Search Results for author: Shiji Song

Found 36 papers, 17 papers with code

AdaFocusV3: On Unified Spatial-temporal Dynamic Video Recognition

no code implementations27 Sep 2022 Yulin Wang, Yang Yue, Xinhong Xu, Ali Hassani, Victor Kulikov, Nikita Orlov, Shiji Song, Humphrey Shi, Gao Huang

Recent research has revealed that reducing the temporal and spatial redundancy are both effective approaches towards efficient video recognition, e. g., allocating the majority of computation to a task-relevant subset of frames or the most valuable image regions of each frame.

Video Recognition

ActiveNeRF: Learning where to See with Uncertainty Estimation

no code implementations18 Sep 2022 Xuran Pan, Zihang Lai, Shiji Song, Gao Huang

In this paper, we present a novel learning framework, ActiveNeRF, aiming to model a 3D scene with a constrained input budget.

Active Learning Novel View Synthesis

Learning to Weight Samples for Dynamic Early-exiting Networks

1 code implementation17 Sep 2022 Yizeng Han, Yifan Pu, Zihang Lai, Chaofei Wang, Shiji Song, Junfen Cao, Wenhui Huang, Chao Deng, Gao Huang

Intuitively, easy samples, which generally exit early in the network during inference, should contribute more to training early classifiers.


The Neural-Prediction based Acceleration Algorithm of Column Generation for Graph-Based Set Covering Problems

no code implementations4 Jul 2022 Haofeng Yuan, Peng Jiang, Shiji Song

In this paper, we propose an improved column generation algorithm with neural prediction (CG-P) for solving graph-based set covering problems.

Combinatorial Optimization

Pseudo-Q: Generating Pseudo Language Queries for Visual Grounding

1 code implementation CVPR 2022 Haojun Jiang, Yuanze Lin, Dongchen Han, Shiji Song, Gao Huang

Our method leverages an off-the-shelf object detector to identify visual objects from unlabeled images, and then language queries for these objects are obtained in an unsupervised fashion with a pseudo-query generation module.

Language Modelling Natural Language Queries +1

Learn From the Past: Experience Ensemble Knowledge Distillation

no code implementations25 Feb 2022 Chaofei Wang, Shaowei Zhang, Shiji Song, Gao Huang

We save a moderate number of intermediate models from the training process of the teacher model uniformly, and then integrate the knowledge of these intermediate models by ensemble technique.

Knowledge Distillation Transfer Learning

Domain Adaptation via Prompt Learning

no code implementations14 Feb 2022 Chunjiang Ge, Rui Huang, Mixue Xie, Zihang Lai, Shiji Song, Shuang Li, Gao Huang

Unsupervised domain adaption (UDA) aims to adapt models learned from a well-annotated source domain to a target domain, where only unlabeled samples are given.

Domain Adaptation

Glance and Focus Networks for Dynamic Visual Recognition

1 code implementation9 Jan 2022 Gao Huang, Yulin Wang, Kangchen Lv, Haojun Jiang, Wenhui Huang, Pengfei Qi, Shiji Song

Spatial redundancy widely exists in visual recognition tasks, i. e., discriminative features in an image or video frame usually correspond to only a subset of pixels, while the remaining regions are irrelevant to the task at hand.

Image Classification Video Recognition

Vision Transformer with Deformable Attention

2 code implementations CVPR 2022 Zhuofan Xia, Xuran Pan, Shiji Song, Li Erran Li, Gao Huang

On the one hand, using dense attention e. g., in ViT, leads to excessive memory and computational cost, and features can be influenced by irrelevant parts which are beyond the region of interests.

Ranked #2 on Object Detection on COCO test-dev (AP metric)

Image Classification Object Detection +1

Temporal-Spatial Causal Interpretations for Vision-Based Reinforcement Learning

no code implementations6 Dec 2021 Wenjie Shi, Gao Huang, Shiji Song, Cheng Wu

TSCI model builds on the formulation of temporal causality, which reflects the temporal causal relations between sequential observations and decisions of RL agent.

Causal Discovery Decision Making +1

On the Integration of Self-Attention and Convolution

1 code implementation CVPR 2022 Xuran Pan, Chunjiang Ge, Rui Lu, Shiji Song, Guanfu Chen, Zeyi Huang, Gao Huang

In this paper, we show that there exists a strong underlying relation between them, in the sense that the bulk of computations of these two paradigms are in fact done with the same operation.

Representation Learning

Fine-Grained Few Shot Learning with Foreground Object Transformation

no code implementations13 Sep 2021 Chaofei Wang, Shiji Song, Qisen Yang, Xiang Li, Gao Huang

As a data augmentation method, FOT can be conveniently applied to any existing few shot learning algorithm and greatly improve its performance on FG-FSL tasks.

Data Augmentation Few-Shot Learning +1

CAM-loss: Towards Learning Spatially Discriminative Feature Representations

no code implementations ICCV 2021 Chaofei Wang, Jiayu Xiao, Yizeng Han, Qisen Yang, Shiji Song, Gao Huang

The backbone of traditional CNN classifier is generally considered as a feature extractor, followed by a linear layer which performs the classification.

Few-Shot Learning Knowledge Distillation +1

Not All Images are Worth 16x16 Words: Dynamic Transformers for Efficient Image Recognition

2 code implementations NeurIPS 2021 Yulin Wang, Rui Huang, Shiji Song, Zeyi Huang, Gao Huang

Inspired by this phenomenon, we propose a Dynamic Transformer to automatically configure a proper number of tokens for each input image.

Ranked #28 on Image Classification on CIFAR-100 (using extra training data)

Image Classification

Adaptive Focus for Efficient Video Recognition

1 code implementation ICCV 2021 Yulin Wang, Zhaoxi Chen, Haojun Jiang, Shiji Song, Yizeng Han, Gao Huang

In this paper, we explore the spatial redundancy in video recognition with the aim to improve the computational efficiency.

Video Recognition

Dynamic Neural Networks: A Survey

no code implementations9 Feb 2021 Yizeng Han, Gao Huang, Shiji Song, Le Yang, Honghui Wang, Yulin Wang

Dynamic neural network is an emerging research topic in deep learning.

Decision Making

Revisiting Locally Supervised Learning: an Alternative to End-to-end Training

1 code implementation26 Jan 2021 Yulin Wang, Zanlin Ni, Shiji Song, Le Yang, Gao Huang

Due to the need to store the intermediate activations for back-propagation, end-to-end (E2E) training of deep networks usually suffers from high GPUs memory footprint.

Revisiting Locally Supervised Training of Deep Neural Networks

no code implementations ICLR 2021 Yulin Wang, Zanlin Ni, Shiji Song, Le Yang, Gao Huang

As InfoPro loss is difficult to compute in its original form, we derive a feasible upper bound as a surrogate optimization objective, yielding a simple but effective algorithm.

Robust Offline Reinforcement Learning from Low-Quality Data

no code implementations1 Jan 2021 Wenjie Shi, Tianchi Cai, Shiji Song, Lihong Gu, Jinjie Gu, Gao Huang

We theoretically show that AdaPT produces a tight upper bound on the distributional deviation between the learned policy and the behavior policy, and this upper bound is the minimum requirement to guarantee policy improvement at each iteration.

Continuous Control Offline RL +1

A Unified Framework for Convolution-based Graph Neural Networks

no code implementations1 Jan 2021 Xuran Pan, Shiji Song, Gao Huang

In this paper, we take a step forward to establish a unified framework for convolution-based graph neural networks, by formulating the basic graph convolution operation as an optimization problem in the graph Fourier space.

3D Object Detection with Pointformer

1 code implementation CVPR 2021 Xuran Pan, Zhuofan Xia, Shiji Song, Li Erran Li, Gao Huang

In this paper, we propose Pointformer, a Transformer backbone designed for 3D point clouds to learn features effectively.

3D Object Detection object-detection +1

Regularizing Deep Networks with Semantic Data Augmentation

1 code implementation21 Jul 2020 Yulin Wang, Gao Huang, Shiji Song, Xuran Pan, Yitong Xia, Cheng Wu

The proposed method is inspired by the intriguing property that deep networks are effective in learning linearized features, i. e., certain directions in the deep feature space correspond to meaningful semantic transformations, e. g., changing the background or view angle of an object.

Data Augmentation

Meta-Semi: A Meta-learning Approach for Semi-supervised Learning

no code implementations5 Jul 2020 Yulin Wang, Jiayi Guo, Shiji Song, Gao Huang

In this paper, we propose a novel meta-learning based SSL algorithm (Meta-Semi) that requires tuning only one additional hyper-parameter, compared with a standard supervised deep learning algorithm, to achieve competitive performance under various conditions of SSL.


Resolution Adaptive Networks for Efficient Inference

2 code implementations CVPR 2020 Le Yang, Yizeng Han, Xi Chen, Shiji Song, Jifeng Dai, Gao Huang

Adaptive inference is an effective mechanism to achieve a dynamic tradeoff between accuracy and computational cost in deep networks.

Self-Supervised Discovering of Interpretable Features for Reinforcement Learning

1 code implementation16 Mar 2020 Wenjie Shi, Gao Huang, Shiji Song, Zhuoyuan Wang, Tingyu Lin, Cheng Wu

Deep reinforcement learning (RL) has recently led to many breakthroughs on a range of complex control tasks.

Atari Games Decision Making +1

Tighter Bound Estimation of Sensitivity Analysis for Incremental and Decremental Data Modification

no code implementations6 Mar 2020 Kaichen Zhou, Shiji Song, Gao Huang, Wu Cheng, Quan Zhou

Specifically, the proposed algorithm can be used to estimate the upper and lower bounds of the updated classifier's coefficient matrix with a low computational complexity related to the size of the updated dataset.

Incremental Learning L2 Regularization

A selected review on reinforcement learning based control for autonomous underwater vehicles

no code implementations27 Nov 2019 Ya-Chu Hsu, Hui Wu, Keyou You, Shiji Song

This paper provides a selected review on RL based control for AUVs with the focus on applications of RL to low-level control tasks for underwater regulation and tracking.


Implicit Semantic Data Augmentation for Deep Networks

1 code implementation NeurIPS 2019 Yulin Wang, Xuran Pan, Shiji Song, Hong Zhang, Cheng Wu, Gao Huang

Our work is motivated by the intriguing property that deep networks are surprisingly good at linearizing features, such that certain directions in the deep feature space correspond to meaningful semantic transformations, e. g., adding sunglasses or changing backgrounds.

Image Augmentation

Multi Pseudo Q-learning Based Deterministic Policy Gradient for Tracking Control of Autonomous Underwater Vehicles

no code implementations7 Sep 2019 Wenjie Shi, Shiji Song, Cheng Wu, C. L. Philip Chen

Different from existing policy gradient methods which employ single actor-critic but cannot realize satisfactory tracking control accuracy and stable learning, our proposed algorithm can achieve high-level tracking control accuracy of AUVs and stable learning by applying a hybrid actors-critics architecture, where multiple actors and critics are trained to learn a deterministic policy and action-value function, respectively.

Policy Gradient Methods Q-Learning

Soft Policy Gradient Method for Maximum Entropy Deep Reinforcement Learning

no code implementations7 Sep 2019 Wenjie Shi, Shiji Song, Cheng Wu

Then, we present an off-policy actor-critic, model-free maximum entropy deep RL algorithm called deep soft policy gradient (DSPG) by combining soft policy gradient with soft Bellman equation.


Regularized Anderson Acceleration for Off-Policy Deep Reinforcement Learning

1 code implementation NeurIPS 2019 Wenjie Shi, Shiji Song, Hui Wu, Ya-Chu Hsu, Cheng Wu, Gao Huang

To tackle this problem, we propose a general acceleration method for model-free, off-policy deep RL algorithms by drawing the idea underlying regularized Anderson acceleration (RAA), which is an effective approach to accelerating the solving of fixed point problems with perturbations.


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