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.
no code implementations • ICLR 2019 • Xilai Li, Yingbo Zhou, Tianfu Wu, Richard Socher, Caiming Xiong
During structure learning, the model optimizes for the best structure for the current task.
1 code implementation • 6 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.
1 code implementation • 14 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.
no code implementations • 17 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.
no code implementations • 3 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.
no code implementations • 14 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.
1 code implementation • 30 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.
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.
1 code implementation • 24 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.
1 code implementation • 15 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.
1 code implementation • CVPR 2023 • Ryan Grainger, Thomas Paniagua, Xi Song, Naresh Cuntoor, Mun Wai Lee, Tianfu Wu
The proposed PaCa module is used in designing efficient and interpretable ViT backbones and semantic segmentation head networks.
no code implementations • 25 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.
1 code implementation • 29 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.
2 code implementations • 9 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.
Ranked #2 on
Monocular 3D Object Detection
on KITTI Cars Moderate
1 code implementation • CVPR 2022 • Nan Xue, Tianfu Wu, Gui-Song Xia, Liangpei Zhang
This paper studies the problem of multi-person pose estimation in a bottom-up fashion.
no code implementations • 31 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.
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.
no code implementations • 15 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.
1 code implementation • 20 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.
3 code implementations • 25 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).
Ranked #2 on
Layout-to-Image Generation
on COCO-Stuff 128x128
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.
Ranked #1 on
Line Segment Detection
on wireframe dataset
(FH metric)
no code implementations • 25 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.
no code implementations • 18 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.
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.
no code implementations • 25 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.
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.
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.
Ranked #2 on
Layout-to-Image Generation
on COCO-Stuff 64x64
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.
Ranked #71 on
Instance Segmentation
on COCO minival
no code implementations • 17 Jun 2019 • Wei Sun, Jawadul H. Bappy, Shanglin Yang, Yi Xu, Tianfu Wu, Hui Zhou
In order to formulate the framework, we employ one generator and two discriminators for image synthesis.
no code implementations • 25 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).
no code implementations • 31 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.
no code implementations • 18 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.
1 code implementation • 8 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.
1 code implementation • CVPR 2019 • Nan Xue, Song Bai, Fu-Dong Wang, Gui-Song Xia, Tianfu Wu, Liangpei Zhang
In experiments, our method is tested on the WireFrame dataset and the YorkUrban dataset with state-of-the-art performance obtained.
no code implementations • 16 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.
1 code implementation • 6 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.
no code implementations • 8 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.
no code implementations • 23 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.
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.
1 code implementation • 14 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.
no code implementations • 16 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.
no code implementations • 12 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
no code implementations • 2 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.
no code implementations • 2 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.
2 code implementations • 2 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.
Ranked #7 on
Face Detection
on Annotated Faces in the Wild
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.
no code implementations • 6 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).
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.
no code implementations • 29 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.
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.
no code implementations • 2 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.