Please log in to upload a file.



There are no updates yet.
Click the Upload button above to add an update.

You must be logged in to translate posts. Please log in or register.

Related Posts