Search Results for author: Jianlin Su

Found 26 papers, 19 papers with code

Naive Bayes-based Context Extension for Large Language Models

1 code implementation26 Mar 2024 Jianlin Su, Murtadha Ahmed, Wenbo, Luo Ao, Mingren Zhu, Yunfeng Liu

However, conventional In-Context Learning (ICL) approaches are often impeded by length limitations of transformer architecture, which pose challenges when attempting to effectively integrate supervision from a substantial number of demonstration examples.

In-Context Learning

VisionLLaMA: A Unified LLaMA Interface for Vision Tasks

1 code implementation1 Mar 2024 Xiangxiang Chu, Jianlin Su, Bo Zhang, Chunhua Shen

Large language models are built on top of a transformer-based architecture to process textual inputs.

Image Classification Image Generation +2

Elucidating the Exposure Bias in Diffusion Models

5 code implementations29 Aug 2023 Mang Ning, Mingxiao Li, Jianlin Su, Albert Ali Salah, Itir Onal Ertugrul

In this paper, we systematically investigate the exposure bias problem in diffusion models by first analytically modelling the sampling distribution, based on which we then attribute the prediction error at each sampling step as the root cause of the exposure bias issue.

Attribute Image Generation

Rank-Aware Negative Training for Semi-Supervised Text Classification

1 code implementation13 Jun 2023 Ahmed Murtadha, Shengfeng Pan, Wen Bo, Jianlin Su, Xinxin Cao, Wenze Zhang, Yunfeng Liu

To alleviate the noisy information, we adapt a reasoning with uncertainty-based approach to rank the unlabeled texts based on the evidential support received from the labeled texts.

Semi-Supervised Text Classification text-classification

ZLPR: A Novel Loss for Multi-label Classification

no code implementations5 Aug 2022 Jianlin Su, Mingren Zhu, Ahmed Murtadha, Shengfeng Pan, Bo Wen, Yunfeng Liu

To support the application of deep learning in multi-label classification (MLC) tasks, we propose the ZLPR (zero-bounded log-sum-exp \& pairwise rank-based) loss in this paper.

Classification Multi-Label Classification

BERT-ASC: Implicit Aspect Representation Learning through Auxiliary-Sentence Construction for Sentiment Analysis

1 code implementation22 Mar 2022 Murtadha Ahmed, Shengfeng Pan, Jianlin Su, Xinxin Cao, Wenze Zhang, Bo Wen, Yunfeng Liu

Unfortunately, the aspect is often expressed implicitly through a set of representatives and thus renders implicit mapping process unattainable unless sufficient labeled examples are available.

Aspect-Based Sentiment Analysis Aspect-Based Sentiment Analysis (ABSA) +2

Sparse-softmax: A Simpler and Faster Alternative Softmax Transformation

no code implementations23 Dec 2021 Shaoshi Sun, Zhenyuan Zhang, BoCheng Huang, Pengbin Lei, Jianlin Su, Shengfeng Pan, Jiarun Cao

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 and sum to one, and the corresponding loss function allows to use maximum likelihood principle to optimize the model.


ZARTS: On Zero-order Optimization for Neural Architecture Search

no code implementations10 Oct 2021 Xiaoxing Wang, Wenxuan Guo, Junchi Yan, Jianlin Su, Xiaokang Yang

Also, we search on the search space of DARTS to compare with peer methods, and our discovered architecture achieves 97. 54% accuracy on CIFAR-10 and 75. 7% top-1 accuracy on ImageNet, which are state-of-the-art performance.

Neural Architecture Search

BioCopy: A Plug-And-Play Span Copy Mechanism in Seq2Seq Models

no code implementations EMNLP (sustainlp) 2021 Yi Liu, Guoan Zhang, Puning Yu, Jianlin Su, Shengfeng Pan

Copy mechanisms explicitly obtain unchanged tokens from the source (input) sequence to generate the target (output) sequence under the neural seq2seq framework.


RoFormer: Enhanced Transformer with Rotary Position Embedding

19 code implementations20 Apr 2021 Jianlin Su, Yu Lu, Shengfeng Pan, Ahmed Murtadha, Bo Wen, Yunfeng Liu

Then, we propose a novel method named Rotary Position Embedding(RoPE) to effectively leverage the positional information.

Position Semantic Text Matching +1

Whitening Sentence Representations for Better Semantics and Faster Retrieval

3 code implementations29 Mar 2021 Jianlin Su, Jiarun Cao, Weijie Liu, Yangyiwen Ou

Therefore, some attempts of boosting the isotropy of sentence distribution, such as flow-based model, have been applied to sentence representations and achieved some improvement.

Retrieval Sentence

Multi-stage Attention ResU-Net for Semantic Segmentation of Fine-Resolution Remote Sensing Images

1 code implementation29 Nov 2020 Rui Li, Shunyi Zheng, Chenxi Duan, Jianlin Su, Ce Zhang

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 vision and natural language processing.

Computational Efficiency Semantic Segmentation

Multi-Attention-Network for Semantic Segmentation of Fine Resolution Remote Sensing Images

no code implementations3 Sep 2020 Rui Li, Shunyi Zheng, Chenxi Duan, Ce Zhang, Jianlin Su, P. M. Atkinson

A novel attention mechanism of kernel attention with linear complexity is proposed to alleviate the large computational demand in attention.

Management Segmentation +1

Linear Attention Mechanism: An Efficient Attention for Semantic Segmentation

2 code implementations29 Jul 2020 Rui Li, Jianlin Su, Chenxi Duan, Shunyi Zheng

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.

Semantic Segmentation

A Batch Normalized Inference Network Keeps the KL Vanishing Away

1 code implementation ACL 2020 Qile Zhu, Jianlin Su, Wei Bi, Xiaojiang Liu, Xiyao Ma, Xiaolin Li, Dapeng Wu

Variational Autoencoder (VAE) is widely used as a generative model to approximate a model's posterior on latent variables by combining the amortized variational inference and deep neural networks.

Dialogue Generation Language Modelling +3

O-GAN: Extremely Concise Approach for Auto-Encoding Generative Adversarial Networks

2 code implementations5 Mar 2019 Jianlin Su

We decompose the network of discriminator orthogonally and add an extra loss into the objective of common GANs, which can enforce discriminator become an effective encoder.

Generative Adversarial Network

Artist Style Transfer Via Quadratic Potential

1 code implementation14 Feb 2019 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.

Style Transfer

Evaluating Generalization Ability of Convolutional Neural Networks and Capsule Networks for Image Classification via Top-2 Classification

1 code implementation29 Jan 2019 Hao Ren, Jianlin Su, Hong Lu

In this paper, we propose a new image classification task called Top-2 classification to evaluate the generalization ability of CNNs and CapsNets.

Classification General Classification +1

GAN-QP: A Novel GAN Framework without Gradient Vanishing and Lipschitz Constraint

5 code implementations18 Nov 2018 Jianlin Su

A significant improvement is WGAN, with the help of 1-Lipschitz constraint on discriminator to prevent from gradient vanishing.

Generative Adversarial Network

Training Generative Adversarial Networks Via Turing Test

2 code implementations25 Oct 2018 Jianlin Su

In this article, we introduce a new mode for training Generative Adversarial Networks (GANs).

f-VAEs: Improve VAEs with Conditional Flows

1 code implementation16 Sep 2018 Jianlin Su, Guang Wu

In this paper, we integrate VAEs and flow-based generative models successfully and get f-VAEs.

Cannot find the paper you are looking for? You can Submit a new open access paper.