336 citations · 1.7k across the 24 of their papers we have counts for
24 papers
Elucidating the Exposure Bias in Diffusion Models
Mang Ning, Mingxiao Li, Jianlin Su +2
Diffusion models have demonstrated impressive generative capabilities, but their \textit{exposure bias} problem, described as the input mismatch between training and sampling, lack…
Rank-Aware Negative Training for Semi-Supervised Text Classification
Ahmed Murtadha, Shengfeng Pan, Wen Bo +4
Semi-supervised text classification-based paradigms (SSTC) typically employ the spirit of self-training. The key idea is to train a deep classifier on limited labeled texts and the…
Global Pointer: Novel Efficient Span-based Approach for Named Entity Recognition
Jianlin Su, Ahmed Murtadha, Shengfeng Pan +5
Named entity recognition (NER) task aims at identifying entities from a piece of text that belong to predefined semantic types such as person, location, organization, etc. The stat…
ZLPR: A Novel Loss for Multi-label Classification
Jianlin Su, Mingren Zhu, Ahmed Murtadha +3
In the era of deep learning, loss functions determine the range of tasks available to models and algorithms. To support the application of deep learning in multi-label classificati…
BERT-ASC: Auxiliary-Sentence Construction for Implicit Aspect Learning in Sentiment Analysis
Murtadha Ahmed, Bo Wen, Shengfeng Pan +3
Aspect-based sentiment analysis (ABSA) aims to associate a text with a set of aspects and infer their respective sentimental polarities. State-of-the-art approaches are built on fi…
Sparse-softmax: A Simpler and Faster Alternative Softmax Transformation
Shaoshi Sun, Zhenyuan Zhang, BoCheng Huang +4
The softmax function is widely used in artificial neural networks for the multiclass classification problems, where the softmax transformation enforces the output to be positive an…
ZARTS: On Zero-order Optimization for Neural Architecture Search
Xiaoxing Wang, Wenxuan Guo, Junchi Yan +2
Differentiable architecture search (DARTS) has been a popular one-shot paradigm for NAS due to its high efficiency. It introduces trainable architecture parameters to represent the…
BioCopy: A Plug-And-Play Span Copy Mechanism in Seq2Seq Models
Yi Liu, Guoan Zhang, Puning Yu +2
Copy mechanisms explicitly obtain unchanged tokens from the source (input) sequence to generate the target (output) sequence under the neural seq2seq framework. However, most of th…
RoFormer: Enhanced Transformer with Rotary Position Embedding
Jianlin Su, Yu Lu, Shengfeng Pan +3
Position encoding recently has shown effective in the transformer architecture. It enables valuable supervision for dependency modeling between elements at different positions of t…
Whitening Sentence Representations for Better Semantics and Faster Retrieval
Jianlin Su, Jiarun Cao, Weijie Liu +1
Pre-training models such as BERT have achieved great success in many natural language processing tasks. However, how to obtain better sentence representation through these pre-trai…
A2-FPN for Semantic Segmentation of Fine-Resolution Remotely Sensed Images
Rui Li, Shunyi Zheng, Ce Zhang +2
Semantic segmentation using fine-resolution remotely sensed images plays a critical role in many practical applications, such as urban planning, environmental protection, natural a…
Multi-stage Attention ResU-Net for Semantic Segmentation of Fine-Resolution Remote Sensing Images
Rui Li, Shunyi Zheng, Chenxi Duan +2
The attention mechanism can refine the extracted feature maps and boost the classification performance of the deep network, which has become an essential technique in computer visi…
Multi-Attention-Network for Semantic Segmentation of Fine Resolution Remote Sensing Images
Rui Li, Shunyi Zheng, Chenxi Duan +3
Semantic segmentation of remote sensing images plays an important role in a wide range of applications including land resource management, biosphere monitoring and urban planning.…
Linear Attention Mechanism: An Efficient Attention for Semantic Segmentation
Rui Li, Jianlin Su, Chenxi Duan +1
In this paper, to remedy this deficiency, we propose a Linear Attention Mechanism which is approximate to dot-product attention with much less memory and computational costs. The e…
Joint Extraction of Entities and Relations Based on a Novel Decomposition Strategy
Bowen Yu, Zhenyu Zhang, Xiaobo Shu +4
Joint extraction of entities and relations aims to detect entity pairs along with their relations using a single model. Prior work typically solves this task in the extract-then-cl…
A Novel Cascade Binary Tagging Framework for Relational Triple Extraction
Zhepei Wei, Jianlin Su, Yue Wang +2
Extracting relational triples from unstructured text is crucial for large-scale knowledge graph construction. However, few existing works excel in solving the overlapping triple pr…
O-GAN: Extremely Concise Approach for Auto-Encoding Generative Adversarial Networks
Jianlin Su
In this paper, we propose Orthogonal Generative Adversarial Networks (O-GANs). We decompose the network of discriminator orthogonally and add an extra loss into the objective of co…
Artist Style Transfer Via Quadratic Potential
Rahul Bhalley, Jianlin Su
In this paper we address the problem of artist style transfer where the painting style of a given artist is applied on a real world photograph. We train our neural networks in adve…
Evaluating Generalization Ability of Convolutional Neural Networks and Capsule Networks for Image Classification via Top-2 Classification
Hao Ren, Jianlin Su, Hong Lu
Image classification is a challenging problem which aims to identify the category of object in the image. In recent years, deep Convolutional Neural Networks (CNNs) have been appli…
GAN-QP: A Novel GAN Framework without Gradient Vanishing and Lipschitz Constraint
Jianlin Su
We know SGAN may have a risk of gradient vanishing. A significant improvement is WGAN, with the help of 1-Lipschitz constraint on discriminator to prevent from gradient vanishing.…
Training Generative Adversarial Networks Via Turing Test
Jianlin Su
In this article, we introduce a new mode for training Generative Adversarial Networks (GANs). Rather than minimizing the distance of evidence distribution and the ge…
f-VAEs: Improve VAEs with Conditional Flows
Jianlin Su, Guang Wu
In this paper, we integrate VAEs and flow-based generative models successfully and get f-VAEs. Compared with VAEs, f-VAEs generate more vivid images, solved the blurred-image probl…
Variational Inference: A Unified Framework of Generative Models and Some Revelations
Jianlin Su
We reinterpreting the variational inference in a new perspective. Via this way, we can easily prove that EM algorithm, VAE, GAN, AAE, ALI(BiGAN) are all special cases of variationa…
Using deep Residual Networks to search for galaxy-Lyα emitter lens candidates based on spectroscopic-selection
Rui Li, Yiping Shu, Jianlin Su +4
More than one hundred galaxy-scale strong gravitational lens systems have been found by searching for the emission lines coming from galaxies with redshifts higher than the lens ga…