no code implementations • 31 Jan 2025 • Zhengqin Lai, Xiaopeng Hong, Yabin Wang, Xiaobai Li
To respond to the requirement of adapting to new data while retaining previously learned knowledge, we introduce the first benchmark specifically designed for incremental micro-expression recognition.
1 code implementation • 15 Aug 2024 • Yabin Wang, Zhiwu Huang, Su Zhou, Adam Prugel-Bennett, Xiaopeng Hong
This paper critiques the overly specialized approach of fine-tuning pre-trained models solely with a penny-wise objective on a single deepfake dataset, while disregarding the pound-wise balance for generalization and knowledge retention.
no code implementations • 28 Jul 2024 • Chenhao Wang, Xiaopeng Hong, Zhiheng Ma, Yupeng Wei, Yabin Wang, Xiaopeng Fan
To overcome the gap between different modalities, we propose a modal emulation-based two-pass multi-modal crowd-counting framework that enables efficient modal emulation, alignment, and fusion.
1 code implementation • 28 Apr 2024 • Yong Dai, Xiaopeng Hong, Yabin Wang, Zhiheng Ma, Dongmei Jiang, YaoWei Wang
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.
1 code implementation • 4 Jan 2024 • Yabin Wang, Zhiwu Huang, Zhiheng Ma, Xiaopeng Hong
The two distinguished features enable DFLIP-3K to develop a benchmark that promotes progress in linguistic profiling of deepfakes, which includes three sub-tasks namely deepfake detection, model identification, and prompt prediction.
1 code implementation • 24 Mar 2023 • Zhiheng Ma, Xiaopeng Hong, Beinan Liu, Yabin Wang, Pinyue Guo, Huiyun Li
It mimics the feature distribution of the target old class on the old model using only samples of new classes.
1 code implementation • 12 Mar 2023 • Yabin Wang, Xiaopeng Hong, Zhiheng Ma, Tiedong Ma, Baoxing Qin, Zhou Su
Task allocation plays a vital role in multi-robot autonomous cleaning systems, where multiple robots work together to clean a large area.
no code implementations • 28 Feb 2023 • Yabin Wang, Zhiwu Huang, Xiaopeng Hong
To address potentially appeared ethics questions, this paper establishes a deepart detection database (DDDB) that consists of a set of high-quality conventional art images (conarts) and five sets of deepart images generated by five state-of-the-art deepfake models.
1 code implementation • 29 Nov 2022 • Yabin Wang, Zhiheng Ma, Zhiwu Huang, YaoWei Wang, Zhou Su, Xiaopeng Hong
To avoid obvious stage learning bottlenecks, we propose a brand-new stage-isolation based incremental learning framework, which leverages a series of stage-isolated classifiers to perform the learning task of each stage without the interference of others.
2 code implementations • 26 Jul 2022 • Yabin Wang, Zhiwu Huang, Xiaopeng Hong
In this paper, we propose one simple paradigm (named as S-Prompting) and two concrete approaches to highly reduce the forgetting degree in one of the most typical continual learning scenarios, i. e., domain increment learning (DIL).
1 code implementation • 11 May 2022 • Chuqiao Li, Zhiwu Huang, Danda Pani Paudel, Yabin Wang, Mohamad Shahbazi, Xiaopeng Hong, Luc van Gool
Within the proposed benchmark, we explore some commonly known essentials of standard continual learning.
no code implementations • 11 Dec 2021 • Hui Lin, Xiaopeng Hong, Yabin Wang
This paper aims to tackle the challenging task of one-shot object counting.
Ranked #14 on
Object Counting
on FSC147