Yabin Wang

Yabin Wang

Auto-generated profile, based on publicly available information

Yabin Wang

Harbin Institute of Technology, Harbin, China

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
26 June 2023 in Proceedings of the AAAI Conference on Artificial Intelligence
Verified
Journal Article
Open access
PDF file
YWYabin Wang
Yabin Wang
ZMZhiheng Ma
Zhiheng Ma
ZHZhiwu Huang
Zhiwu Huang
YWYaowei Wang
Yaowei Wang
ZSZhou Su
Zhou Su
XHXiaopeng Hong
Xiaopeng Hong
This paper focuses on the prevalent stage interference and stage performance imbalance of incremental learning. To avoid obvious stage learning bottlenecks, we propose a new incremental learning framework, which leverages a series of stage-isolated classifiers to perform the learning task at each stage, without interference from others. To be concrete, to aggregate multiple stage classifiers as a uniform one impartially, we first introduce a temperature-controlled energy metric for indicating the confidence score levels of the stage classifiers. We then propose an anchor-based energy self-normalization strategy to ensure the stage classifiers work at the same energy level. Finally, we design a voting-based inference augmentation strategy for robust inference. The proposed method is rehearsal-free and can work for almost all incremental learning scenarios. We evaluate the proposed method on four large datasets. Extensive results demonstrate the superiority of the proposed method in setting up new state-of-the-art overall performance. Code is available at https://github.com/iamwangyabin/ESN.

1 July 2024 in Knowledge-Based Systems
Verified
Journal Article
Closed access
YWYujun Wang
Yujun Wang
XHXiaopeng Hong
Xiaopeng Hong
YWYabin Wang
Yabin Wang
JZJunzhou Zhao
Junzhou Zhao
Guanghui SunGuanghui Sun
Guanghui Sun
BQBaoxing Qin
Baoxing Qin

4 March 2026 in Pattern Recognition
Verified
Journal Article
Closed access
YWYabin Wang
Yabin Wang
XHXiaopeng Hong
Xiaopeng Hong
YLYaqi Li
Yaqi Li
ZMZhiheng Ma
Zhiheng Ma
ZHZhiwu Huang
Zhiwu Huang

3 January 2025 in IEEE Transactions on Artificial Intelligence
Verified
Journal Article
Closed access
YDYong Dai
Yong Dai
XHXiaopeng Hong
Xiaopeng Hong
YWYabin Wang
Yabin Wang
ZMZhiheng Ma
Zhiheng Ma
Dongmei JiangDongmei Jiang
Dongmei Jiang
YWYaowei Wang
Yaowei Wang
Contemporary continual learning approaches typically select prompts from a pool, which function as supplementary inputs to a pre-trained model. However, this strategy is hindered by the inherent noise of its selection approach when handling increasing tasks. In response to these challenges, we reformulate the prompting approach for continual learning and propose the prompt customization (PC) method. PC mainly comprises a prompt generation module (PGM) and a prompt modulation module (PMM). In contrast to conventional methods that employ hard prompt selection, PGM assigns different coefficients to prompts from a fixed-sized pool of prompts and generates tailored prompts. Moreover, PMM further modulates the prompts by adaptively assigning weights according to the correlations between input data and corresponding prompts. We evaluate our method on four benchmark datasets for three diverse settings, including the class, domain, and task-agnostic incremental learning tasks. Experimental results demonstrate consistent improvement (by up to 16.2%), yielded by the proposed method, over the state-of-the-art (SOTA) techniques. The code has been released online.

1 March 2021 in Computer-Aided Design
Verified
Journal Article
Closed access
SZShuai Zheng
Shuai Zheng
YWYabin Wang
Yabin Wang
BLBaotong Li
Baotong Li
Xin LiXin Li
Xin Li

1 July 2026 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
YWYabin Wang
Yabin Wang
ZHZhiwu Huang
Zhiwu Huang
ZSZhou Su
Zhou Su
APAdam Prügel-Bennett
Adam Prügel-Bennett
XHXiaopeng Hong
Xiaopeng Hong
The rise of AI-generated images has sparked serious concerns about their potential misuse across various domains, prompting the urgent need for robust detection methods. Despite advancements, many current approaches prioritize short-term gains at the expense of long-term effectiveness. This paper critiques the overly specialized approach of fine-tuning pre-trained models for short-term gains on a single AI image dataset, while disregarding the long-term imperative of achieving generalization and knowledge retention. To address this trade-off issue, we propose a novel learning framework (PoundNet) for the generalization of AI-generated image detection on a pre-trained vision-language model. PoundNet incorporates a learnable prompt design and a balanced objective to preserve broad knowledge from upstream tasks (object classification) while enhancing generalization for downstream tasks (AI-generated image detection). We train PoundNet on a single standard AI image dataset, following common practice in the literature. We then evaluate its performance across 10 large-scale public AI-generated image detection datasets with 5 main evaluation metrics, forming the largest benchmark test set for assessing the generalization ability of AI-generated image detection models, to our knowledge. The comprehensive benchmark evaluation demonstrates that PoundNet successfully balances generalization with knowledge retention, achieving a remarkable relative improvement of 19% in AI-generated image detection performance compared to state-of-the-art methods, while maintaining a strong performance of 63% on object classification tasks.