Search Results for author: Tianfu Wu

Found 52 papers, 22 papers with code

High Resolution and Fast Face Completion via Progressively Attentive GANs

no code implementations ICLR 2019 Zeyuan Chen, Shaoliang Nie, Tianfu Wu, Christopher G. Healey

Face completion is a challenging task with the difficulty level increasing significantly with respect to high resolution, the complexity of "holes" and the controllable attributes of filled-in fragments.

Facial Inpainting Vocal Bursts Intensity Prediction

CGBA: Curvature-aware Geometric Black-box Attack

1 code implementation6 Aug 2023 Md Farhamdur Reza, Ali Rahmati, Tianfu Wu, Huaiyu Dai

While the proposed CGBA attack can work effectively for an arbitrary decision boundary, it is particularly efficient in exploiting the low curvature to craft high-quality adversarial examples, which is widely seen and experimentally verified in commonly used classifiers under non-targeted attacks.

Volumetric Wireframe Parsing from Neural Attraction Fields

1 code implementation14 Jul 2023 Nan Xue, Bin Tan, Yuxi Xiao, Liang Dong, Gui-Song Xia, Tianfu Wu

Benefitting from our explicit modeling of 3D junctions, we finally compute the primal sketch of 3D wireframes by attracting the queried 3D line segments to the 3D junctions, significantly simplifying the computation paradigm of 3D wireframe parsing.

3D Wireframe Reconstruction

Implicit Bayes Adaptation: A Collaborative Transport Approach

no code implementations17 Apr 2023 Bo Jiang, Hamid Krim, Tianfu Wu, Derya Cansever

We integrate a metric correction term as well as a prior cluster structure in the source data of the OT-driven adaptation.

Unsupervised Domain Adaptation

Monocular 3D Object Detection with Bounding Box Denoising in 3D by Perceiver

no code implementations3 Apr 2023 Xianpeng Liu, Ce Zheng, Kelvin Cheng, Nan Xue, Guo-Jun Qi, Tianfu Wu

Motivated by a new and strong observation that this challenge can be remedied by a 3D-space local-grid search scheme in an ideal case, we propose a stage-wise approach, which combines the information flow from 2D-to-3D (3D bounding box proposal generation with a single 2D image) and 3D-to-2D (proposal verification by denoising with 3D-to-2D contexts) in a top-down manner.

Denoising Monocular 3D Object Detection +1

Learning to Grow Artificial Hippocampi in Vision Transformers for Resilient Lifelong Learning

no code implementations14 Mar 2023 Chinmay Savadikar, Michelle Dai, Tianfu Wu

This paper presents a method of learning to grow ArtiHippo in Vision Transformers (ViTs) for resilient lifelong learning.

Neural Architecture Search

NOPE-SAC: Neural One-Plane RANSAC for Sparse-View Planar 3D Reconstruction

1 code implementation30 Nov 2022 Bin Tan, Nan Xue, Tianfu Wu, Gui-Song Xia

This paper studies the challenging two-view 3D reconstruction in a rigorous sparse-view configuration, which is suffering from insufficient correspondences in the input image pairs for camera pose estimation.

3D Reconstruction Pose Estimation

Level-S$^2$fM: Structure from Motion on Neural Level Set of Implicit Surfaces

1 code implementation CVPR 2023 Yuxi Xiao, Nan Xue, Tianfu Wu, Gui-Song Xia

This paper presents a neural incremental Structure-from-Motion (SfM) approach, Level-S$^2$fM, which estimates the camera poses and scene geometry from a set of uncalibrated images by learning coordinate MLPs for the implicit surfaces and the radiance fields from the established keypoint correspondences.

3D Reconstruction Neural Rendering +1

Holistically-Attracted Wireframe Parsing: From Supervised to Self-Supervised Learning

1 code implementation24 Oct 2022 Nan Xue, Tianfu Wu, Song Bai, Fu-Dong Wang, Gui-Song Xia, Liangpei Zhang, Philip H. S. Torr

This article presents Holistically-Attracted Wireframe Parsing (HAWP), a method for geometric analysis of 2D images containing wireframes formed by line segments and junctions.

Self-Supervised Learning Wireframe Parsing

HoW-3D: Holistic 3D Wireframe Perception from a Single Image

1 code implementation15 Aug 2022 Wenchao Ma, Bin Tan, Nan Xue, Tianfu Wu, Xianwei Zheng, Gui-Song Xia

This paper studies the problem of holistic 3D wireframe perception (HoW-3D), a new task of perceiving both the visible 3D wireframes and the invisible ones from single-view 2D images.

Refining Self-Supervised Learning in Imaging: Beyond Linear Metric

no code implementations25 Feb 2022 Bo Jiang, Hamid Krim, Tianfu Wu, Derya Cansever

We introduce in this paper a new statistical perspective, exploiting the Jaccard similarity metric, as a measure-based metric to effectively invoke non-linear features in the loss of self-supervised contrastive learning.

Contrastive Learning Self-Supervised Learning

Learning Spatially-Adaptive Squeeze-Excitation Networks for Image Synthesis and Image Recognition

1 code implementation29 Dec 2021 Jianghao Shen, Tianfu Wu

For image recognition tasks, the proposed SASE is used as a drop-in replacement for convolution layers in ResNets and achieves much better accuracy than the vanilla ResNets, and slightly better than the MHSA counterparts such as the Swin-Transformer and Pyramid-Transformer in the ImageNet-1000 dataset, with significantly smaller models.

Image Classification Image Generation +2

Learning Auxiliary Monocular Contexts Helps Monocular 3D Object Detection

2 code implementations9 Dec 2021 Xianpeng Liu, Nan Xue, Tianfu Wu

It presents the MonoCon method which learns Monocular Contexts, as auxiliary tasks in training, to help monocular 3D object detection.

Monocular 3D Object Detection object-detection +1

Towards Adversarially Robust and Domain Generalizable Stereo Matching by Rethinking DNN Feature Backbones

no code implementations31 Jul 2021 Kelvin Cheng, Christopher Healey, Tianfu Wu

Although it has been well-known that DNNs often suffer from adversarial vulnerability with a catastrophic drop in performance, the situation is even worse in stereo matching.

Adversarial Robustness Stereo Matching

PlaneTR: Structure-Guided Transformers for 3D Plane Recovery

no code implementations ICCV 2021 Bin Tan, Nan Xue, Song Bai, Tianfu Wu, Gui-Song Xia

This paper presents a neural network built upon Transformers, namely PlaneTR, to simultaneously detect and reconstruct planes from a single image.

Deep Consensus Learning

no code implementations15 Mar 2021 Wei Sun, Tianfu Wu

For the real image corresponding to the input layout, its mask also is computed by the inference network, and then used by the generator to reconstruct the real image.

Image Generation Semantic Segmentation

Local Clustering with Mean Teacher for Semi-supervised Learning

1 code implementation20 Apr 2020 Zexi Chen, Benjamin Dutton, Bharathkumar Ramachandra, Tianfu Wu, Ranga Raju Vatsavai

In MT, each data point is considered independent of other points during training; however, data points are likely to be close to each other in feature space if they share similar features.


Learning Layout and Style Reconfigurable GANs for Controllable Image Synthesis

3 code implementations25 Mar 2020 Wei Sun, Tianfu Wu

This paper focuses on a recent emerged task, layout-to-image, to learn generative models that are capable of synthesizing photo-realistic images from spatial layout (i. e., object bounding boxes configured in an image lattice) and style (i. e., structural and appearance variations encoded by latent vectors).

Layout-to-Image Generation

Holistically-Attracted Wireframe Parsing

1 code implementation CVPR 2020 Nan Xue, Tianfu Wu, Song Bai, Fu-Dong Wang, Gui-Song Xia, Liangpei Zhang, Philip H. S. Torr

For computing line segment proposals, a novel exact dual representation is proposed which exploits a parsimonious geometric reparameterization for line segments and forms a holistic 4-dimensional attraction field map for an input image.

Line Segment Detection Wireframe Parsing

Stochastic-Sign SGD for Federated Learning with Theoretical Guarantees

no code implementations25 Feb 2020 Richeng Jin, Yufan Huang, Xiaofan He, Huaiyu Dai, Tianfu Wu

We present Stochastic-Sign SGD which utilizes novel stochastic-sign based gradient compressors enabling the aforementioned properties in a unified framework.

Federated Learning Quantization

Learning Regional Attraction for Line Segment Detection

no code implementations18 Dec 2019 Nan Xue, Song Bai, Fu-Dong Wang, Gui-Song Xia, Tianfu Wu, Liangpei Zhang, Philip H. S. Torr

Given a line segment map, the proposed regional attraction first establishes the relationship between line segments and regions in the image lattice.

Line Segment Detection

Towards Interpretable Object Detection by Unfolding Latent Structures

no code implementations ICCV 2019 Tianfu Wu, Xi Song

The proposed method focuses on weakly-supervised extractive rationale generation, that is learning to unfold latent discriminative part configurations of object instances automatically and simultaneously in detection without using any supervision for part configurations.

object-detection Object Detection

Towards Controllable and Interpretable Face Completion via Structure-Aware and Frequency-Oriented Attentive GANs

no code implementations25 Sep 2019 Zeyuan Chen, Shaoliang Nie, Tianfu Wu, Christopher G. Healey

The proposed frequency-oriented attentive module (FOAM) encourages GANs to attend to only finer details in the coarse-to-fine progressive training, thus enabling progressive attention to face structures.

Facial Inpainting

Inducing Hierarchical Compositional Model by Sparsifying Generator Network

no code implementations CVPR 2020 Xianglei Xing, Tianfu Wu, Song-Chun Zhu, Ying Nian Wu

To realize this AND-OR hierarchy in image synthesis, we learn a generator network that consists of the following two components: (i) Each layer of the hierarchy is represented by an over-complete set of convolutional basis functions.

Image Generation Image Reconstruction

Image Synthesis From Reconfigurable Layout and Style

4 code implementations ICCV 2019 Wei Sun, Tianfu Wu

Despite remarkable recent progress on both unconditional and conditional image synthesis, it remains a long-standing problem to learn generative models that are capable of synthesizing realistic and sharp images from reconfigurable spatial layout (i. e., bounding boxes + class labels in an image lattice) and style (i. e., structural and appearance variations encoded by latent vectors), especially at high resolution.

Layout-to-Image Generation

Attentive Normalization

2 code implementations ECCV 2020 Xilai Li, Wei Sun, Tianfu Wu

In state-of-the-art deep neural networks, both feature normalization and feature attention have become ubiquitous.

Image Classification Instance Segmentation +3

Adversarial Distillation for Ordered Top-k Attacks

no code implementations25 May 2019 Zekun Zhang, Tianfu Wu

One scheme of learning attacks is to design a proper adversarial objective function that leads to the imperceptible perturbation for any test image (e. g., the Carlini-Wagner (C&W) method).

Image Classification

Learn to Grow: A Continual Structure Learning Framework for Overcoming Catastrophic Forgetting

no code implementations31 Mar 2019 Xilai Li, Yingbo Zhou, Tianfu Wu, Richard Socher, Caiming Xiong

Addressing catastrophic forgetting is one of the key challenges in continual learning where machine learning systems are trained with sequential or streaming tasks.

Continual Learning Neural Architecture Search +1

Learning Spatial Pyramid Attentive Pooling in Image Synthesis and Image-to-Image Translation

no code implementations18 Jan 2019 Wei Sun, Tianfu Wu

In experiments, the proposed SPAP is tested in GANs on the Celeba-HQ-128 dataset~\cite{karras2017progressive}, and tested in CycleGANs on the Image-to-Image translation datasets including the Cityscape dataset~\cite{cordts2016cityscapes}, Facade and Aerial Maps dataset~\cite{zhu2017unpaired}, both obtaining better performance.

Image-to-Image Translation Translation

Neural Abstract Style Transfer for Chinese Traditional Painting

1 code implementation8 Dec 2018 Bo Li, Caiming Xiong, Tianfu Wu, Yu Zhou, Lun Zhang, Rufeng Chu

In experiments, the proposed method shows more appealing stylized results in transferring the style of Chinese traditional painting than state-of-the-art neural style transfer methods.

Style Transfer

Relational Long Short-Term Memory for Video Action Recognition

no code implementations16 Nov 2018 Zexi Chen, Bharathkumar Ramachandra, Tianfu Wu, Ranga Raju Vatsavai

By doing this, our Relational LSTM is capable of capturing long and short-range spatio-temporal relations between objects in videos in a principled way.

Action Recognition Temporal Action Localization

ARCHER: Aggressive Rewards to Counter bias in Hindsight Experience Replay

1 code implementation6 Sep 2018 Sameera Lanka, Tianfu Wu

Experience replay is an important technique for addressing sample-inefficiency in deep reinforcement learning (RL), but faces difficulty in learning from binary and sparse rewards due to disproportionately few successful experiences in the replay buffer.

Continuous Control Reinforcement Learning (RL)

Auto-Context R-CNN

no code implementations8 Jul 2018 Bo Li, Tianfu Wu, Lun Zhang, Rufeng Chu

Although surrounding context is well-known for its importance in object detection, it has yet been integrated in R-CNNs in a flexible and effective way.

object-detection Object Detection

High Resolution Face Completion with Multiple Controllable Attributes via Fully End-to-End Progressive Generative Adversarial Networks

no code implementations23 Jan 2018 Zeyuan Chen, Shaoliang Nie, Tianfu Wu, Christopher G. Healey

It is a challenging task with the difficulty level increasing significantly with respect to high resolution, the complexity of "holes" and the controllable attributes of filled-in fragments.

Facial Inpainting

AOGNets: Compositional Grammatical Architectures for Deep Learning

4 code implementations CVPR 2019 Xilai Li, Xi Song, Tianfu Wu

This paper presents deep compositional grammatical architectures which harness the best of two worlds: grammar models and DNNs.

Adversarial Defense Image Classification +3

Towards Interpretable R-CNN by Unfolding Latent Structures

1 code implementation14 Nov 2017 Tianfu Wu, Wei Sun, Xilai Li, Xi Song, Bo Li

We focus on weakly-supervised extractive rationale generation, that is learning to unfold latent discriminative part configurations of object instances automatically and simultaneously in detection without using any supervision for part configurations.

object-detection Object Detection

Scene-centric Joint Parsing of Cross-view Videos

no code implementations16 Sep 2017 Hang Qi, Yuanlu Xu, Tao Yuan, Tianfu Wu, Song-Chun Zhu

The proposed joint parsing framework represents such correlations and constraints explicitly and generates semantic scene-centric parse graphs.

Video Understanding

An Attention-Driven Approach of No-Reference Image Quality Assessment

no code implementations12 Dec 2016 Diqi Chen, Yizhou Wang, Tianfu Wu, Wen Gao

The model learning is implemented by a reinforcement strategy, in which the rewards of both tasks guide the learning of the optimal sampling policy to acquire the "task-informative" image regions so that the predictions can be made accurately and efficiently (in terms of the sampling steps).

Multi-Task Learning No-Reference Image Quality Assessment +1

Zero-Shot Learning posed as a Missing Data Problem

no code implementations2 Dec 2016 Bo Zhao, Botong Wu, Tianfu Wu, Yizhou Wang

This paper presents a method of zero-shot learning (ZSL) which poses ZSL as the missing data problem, rather than the missing label problem.

Zero-Shot Learning

Object Detection via Aspect Ratio and Context Aware Region-based Convolutional Networks

no code implementations2 Dec 2016 Bo Li, Tianfu Wu, Shuai Shao, Lun Zhang, Rufeng Chu

This paper presents a method of integrating a mixture of object models and region-based convolutional networks for accurate object detection.

object-detection Object Detection

Face Detection with End-to-End Integration of a ConvNet and a 3D Model

2 code implementations2 Jun 2016 Yunzhu Li, Benyuan Sun, Tianfu Wu, Yizhou Wang

The proposed method addresses two issues in adapting state- of-the-art generic object detection ConvNets (e. g., faster R-CNN) for face detection: (i) One is to eliminate the heuristic design of prede- fined anchor boxes in the region proposals network (RPN) by exploit- ing a 3D mean face model.

Face Detection Face Model +3

Recognizing Car Fluents from Video

no code implementations CVPR 2016 Bo Li, Tianfu Wu, Caiming Xiong, Song-Chun Zhu

Since there are no publicly related dataset, we collect and annotate a car fluent dataset consisting of car videos with diverse fluents.

A Restricted Visual Turing Test for Deep Scene and Event Understanding

no code implementations6 Dec 2015 Hang Qi, Tianfu Wu, Mun-Wai Lee, Song-Chun Zhu

and a sequence of story-line based queries, the task is to provide answers either simply in binary form "true/false" (to a polar query) or in an accurate natural language description (to a non-polar query).

Question Answering Video Captioning +1

Online Object Tracking, Learning and Parsing with And-Or Graphs

1 code implementation CVPR 2014 Tianfu Wu, Yang Lu, Song-Chun Zhu

In the former, our AOGTracker outperforms state-of-the-art tracking algorithms including two trackers based on deep convolutional network.

Object Tracking

Learning And-Or Models to Represent Context and Occlusion for Car Detection and Viewpoint Estimation

no code implementations29 Jan 2015 Tianfu Wu, Bo Li, Song-Chun Zhu

Firstly, the structure of the And-Or model is learned with three components: (a) mining multi-car contextual patterns based on layouts of annotated single car bounding boxes, (b) mining occlusion configurations between single cars, and (c) learning different combinations of part visibility based on car 3D CAD simulation.

Viewpoint Estimation

Discriminatively Trained And-Or Tree Models for Object Detection

no code implementations CVPR 2013 Xi Song, Tianfu Wu, Yunde Jia, Song-Chun Zhu

This paper presents a method of learning reconfigurable And-Or Tree (AOT) models discriminatively from weakly annotated data for object detection.

object-detection Object Detection

Learning Mixtures of Bernoulli Templates by Two-Round EM with Performance Guarantee

no code implementations2 May 2013 Adrian Barbu, Tianfu Wu, Ying Nian Wu

Each template is a binary vector, and a template generates examples by randomly switching its binary components independently with a certain probability.

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