Author name cluster

Xinjie Li

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

4 papers

1 author row

IJCAI Conference 2025 Conference Paper

RetroMoE: A Mixture-of-Experts Latent Translation Framework for Single-step Retrosynthesis

Xinjie Li
Abhinav Verma

Single-step retrosynthesis is a crucial task in organic synthesis, where the objective is to identify the reactants needed to produce a given product. In recent years, a variety of machine learning methods have been developed to tackle retrosynthesis prediction. In our study, we introduce RetroMoE, a novel generative model designed for the single-step retrosynthesis task. We start with a non-symmetric variational autoencoder (VAE) that incorporates a graph encoder to map molecular graphs into a latent space, followed by a transformer decoder for precise prediction of molecular SMILES strings. Additionally, we implement a simple yet effective mixture-of-experts (MoE) network to translate the product latent embedding into the reactant latent embedding. To our knowledge, this is the first approach that frames single-step retrosynthesis as a latent translation problem. Extensive experiments on the USPTO-50K and USPTO-MIT datasets demonstrate the superiority of our method, which not only surpasses most semi-template-based and template-free methods but also delivers competitive results against template-based methods. Notably, under the class-known setting on the USPTO-50K, our method achieves top-1 exact match accuracy comparable to the state-of-the-art template method, RetroKNN.

PDF Details DOI

AAAI Conference 2023 Conference Paper

MEID: Mixture-of-Experts with Internal Distillation for Long-Tailed Video Recognition

Xinjie Li
Huijuan Xu

The long-tailed video recognition problem is especially challenging, as videos tend to be long and untrimmed, and each video may contain multiple classes, causing frame-level class imbalance. The previous method tackles the long-tailed video recognition only through frame-level sampling for class re-balance without distinguishing the frame-level feature representation between head and tail classes. To improve the frame-level feature representation of tail classes, we modulate the frame-level features with an auxiliary distillation loss to reduce the distribution distance between head and tail classes. Moreover, we design a mixture-of-experts framework with two different expert designs, i.e., the first expert with an attention-based classification network handling the original long-tailed distribution, and the second expert dealing with the re-balanced distribution from class-balanced sampling. Notably, in the second expert, we specifically focus on the frames unsolved by the first expert through designing a complementary frame selection module, which inherits the attention weights from the first expert and selects frames with low attention weights, and we also enhance the motion feature representation for these selected frames. To highlight the multi-label challenge in long-tailed video recognition, we create two additional benchmarks based on Charades and CharadesEgo videos with the multi-label property, called CharadesLT and CharadesEgoLT. Extensive experiments are conducted on the existing long-tailed video benchmark VideoLT and the two new benchmarks to verify the effectiveness of our proposed method with state-of-the-art performance. The code and proposed benchmarks are released at https://github.com/VisionLanguageLab/MEID.

PDF Details DOI

EAAI Journal 2022 Journal Article

Enhancing underwater image via adaptive color and contrast enhancement, and denoising

Xinjie Li
Guojia Hou
Kunqian Li
Zhenkuan Pan

Images captured under water are often characterized by low contrast, color distortion, and noise, hindering some visual tasks carried out on it. Despite remarkable breakthrough has been made in recent years, effective and robust enhancement of degraded image remains a challenging problem. To improve the quality of underwater images, we propose a novel scheme by constructing an adaptive color and contrast enhancement, and denoising (ACCE-D) framework. In the proposed framework, Difference of Gaussian (DoG) filter and bilateral filter are respectively employed to decompose the high-frequency and low-frequency components. Benefited from this separation, we utilize soft-thresholding operation to suppress the noise in the high-frequency component. Specially, the low-frequency component is enhanced by using an adaptive color and contrast enhancement (ACCE) strategy. Moreover, we derive a numerical solution for ACCE, and adopt a pyramid-based strategy to accelerate the solving procedure. Both qualitative and quantitative experiments demonstrate that our strategy is effective in color correction, contrast enhancement, and detail revealing. In the quantitative evaluations, by performing on the 890 real-world underwater images from UIEBD, the proposed method obtains 0. 65 UCIQE, 1. 59 UIQM, 0. 81 FDUM, 1. 34 PCQI, 0. 62 CBPD, and 7. 75 entropy scores, achieving average increase of 5% comparing with several state-of-the-art methods. Furthermore, we have verified the utility of our proposed ACCE-D for enhancing other types of degraded scenes, including foggy scene, sandstorm scene and low-light scene.

Details DOI

IJCAI Conference 2021 Conference Paper

Improving Stylized Neural Machine Translation with Iterative Dual Knowledge Transfer

Xuanxuan Wu
Jian Liu
Xinjie Li
Jinan Xu
Yufeng Chen
Yujie Zhang
Hui Huang

Stylized neural machine translation (NMT) aims to translate sentences of one style into sentences of another style, which is essential for the application of machine translation in a real-world scenario. However, a major challenge in this task is the scarcity of high-quality parallel data which is stylized paired. To address this problem, we propose an iterative dual knowledge transfer framework that utilizes informal training data of machine translation and formality style transfer data to create large-scale stylized paired data, for the training of stylized machine translation model. Specifically, we perform bidirectional knowledge transfer between translation model and text style transfer model iteratively through knowledge distillation. Then, we further propose a data-refinement module to process the noisy synthetic parallel data generated during knowledge transfer. Experiment results demonstrate the effectiveness of our method, achieving an improvement over the existing best model by 5 BLEU points on MTFC dataset. Meanwhile, extensive analyses illustrate our method can also improve the accuracy of formality style transfer.

PDF Details DOI