Filters








360 Hits in 1.3 sec

Phase Consistent Ecological Domain Adaptation [article]

Yanchao Yang, Dong Lao, Ganesh Sundaramoorthi, Stefano Soatto
2020 arXiv   pre-print
We introduce two criteria to regularize the optimization involved in learning a classifier in a domain where no annotated data are available, leveraging annotated data in a different domain, a problem known as unsupervised domain adaptation. We focus on the task of semantic segmentation, where annotated synthetic data are aplenty, but annotating real data is laborious. The first criterion, inspired by visual psychophysics, is that the map between the two image domains be phase-preserving. This
more » ... estricts the set of possible learned maps, while enabling enough flexibility to transfer semantic information. The second criterion aims to leverage ecological statistics, or regularities in the scene which are manifest in any image of it, regardless of the characteristics of the illuminant or the imaging sensor. It is implemented using a deep neural network that scores the likelihood of each possible segmentation given a single un-annotated image. Incorporating these two priors in a standard domain adaptation framework improves performance across the board in the most common unsupervised domain adaptation benchmarks for semantic segmentation.
arXiv:2004.04923v1 fatcat:kt5qeiilivavpbfavsxjem56by

Matching Through Features and Features Through Matching [article]

Ganesh Sundaramoorthi, Yanchao Yang
2012 arXiv   pre-print
This paper addresses how to construct features for the problem of image correspondence, in particular, the paper addresses how to construct features so as to maintain the right level of invariance versus discriminability. We show that without additional prior knowledge of the 3D scene, the right tradeoff cannot be established in a pre-processing step of the images as is typically done in most feature-based matching methods. However, given knowledge of the second image to match, the tradeoff
more » ... een invariance and discriminability of features in the first image is less ambiguous. This suggests to setup the problem of feature extraction and matching as a joint estimation problem. We develop a possible mathematical framework, a possible computational algorithm, and we give example demonstration on finding correspondence on images related by a scene that undergoes large 3D deformation of non-planar objects and camera viewpoint change.
arXiv:1211.4771v1 fatcat:av2htfcgrzhrllm3wtzpljgfa4

FDA: Fourier Domain Adaptation for Semantic Segmentation [article]

Yanchao Yang, Stefano Soatto
2020 arXiv   pre-print
We describe a simple method for unsupervised domain adaptation, whereby the discrepancy between the source and target distributions is reduced by swapping the low-frequency spectrum of one with the other. We illustrate the method in semantic segmentation, where densely annotated images are aplenty in one domain (synthetic data), but difficult to obtain in another (real images). Current state-of-the-art methods are complex, some requiring adversarial optimization to render the backbone of a
more » ... l network invariant to the discrete domain selection variable. Our method does not require any training to perform the domain alignment, just a simple Fourier Transform and its inverse. Despite its simplicity, it achieves state-of-the-art performance in the current benchmarks, when integrated into a relatively standard semantic segmentation model. Our results indicate that even simple procedures can discount nuisance variability in the data that more sophisticated methods struggle to learn away.
arXiv:2004.05498v1 fatcat:zdxfmemryjextggcml3cceylgq

Learning Semantic-Aware Dynamics for Video Prediction [article]

Xinzhu Bei, Yanchao Yang, Stefano Soatto
2021 arXiv   pre-print
We propose an architecture and training scheme to predict video frames by explicitly modeling dis-occlusions and capturing the evolution of semantically consistent regions in the video. The scene layout (semantic map) and motion (optical flow) are decomposed into layers, which are predicted and fused with their context to generate future layouts and motions. The appearance of the scene is warped from past frames using the predicted motion in co-visible regions; dis-occluded regions are
more » ... ed with content-aware inpainting utilizing the predicted scene layout. The result is a predictive model that explicitly represents objects and learns their class-specific motion, which we evaluate on video prediction benchmarks.
arXiv:2104.09762v1 fatcat:rzbewbus4zftpn6cu4e6asfoi4

Collaborative Inference of Coexisting Information Diffusions [article]

Yanchao Sun, Cong Qian, Ning Yang, Philip S. Yu
2017 arXiv   pre-print
The existing methods, however, often focus only on single information * Ning Yang is the corresponding author. diffusion trace, while in a real-world social network, there often coexist multiple diffusions  ... 
arXiv:1708.06890v1 fatcat:5uoyjdmbznbzngqrmczcsdj7my

Learning to Manipulate Individual Objects in an Image [article]

Yanchao Yang, Yutong Chen, Stefano Soatto
2020 arXiv   pre-print
We describe a method to train a generative model with latent factors that are (approximately) independent and localized. This means that perturbing the latent variables affects only local regions of the synthesized image, corresponding to objects. Unlike other unsupervised generative models, ours enables object-centric manipulation, without requiring object-level annotations, or any form of annotation for that matter. The key to our method is the combination of spatial disentanglement, enforced
more » ... by a Contextual Information Separation loss, and perceptual cycle-consistency, enforced by a loss that penalizes changes in the image partition in response to perturbations of the latent factors. We test our method's ability to allow independent control of spatial and semantic factors of variability on existing datasets and also introduce two new ones that highlight the limitations of current methods.
arXiv:2004.05495v1 fatcat:htsvypj2dzcqzpb3b3vhdpr6li

GIMO: Gaze-Informed Human Motion Prediction in Context [article]

Yang Zheng, Yanchao Yang, Kaichun Mo, Jiaman Li, Tao Yu, Yebin Liu, Karen Liu, Leonidas J. Guibas
2022 arXiv   pre-print
Predicting human motion is critical for assistive robots and AR/VR applications, where the interaction with humans needs to be safe and comfortable. Meanwhile, an accurate prediction depends on understanding both the scene context and human intentions. Even though many works study scene-aware human motion prediction, the latter is largely underexplored due to the lack of ego-centric views that disclose human intent and the limited diversity in motion and scenes. To reduce the gap, we propose a
more » ... arge-scale human motion dataset that delivers high-quality body pose sequences, scene scans, as well as ego-centric views with eye gaze that serves as a surrogate for inferring human intent. By employing inertial sensors for motion capture, our data collection is not tied to specific scenes, which further boosts the motion dynamics observed from our subjects. We perform an extensive study of the benefits of leveraging eye gaze for ego-centric human motion prediction with various state-of-the-art architectures. Moreover, to realize the full potential of gaze, we propose a novel network architecture that enables bidirectional communication between the gaze and motion branches. Our network achieves the top performance in human motion prediction on the proposed dataset, thanks to the intent information from the gaze and the denoised gaze feature modulated by the motion. The proposed dataset and our network implementation will be publicly available.
arXiv:2204.09443v1 fatcat:oks4nca3ebbz7o36xqoygsnteq

Conditional Prior Networks for Optical Flow [chapter]

Yanchao Yang, Stefano Soatto
2018 Lecture Notes in Computer Science  
Classical computation of optical flow involves generic priors (regularizers) that capture rudimentary statistics of images, but not long-range correlations or semantics. On the other hand, fully supervised methods learn the regularity in the annotated data, without explicit regularization and with the risk of overfitting. We seek to learn richer priors on the set of possible flows that are statistically compatible with an image. Once the prior is learned in a supervised fashion, one can easily
more » ... earn the full map to infer optical flow directly from two or more images, without any need for (additional) supervision. We introduce a novel architecture, called Conditional Prior Network (CPN), and show how to train it to yield a conditional prior. When used in conjunction with a simple optical flow architecture, the CPN beats all variational methods and all unsupervised learning-based ones using the same data term. It performs comparably to fully supervised ones, that however are fine-tuned to a particular dataset. Our method, on the other hand, performs well even when transferred between datasets.
doi:10.1007/978-3-030-01267-0_17 fatcat:q4z7topa7vaa3hftp22zyyxalq

DyStaB: Unsupervised Object Segmentation via Dynamic-Static Bootstrapping [article]

Yanchao Yang, Brian Lai, Stefano Soatto
2021 arXiv   pre-print
IEEE, 2017. 3, 8 [26] Huaizu Jiang, Jingdong Wang, Zejian Yuan, Yang Wu, Nanning Zheng, and Shipeng Li. Salient object detection: A discriminative regional feature integration approach.  ... 
arXiv:2008.07012v2 fatcat:ofh5xvyipnak7kaxagz4jlv7ny

Zeeman effect in centrosymmetric antiferromagnets controlled by electric field [article]

Hong Jian Zhao, Xinran Liu, Yanchao Wang, Yurong Yang, Laurent Bellaiche, Yanming Ma
2022 arXiv   pre-print
Centrosymmetric antiferromagnets, although abundant in nature, seem less promising than ferromagnets or ferroelectrics for practical applications in semiconductor spintronics. As a matter of fact, the lack of spontaneous polarization and magnetization hinders the efficient utilization of electronic spin in these materials. Here, we propose a paradigm to harness electronic spin in centrosymmetric antiferromagnets via Zeeman spin splittings of electronic energy levels – termed as spin Zeeman
more » ... t – which is controlled by an electric field. By symmetry analysis, we identify twenty-one centrosymmetric antiferromagnetic point groups that accommodate such a spin Zeeman effect. We further predicted by first-principles that near-room temperature antiferromagnetic SrFe_2S_2O is an excellent candidate showcasing a Zeeman splitting as large as ∼75 meV, induced by an electric field of 0.15 V/Å. Moreover, the electronic spin magnetization associated to the split energy levels is switchable when reversing the electric field. Our work thus sheds light on the electric-field control of electronic spin in antiferromagnets, which broadens the scope of application of centrosymmetric antiferromagnets.
arXiv:2204.07264v1 fatcat:77qmwiblbfei7gratggtdzi6he

Application of BIM Technology in Prefabricated Housing Design

Zhao Yanchao, G. Yang, M. Ziegler
2020 E3S Web of Conferences  
BIM technology applied to the architectural design industry builds a more efficient and scientific building structure model. BIM also improves the design quality of construction projects and ensures the safety and efficiency of building construction. According to the actual situation of a prefabricated residential project, this paper analyzes the BIM design and combination of architecture, structure and equipment on the basis of module system, and puts forward collaborative design and house
more » ... split mode. The target is to provide reliable reference for BIM design of similar projects.
doi:10.1051/e3sconf/202019803017 fatcat:zpfkqef5pzhxtofditbqvhxgfi

S2F: Slow-to-Fast Interpolator Flow

Yanchao Yang, Stefano Soatto
2017 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)  
We introduce a method to compute optical flow at multiple scales of motion, without resorting to multiresolution or combinatorial methods. It addresses the key problem of small objects moving fast, and resolves the artificial binding between how large an object is and how fast it can move before being diffused away by classical scale-space. Even with no learning, it achieves top performance on the most challenging optical flow benchmark. Moreover, the results are interpretable, and indeed we
more » ... t the assumptions underlying our method explicitly. The key to our approach is the matching progression from slow to fast, as well as the choice of interpolation method, or equivalently the prior, to fill in regions where the data allows it. We use several offthe-shelf components, with relatively low sensitivity to parameter tuning. Computational cost is comparable to the state-of-the-art.
doi:10.1109/cvpr.2017.401 dblp:conf/cvpr/YangS17 fatcat:fx5lqepy5vd2fdunk4534svjmi

BEAS

Yang Cao, Wenfei Fan, Yanghao Wang, Tengfei Yuan, Yanchao Li, Laura Yu Chen
2017 Proceedings of the 2017 ACM International Conference on Management of Data - SIGMOD '17  
We demonstrate BEAS, a prototype system for querying relations with bounded resources. BEAS advocates an unconventional query evaluation paradigm under an access schema A, which is a combination of cardinality constraints and associated indices. Given an SQL query Q and a dataset D, BEAS computes Q(D) by accessing a bounded fraction DQ of D, such that Q(DQ) = Q(D) and DQ is determined by A and Q only, no matter how big D grows. It identifies DQ by reasoning about the cardinality constraints of
more » ... , and fetches DQ using the indices of A. We demonstrate the feasibility of bounded evaluation by walking through each functional component of BEAS. As a proof of concept, we demonstrate how BEAS conducts CDR analyses in telecommunication industry, compared with commercial database systems.
doi:10.1145/3035918.3058748 dblp:conf/sigmod/CaoFWYLC17 fatcat:eldfeyfz3rctla2tbir4tptocq

Stochastic Channel Selection in Cognitive Radio Networks

Yang Song, Yuguang Fang, Yanchao Zhang
2007 IEEE GLOBECOM 2007-2007 IEEE Global Telecommunications Conference  
In this paper, we investigate the channel selection strategy for secondary users in cognitive radio networks. We claim that in order to avoid the costly channel switchings, a secondary user may desire an optimal channel which maximizes the probability of successful transmissions, rather than consistently adapting channels to the random environment. We propose a stochastic channel selection algorithm based on the learning automata techniques. This algorithm adjusts the probability of selecting
more » ... ch available channel and converges to the -optimal solution asymptotically.
doi:10.1109/glocom.2007.925 dblp:conf/globecom/SongFZ07 fatcat:zq3h5edatbaovi4iljdi5m6olm

Unsupervised Moving Object Detection via Contextual Information Separation [article]

Yanchao Yang, Antonio Loquercio, Davide Scaramuzza, Stefano Soatto
2019 arXiv   pre-print
We propose an adversarial contextual model for detecting moving objects in images. A deep neural network is trained to predict the optical flow in a region using information from everywhere else but that region (context), while another network attempts to make such context as uninformative as possible. The result is a model where hypotheses naturally compete with no need for explicit regularization or hyper-parameter tuning. Although our method requires no supervision whatsoever, it outperforms
more » ... several methods that are pre-trained on large annotated datasets. Our model can be thought of as a generalization of classical variational generative region-based segmentation, but in a way that avoids explicit regularization or solution of partial differential equations at run-time.
arXiv:1901.03360v2 fatcat:el3fyy67kvdwjntijcwdsnu4sq
« Previous Showing results 1 — 15 out of 360 results