20 citations · 72 across the 20 of their papers we have counts for
20 papers
Understanding Self-attention Mechanism via Dynamical System Perspective
Zhongzhan Huang, Mingfu Liang, Jinghui Qin +2
The self-attention mechanism (SAM) is widely used in various fields of artificial intelligence and has successfully boosted the performance of different models. However, current ex…
LSAS: Lightweight Sub-attention Strategy for Alleviating Attention Bias Problem
Shanshan Zhong, Wushao Wen, Jinghui Qin +2
In computer vision, the performance of deep neural networks (DNNs) is highly related to the feature extraction ability, i.e., the ability to recognize and focus on key pixel region…
SUR-adapter: Enhancing Text-to-Image Pre-trained Diffusion Models with Large Language Models
Shanshan Zhong, Zhongzhan Huang, Wushao Wen +2
Diffusion models, which have emerged to become popular text-to-image generation models, can produce high-quality and content-rich images guided by textual prompts. However, there a…
ASR: Attention-alike Structural Re-parameterization
Shanshan Zhong, Zhongzhan Huang, Wushao Wen +2
The structural re-parameterization (SRP) technique is a novel deep learning technique that achieves interconversion between different network architectures through equivalent param…
UniGeo: Unifying Geometry Logical Reasoning via Reformulating Mathematical Expression
Jiaqi Chen, Tong Li, Jinghui Qin +4
Geometry problem solving is a well-recognized testbed for evaluating the high-level multi-modal reasoning capability of deep models. In most existing works, two main geometry probl…
Deepening Neural Networks Implicitly and Locally via Recurrent Attention Strategy
Shanshan Zhong, Wushao Wen, Jinghui Qin +1
More and more empirical and theoretical evidence shows that deepening neural networks can effectively improve their performance under suitable training settings. However, deepening…
Single- & double-strangeness hypernuclei up to within chiral effective field theory
H. Le
We investigate and hypernuclei with employing the Jacobi-NCSM approach and in combination with baryon-baryon interactions derived within the frame work of chira…
Switchable Self-attention Module
Shanshan Zhong, Wushao Wen, Jinghui Qin
Attention mechanism has gained great success in vision recognition. Many works are devoted to improving the effectiveness of attention mechanism, which finely design the structure…
Mix-Pooling Strategy for Attention Mechanism
Shanshan Zhong, Wushao Wen, Jinghui Qin
Recently many effective attention modules are proposed to boot the model performance by exploiting the internal information of convolutional neural networks in computer vision. In…
Real-World Image Super-Resolution by Exclusionary Dual-Learning
Hao Li, Jinghui Qin, Zhijing Yang +4
Real-world image super-resolution is a practical image restoration problem that aims to obtain high-quality images from in-the-wild input, has recently received considerable attent…
Unbiased Math Word Problems Benchmark for Mitigating Solving Bias
Zhicheng Yang, Jinghui Qin, Jiaqi Chen +1
In this paper, we revisit the solving bias when evaluating models on current Math Word Problem (MWP) benchmarks. However, current solvers exist solving bias which consists of data…
LogicSolver: Towards Interpretable Math Word Problem Solving with Logical Prompt-enhanced Learning
Zhicheng Yang, Jinghui Qin, Jiaqi Chen +2
Recently, deep learning models have made great progress in MWP solving on answer accuracy. However, they are uninterpretable since they mainly rely on shallow heuristics to achieve…
Neural-Symbolic Solver for Math Word Problems with Auxiliary Tasks
Jinghui Qin, Xiaodan Liang, Yining Hong +2
Previous math word problem solvers following the encoder-decoder paradigm fail to explicitly incorporate essential math symbolic constraints, leading to unexplainable and unreasona…
Content-adaptive Representation Learning for Fast Image Super-resolution
Yukai Shi, Jinghui Qin
Deep convolutional networks have attracted great attention in image restoration and enhancement. Generally, restoration quality has been improved by building more and more convolut…
GeoQA: A Geometric Question Answering Benchmark Towards Multimodal Numerical Reasoning
Jiaqi Chen, Jianheng Tang, Jinghui Qin +4
Automatic math problem solving has recently attracted increasing attention as a long-standing AI benchmark. In this paper, we focus on solving geometric problems, which requires a…
Semantically-Aligned Universal Tree-Structured Solver for Math Word Problems
Jinghui Qin, Lihui Lin, Xiaodan Liang +2
A practical automatic textual math word problems (MWPs) solver should be able to solve various textual MWPs while most existing works only focused on one-unknown linear MWPs. Herei…
GRADE: Automatic Graph-Enhanced Coherence Metric for Evaluating Open-Domain Dialogue Systems
Lishan Huang, Zheng Ye, Jinghui Qin +2
Automatically evaluating dialogue coherence is a challenging but high-demand ability for developing high-quality open-domain dialogue systems. However, current evaluation metrics c…
Dynamic Knowledge Routing Network For Target-Guided Open-Domain Conversation
Jinghui Qin, Zheng Ye, Jianheng Tang +1
Target-guided open-domain conversation aims to proactively and naturally guide a dialogue agent or human to achieve specific goals, topics or keywords during open-ended conversatio…
Difficulty-aware Image Super Resolution via Deep Adaptive Dual-Network
Jinghui Qin, Ziwei Xie, Yukai Shi +1
Recently, deep learning based single image super-resolution(SR) approaches have achieved great development. The state-of-the-art SR methods usually adopt a feed-forward pipeline to…
PIRM Challenge on Perceptual Image Enhancement on Smartphones: Report
Andrey Ignatov, Radu Timofte, Thang Van Vu +45
This paper reviews the first challenge on efficient perceptual image enhancement with the focus on deploying deep learning models on smartphones. The challenge consisted of two tra…