12 citations · 45 across the 14 of their papers we have counts for
15 papers
DiffFit: Unlocking Transferability of Large Diffusion Models via Simple Parameter-Efficient Fine-Tuning
Enze Xie, Lewei Yao, Han Shi +5
Diffusion models have proven to be highly effective in generating high-quality images. However, adapting large pre-trained diffusion models to new domains remains an open challenge…
Bridging the Emotional Semantic Gap via Multimodal Relevance Estimation
Chuan Zhang, Daoxin Zhang, Ruixiu Zhang +2
Human beings have rich ways of emotional expressions, including facial action, voice, and natural languages. Due to the diversity and complexity of different individuals, the emoti…
SIAD: Self-supervised Image Anomaly Detection System
Jiawei Li, Chenxi Lan, Xinyi Zhang +7
Recent trends in AIGC effectively boosted the application of visual inspection. However, most of the available systems work in a human-in-the-loop manner and can not provide long-t…
PSP: Pre-trained Soft Prompts for Few-Shot Abstractive Summarization
Xiaochen Liu, Yang Gao, Yu Bai +4
Few-shot abstractive summarization has become a challenging task in natural language generation. To support it, we designed a novel soft prompts architecture coupled with a prompt…
Ask to Understand: Question Generation for Multi-hop Question Answering
Jiawei Li, Mucheng Ren, Yang Gao +1
Multi-hop Question Answering (QA) requires the machine to answer complex questions by finding scattering clues and reasoning from multiple documents. Graph Network (GN) and Questio…
Code Smells in Machine Learning Systems
Jiri Gesi, Siqi Liu, Jiawei Li +6
As Deep learning (DL) systems continuously evolve and grow, assuring their quality becomes an important yet challenging task. Compared to non-DL systems, DL systems have more compl…
Consensus Division in an Arbitrary Ratio
Paul W. Goldberg, Jiawei Li
We consider the problem of partitioning a line segment into two subsets, so that finite measures all have the same ratio of values for the subsets. Letting denote t…
MixACM: Mixup-Based Robustness Transfer via Distillation of Activated Channel Maps
Muhammad Awais, Fengwei Zhou, Chuanlong Xie +3
Deep neural networks are susceptible to adversarially crafted, small and imperceptible changes in the natural inputs. The most effective defense mechanism against these examples is…
PyNose: A Test Smell Detector For Python
Tongjie Wang, Yaroslav Golubev, Oleg Smirnov +3
Similarly to production code, code smells also occur in test code, where they are called test smells. Test smells have a detrimental effect not only on test code but also on the pr…
Salient Object Ranking with Position-Preserved Attention
Hao Fang, Daoxin Zhang, Yi Zhang +5
Instance segmentation can detect where the objects are in an image, but hard to understand the relationship between them. We pay attention to a typical relationship, relative salie…
Towards Explainable Multi-Party Learning: A Contrastive Knowledge Sharing Framework
Yuan Gao, Jiawei Li, Maoguo Gong +2
Multi-party learning provides solutions for training joint models with decentralized data under legal and practical constraints. However, traditional multi-party learning approache…
Changes from the Trenches: Should We Automate Them?
Yaroslav Golubev, Jiawei Li, Viacheslav Bushev +2
Code changes constitute one of the most important features of software evolution. Studying them can provide insights into the nature of software development and also lead to practi…
Horizontal-to-Vertical Video Conversion
Tun Zhu, Daoxin Zhang, Yao Hu +4
Alongside the prevalence of mobile videos, the general public leans towards consuming vertical videos on hand-held devices. To revitalize the exposure of horizontal contents, we he…
The Query Complexity of Local Search and Brouwer in Rounds
Simina Brânzei, Jiawei Li
We consider the query complexity of finding a local minimum of a function defined on a graph. This abstract problem is fundamental to many optimization tasks, such as finding a loc…
MetaAugment: Sample-Aware Data Augmentation Policy Learning
Fengwei Zhou, Jiawei Li, Chuanlong Xie +4
Automated data augmentation has shown superior performance in image recognition. Existing works search for dataset-level augmentation policies without considering individual sample…