arXiv subjects

Yanchao Yang

Publications and source records attributed to Yanchao Yang.

67 records · Page 4Linked to original sources

arXiv2022

DCL: Differential Contrastive Learning for Geometry-Aware Depth Synthesis

We describe a method for unpaired realistic depth synthesis that learns diverse variations from the real-world depth scans and ensures geometric consistency between the synthetic and synthesized depth. The synthesized realistic depth can then be used to train task-specific networks facilitating label transfer from the synthetic domain. Unlike existing image synthesis pipelines, where geometries are mostly ignored, we treat geometries carried by the depth scans based on their own existence. We propose differential contrastive learning that explicitly enforces the underlying geometric properties to be invariant regarding the real variations been learned. The resulting depth synthesis method is task-agnostic, and we demonstrate the effectiveness of the proposed synthesis method by extensive evaluations on real-world geometric reasoning tasks. The networks trained with the depth synthesized by our method consistently achieve better performance across a wide range of tasks than state of the art, and can even surpass the networks supervised with full real-world annotations when slightly fine-tuned, showing good transferability.

cs.CV↗

arXiv2021

Domain Adaptation on Point Clouds via Geometry-Aware Implicits

As a popular geometric representation, point clouds have attracted much attention in 3D vision, leading to many applications in autonomous driving and robotics. One important yet unsolved issue for learning on point cloud is that point clouds of the same object can have significant geometric variations if generated using different procedures or captured using different sensors. These inconsistencies induce domain gaps such that neural networks trained on one domain may fail to generalize on others. A typical technique to reduce the domain gap is to perform adversarial training so that point clouds in the feature space can align. However, adversarial training is easy to fall into degenerated local minima, resulting in negative adaptation gains. Here we propose a simple yet effective method for unsupervised domain adaptation on point clouds by employing a self-supervised task of learning geometry-aware implicits, which plays two critical roles in one shot. First, the geometric information in the point clouds is preserved through the implicit representations for downstream tasks. More importantly, the domain-specific variations can be effectively learned away in the implicit space. We also propose an adaptive strategy to compute unsigned distance fields for arbitrary point clouds due to the lack of shape models in practice. When combined with a task loss, the proposed outperforms state-of-the-art unsupervised domain adaptation methods that rely on adversarial domain alignment and more complicated self-supervised tasks. Our method is evaluated on both PointDA-10 and GraspNet datasets. The code and trained models will be publicly available.

cs.CV↗

arXiv2021

ADeLA: Automatic Dense Labeling with Attention for Viewpoint Adaptation in Semantic Segmentation

We describe an unsupervised domain adaptation method for image content shift caused by viewpoint changes for a semantic segmentation task. Most existing methods perform domain alignment in a shared space and assume that the mapping from the aligned space to the output is transferable. However, the novel content induced by viewpoint changes may nullify such a space for effective alignments, thus resulting in negative adaptation. Our method works without aligning any statistics of the images between the two domains. Instead, it utilizes a view transformation network trained only on color images to hallucinate the semantic images for the target. Despite the lack of supervision, the view transformation network can still generalize to semantic images thanks to the inductive bias introduced by the attention mechanism. Furthermore, to resolve ambiguities in converting the semantic images to semantic labels, we treat the view transformation network as a functional representation of an unknown mapping implied by the color images and propose functional label hallucination to generate pseudo-labels in the target domain. Our method surpasses baselines built on state-of-the-art correspondence estimation and view synthesis methods. Moreover, it outperforms the state-of-the-art unsupervised domain adaptation methods that utilize self-training and adversarial domain alignment. Our code and dataset will be made publicly available.

cs.CV↗

arXiv2021

Learning Semantic-Aware Dynamics for Video Prediction

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 synthesized 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.

cs.CV↗

arXiv2021

DyStaB: Unsupervised Object Segmentation via Dynamic-Static Bootstrapping

We describe an unsupervised method to detect and segment portions of images of live scenes that, at some point in time, are seen moving as a coherent whole, which we refer to as objects. Our method first partitions the motion field by minimizing the mutual information between segments. Then, it uses the segments to learn object models that can be used for detection in a static image. Static and dynamic models are represented by deep neural networks trained jointly in a bootstrapping strategy, which enables extrapolation to previously unseen objects. While the training process requires motion, the resulting object segmentation network can be used on either static images or videos at inference time. As the volume of seen videos grows, more and more objects are seen moving, priming their detection, which then serves as a regularizer for new objects, turning our method into unsupervised continual learning to segment objects. Our models are compared to the state of the art in both video object segmentation and salient object detection. In the six benchmark datasets tested, our models compare favorably even to those using pixel-level supervision, despite requiring no manual annotation.

cs.CV↗

arXiv2020

Learning to Manipulate Individual Objects in an Image

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 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.

cs.CV↗

arXiv2020

FDA: Fourier Domain Adaptation for Semantic Segmentation

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 neural 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.

cs.CV↗

arXiv2020

Phase Consistent Ecological Domain Adaptation

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 restricts 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.

cs.CV↗

arXiv2019

Dense Depth Posterior (DDP) from Single Image and Sparse Range

We present a deep learning system to infer the posterior distribution of a dense depth map associated with an image, by exploiting sparse range measurements, for instance from a lidar. While the lidar may provide a depth value for a small percentage of the pixels, we exploit regularities reflected in the training set to complete the map so as to have a probability over depth for each pixel in the image. We exploit a Conditional Prior Network, that allows associating a probability to each depth value given an image, and combine it with a likelihood term that uses the sparse measurements. Optionally we can also exploit the availability of stereo during training, but in any case only require a single image and a sparse point cloud at run-time. We test our approach on both unsupervised and supervised depth completion using the KITTI benchmark, and improve the state-of-the-art in both.

cs.CV↗

arXiv2019

Unsupervised Moving Object Detection via Contextual Information Separation

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 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.

cs.CV↗

arXiv2018

Conditional Prior Networks for Optical Flow

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 learn 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.

cs.CV↗

arXiv2013

Shape Tracking With Occlusions via Coarse-To-Fine Region-Based Sobolev Descent

We present a method to track the precise shape of an object in video based on new modeling and optimization on a new Riemannian manifold of parameterized regions. Joint dynamic shape and appearance models, in which a template of the object is propagated to match the object shape and radiance in the next frame, are advantageous over methods employing global image statistics in cases of complex object radiance and cluttered background. In cases of 3D object motion and viewpoint change, self-occlusions and dis-occlusions of the object are prominent, and current methods employing joint shape and appearance models are unable to adapt to new shape and appearance information, leading to inaccurate shape detection. In this work, we model self-occlusions and dis-occlusions in a joint shape and appearance tracking framework. Self-occlusions and the warp to propagate the template are coupled, thus a joint problem is formulated. We derive a coarse-to-fine optimization scheme, advantageous in object tracking, that initially perturbs the template by coarse perturbations before transitioning to finer-scale perturbations, traversing all scales, seamlessly and automatically. The scheme is a gradient descent on a novel infinite-dimensional Riemannian manifold that we introduce. The manifold consists of planar parameterized regions, and the metric that we introduce is a novel Sobolev-type metric defined on infinitesimal vector fields on regions. The metric has the property of resulting in a gradient descent that automatically favors coarse-scale deformations (when they reduce the energy) before moving to finer-scale deformations. Experiments on video exhibiting occlusion/dis-occlusion, complex radiance and background show that occlusion/dis-occlusion modeling leads to superior shape accuracy compared to recent methods employing joint shape/appearance models or employing global statistics.

cs.CV↗

arXiv2012

Matching Through Features and Features Through Matching

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 between 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.

cs.CV↗