Search Results for author: Yuhang Song

Found 34 papers, 14 papers with code

SurvMamba: State Space Model with Multi-grained Multi-modal Interaction for Survival Prediction

no code implementations11 Apr 2024 Ying Chen, Jiajing Xie, Yuxiang Lin, Yuhang Song, Wenxian Yang, Rongshan Yu

SurvMamba is implemented with a Hierarchical Interaction Mamba (HIM) module that facilitates efficient intra-modal interactions at different granularities, thereby capturing more detailed local features as well as rich global representations.

Survival Prediction whole slide images

Associative Memories in the Feature Space

no code implementations16 Feb 2024 Tommaso Salvatori, Beren Millidge, Yuhang Song, Rafal Bogacz, Thomas Lukasiewicz

This problem can be easily solved by computing \emph{similarities} in an embedding space instead of the pixel space.

Learning to Terminate in Object Navigation

1 code implementation28 Sep 2023 Yuhang Song, Anh Nguyen, Chun-Yi Lee

This paper tackles the critical challenge of object navigation in autonomous navigation systems, particularly focusing on the problem of target approach and episode termination in environments with long optimal episode length in Deep Reinforcement Learning (DRL) based methods.

Autonomous Navigation Object +2

Predictive Coding beyond Gaussian Distributions

no code implementations7 Nov 2022 Luca Pinchetti, Tommaso Salvatori, Yordan Yordanov, Beren Millidge, Yuhang Song, Thomas Lukasiewicz

A large amount of recent research has the far-reaching goal of finding training methods for deep neural networks that can serve as alternatives to backpropagation (BP).

Bird-Eye Transformers for Text Generation Models

1 code implementation8 Oct 2022 Lei Sha, Yuhang Song, Yordan Yordanov, Tommaso Salvatori, Thomas Lukasiewicz

Transformers have become an indispensable module for text generation models since their great success in machine translation.

Attribute Inductive Bias +3

A Theoretical Framework for Inference and Learning in Predictive Coding Networks

1 code implementation21 Jul 2022 Beren Millidge, Yuhang Song, Tommaso Salvatori, Thomas Lukasiewicz, Rafal Bogacz

In this paper, we provide a comprehensive theoretical analysis of the properties of PCNs trained with prospective configuration.

Continual Learning

Predictive Coding: Towards a Future of Deep Learning beyond Backpropagation?

no code implementations18 Feb 2022 Beren Millidge, Tommaso Salvatori, Yuhang Song, Rafal Bogacz, Thomas Lukasiewicz

The backpropagation of error algorithm used to train deep neural networks has been fundamental to the successes of deep learning.

Learning on Arbitrary Graph Topologies via Predictive Coding

no code implementations31 Jan 2022 Tommaso Salvatori, Luca Pinchetti, Beren Millidge, Yuhang Song, TianYi Bao, Rafal Bogacz, Thomas Lukasiewicz

Training with backpropagation (BP) in standard deep learning consists of two main steps: a forward pass that maps a data point to its prediction, and a backward pass that propagates the error of this prediction back through the network.

Associative Memories via Predictive Coding

no code implementations NeurIPS 2021 Tommaso Salvatori, Yuhang Song, Yujian Hong, Simon Frieder, Lei Sha, Zhenghua Xu, Rafal Bogacz, Thomas Lukasiewicz

We conclude by discussing the possible impact of this work in the neuroscience community, by showing that our model provides a plausible framework to study learning and retrieval of memories in the brain, as it closely mimics the behavior of the hippocampus as a memory index and generative model.

Hippocampus Retrieval

LAU-Net: Latitude Adaptive Upscaling Network for Omnidirectional Image Super-Resolution

no code implementations CVPR 2021 Xin Deng, Hao Wang, Mai Xu, Yichen Guo, Yuhang Song, Li Yang

In addition, we propose a deep reinforcement learning scheme with a latitude adaptive reward, in order to automatically select optimal upscaling factors for different latitude bands.

Image Super-Resolution

Reverse Differentiation via Predictive Coding

no code implementations8 Mar 2021 Tommaso Salvatori, Yuhang Song, Thomas Lukasiewicz, Rafal Bogacz, Zhenghua Xu

Recent works prove that these methods can approximate BP up to a certain margin on multilayer perceptrons (MLPs), and asymptotically on any other complex model, and that zero-divergence inference learning (Z-IL), a variant of PC, is able to exactly implement BP on MLPs.

Self-Supervised Continuous Control without Policy Gradient

no code implementations1 Jan 2021 Hao Sun, Ziping Xu, Meng Fang, Yuhang Song, Jiechao Xiong, Bo Dai, Zhengyou Zhang, Bolei Zhou

Despite the remarkable progress made by the policy gradient algorithms in reinforcement learning (RL), sub-optimal policies usually result from the local exploration property of the policy gradient update.

Continuous Control Policy Gradient Methods +3

Can the Brain Do Backpropagation? --- Exact Implementation of Backpropagation in Predictive Coding Networks

no code implementations NeurIPS 2020 Yuhang Song, Thomas Lukasiewicz, Zhenghua Xu, Rafal Bogacz

However, there are several gaps between BP and learning in biologically plausible neuronal networks of the brain (learning in the brain, or simply BL, for short), in particular, (1) it has been unclear to date, if BP can be implemented exactly via BL, (2) there is a lack of local plasticity in BP, i. e., weight updates require information that is not locally available, while BL utilizes only locally available information, and (3)~there is a lack of autonomy in BP, i. e., some external control over the neural network is required (e. g., switching between prediction and learning stages requires changes to dynamics and synaptic plasticity rules), while BL works fully autonomously.

Zeroth-Order Supervised Policy Improvement

no code implementations11 Jun 2020 Hao Sun, Ziping Xu, Yuhang Song, Meng Fang, Jiechao Xiong, Bo Dai, Bolei Zhou

However, PG algorithms rely on exploiting the value function being learned with the first-order update locally, which results in limited sample efficiency.

Continuous Control Policy Gradient Methods +2

Novel Human-Object Interaction Detection via Adversarial Domain Generalization

no code implementations22 May 2020 Yuhang Song, Wenbo Li, Lei Zhang, Jianwei Yang, Emre Kiciman, Hamid Palangi, Jianfeng Gao, C. -C. Jay Kuo, Pengchuan Zhang

We study in this paper the problem of novel human-object interaction (HOI) detection, aiming at improving the generalization ability of the model to unseen scenarios.

Domain Generalization Human-Object Interaction Detection +1

AutoRemover: Automatic Object Removal for Autonomous Driving Videos

1 code implementation28 Nov 2019 Rong Zhang, Wei Li, Peng Wang, Chenye Guan, Jin Fang, Yuhang Song, Jinhui Yu, Baoquan Chen, Weiwei Xu, Ruigang Yang

To deal with shadows, we build up an autonomous driving shadow dataset and design a deep neural network to detect shadows automatically.

Autonomous Driving Object +1

Mega-Reward: Achieving Human-Level Play without Extrinsic Rewards

1 code implementation12 May 2019 Yuhang Song, Jianyi Wang, Thomas Lukasiewicz, Zhenghua Xu, Shangtong Zhang, Andrzej Wojcicki, Mai Xu

Intrinsic rewards were introduced to simulate how human intelligence works; they are usually evaluated by intrinsically-motivated play, i. e., playing games without extrinsic rewards but evaluated with extrinsic rewards.

Diversity-Driven Extensible Hierarchical Reinforcement Learning

1 code implementation10 Nov 2018 Yuhang Song, Jianyi Wang, Thomas Lukasiewicz, Zhenghua Xu, Mai Xu

However, HRL with multiple levels is usually needed in many real-world scenarios, whose ultimate goals are highly abstract, while their actions are very primitive.

Hierarchical Reinforcement Learning reinforcement-learning +1

PortraitGAN for Flexible Portrait Manipulation

no code implementations5 Jul 2018 Jiali Duan, Xiaoyuan Guo, Yuhang Song, Chao Yang, C. -C. Jay Kuo

Previous methods have dealt with discrete manipulation of facial attributes such as smile, sad, angry, surprise etc, out of canonical expressions and they are not scalable, operating in single modality.

SPG-Net: Segmentation Prediction and Guidance Network for Image Inpainting

1 code implementation9 May 2018 Yuhang Song, Chao Yang, Yeji Shen, Peng Wang, Qin Huang, C. -C. Jay Kuo

In this paper, we focus on image inpainting task, aiming at recovering the missing area of an incomplete image given the context information.

Image Inpainting Interactive Segmentation +2

Image Inpainting using Block-wise Procedural Training with Annealed Adversarial Counterpart

no code implementations23 Mar 2018 Chao Yang, Yuhang Song, Xiaofeng Liu, Qingming Tang, C. -C. Jay Kuo

We present a new approach to address the difficulty of training a very deep generative model to synthesize high-quality photo-realistic inpainting.

Facial Inpainting Image Harmonization

Contextual-based Image Inpainting: Infer, Match, and Translate

no code implementations ECCV 2018 Yuhang Song, Chao Yang, Zhe Lin, Xiaofeng Liu, Qin Huang, Hao Li, C. -C. Jay Kuo

We study the task of image inpainting, which is to fill in the missing region of an incomplete image with plausible contents.

Image Inpainting Translation

Predicting Head Movement in Panoramic Video: A Deep Reinforcement Learning Approach

1 code implementation30 Oct 2017 Yuhang Song, Mai Xu, Jianyi Wang, Minglang Qiao, Liangyu Huo, Zulin Wang

Finally, the experiments validate that our approach is effective in both offline and online prediction of HM positions for panoramic video, and that the learned offline-DHP model can improve the performance of online-DHP.

Position reinforcement-learning +1

Generalization Tower Network: A Novel Deep Neural Network Architecture for Multi-Task Learning

1 code implementation27 Oct 2017 Yuhang Song, Main Xu, Songyang Zhang, Liangyu Huo

However, the conventional deep neural network architecture is limited in learning representations for multi-task RL (MT-RL), as multiple tasks can refer to different kinds of representations.

Atari Games Multi-Task Learning +1

Learning Approximate Stochastic Transition Models

1 code implementation26 Oct 2017 Yuhang Song, Christopher Grimm, Xianming Wang, Michael L. Littman

We examine the problem of learning mappings from state to state, suitable for use in a model-based reinforcement-learning setting, that simultaneously generalize to novel states and can capture stochastic transitions.

Model-based Reinforcement Learning reinforcement-learning +1

Summable Reparameterizations of Wasserstein Critics in the One-Dimensional Setting

no code implementations19 Sep 2017 Christopher Grimm, Yuhang Song, Michael L. Littman

Generative adversarial networks (GANs) are an exciting alternative to algorithms for solving density estimation problems---using data to assess how likely samples are to be drawn from the same distribution.

Density Estimation

Semantic Segmentation with Reverse Attention

no code implementations20 Jul 2017 Qin Huang, Chunyang Xia, Chi-Hao Wu, Siyang Li, Ye Wang, Yuhang Song, C. -C. Jay Kuo

Recent development in fully convolutional neural network enables efficient end-to-end learning of semantic segmentation.

Segmentation Semantic Segmentation

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