arXiv subjects

Martial Hebert

Publications and source records attributed to Martial Hebert.

At least 73 records · Page 4Linked to original sources

arXiv2017

The Pose Knows: Video Forecasting by Generating Pose Futures

Current approaches in video forecasting attempt to generate videos directly in pixel space using Generative Adversarial Networks (GANs) or Variational Autoencoders (VAEs). However, since these approaches try to model all the structure and scene dynamics at once, in unconstrained settings they often generate uninterpretable results. Our insight is to model the forecasting problem at a higher level of abstraction. Specifically, we exploit human pose detectors as a free source of supervision and break the video forecasting problem into two discrete steps. First we explicitly model the high level structure of active objects in the scene---humans---and use a VAE to model the possible future movements of humans in the pose space. We then use the future poses generated as conditional information to a GAN to predict the future frames of the video in pixel space. By using the structured space of pose as an intermediate representation, we sidestep the problems that GANs have in generating video pixels directly. We show through quantitative and qualitative evaluation that our method outperforms state-of-the-art methods for video prediction.

cs.CV↗

arXiv2017

General models for rational cameras and the case of two-slit projections

The rational camera model recently introduced in [19] provides a general methodology for studying abstract nonlinear imaging systems and their multi-view geometry. This paper builds on this framework to study "physical realizations" of rational cameras. More precisely, we give an explicit account of the mapping between between physical visual rays and image points (missing in the original description), which allows us to give simple analytical expressions for direct and inverse projections. We also consider "primitive" camera models, that are orbits under the action of various projective transformations, and lead to a general notion of intrinsic parameters. The methodology is general, but it is illustrated concretely by an in-depth study of two-slit cameras, that we model using pairs of linear projections. This simple analytical form allows us to describe models for the corresponding primitive cameras, to introduce intrinsic parameters with a clear geometric meaning, and to define an epipolar tensor characterizing two-view correspondences. In turn, this leads to new algorithms for structure from motion and self-calibration.

cs.CV↗

arXiv2017

Gradient Boosting on Stochastic Data Streams

Boosting is a popular ensemble algorithm that generates more powerful learners by linearly combining base models from a simpler hypothesis class. In this work, we investigate the problem of adapting batch gradient boosting for minimizing convex loss functions to online setting where the loss at each iteration is i.i.d sampled from an unknown distribution. To generalize from batch to online, we first introduce the definition of online weak learning edge with which for strongly convex and smooth loss functions, we present an algorithm, Streaming Gradient Boosting (SGB) with exponential shrinkage guarantees in the number of weak learners. We further present an adaptation of SGB to optimize non-smooth loss functions, for which we derive a O(ln N/N) convergence rate. We also show that our analysis can extend to adversarial online learning setting under a stronger assumption that the online weak learning edge will hold in adversarial setting. We finally demonstrate experimental results showing that in practice our algorithms can achieve competitive results as classic gradient boosting while using less computation.

cs.LG↗

arXiv2016

Contextual Visual Similarity

Measuring visual similarity is critical for image understanding. But what makes two images similar? Most existing work on visual similarity assumes that images are similar because they contain the same object instance or category. However, the reason why images are similar is much more complex. For example, from the perspective of category, a black dog image is similar to a white dog image. However, in terms of color, a black dog image is more similar to a black horse image than the white dog image. This example serves to illustrate that visual similarity is ambiguous but can be made precise when given an explicit contextual perspective. Based on this observation, we propose the concept of contextual visual similarity. To be concrete, we examine the concept of contextual visual similarity in the application domain of image search. Instead of providing only a single image for image similarity search (\eg, Google image search), we require three images. Given a query image, a second positive image and a third negative image, dissimilar to the first two images, we define a contextualized similarity search criteria. In particular, we learn feature weights over all the feature dimensions of each image such that the distance between the query image and the positive image is small and their distances to the negative image are large after reweighting their features. The learned feature weights encode the contextualized visual similarity specified by the user and can be used for attribute specific image search. We also show the usefulness of our contextualized similarity weighting scheme for different tasks, such as answering visual analogy questions and unsupervised attribute discovery.

cs.CV↗

arXiv2016

Efficient Feature Group Sequencing for Anytime Linear Prediction

We consider \textit{anytime} linear prediction in the common machine learning setting, where features are in groups that have costs. We achieve anytime (or interruptible) predictions by sequencing the computation of feature groups and reporting results using the computed features at interruption. We extend Orthogonal Matching Pursuit (OMP) and Forward Regression (FR) to learn the sequencing greedily under this group setting with costs. We theoretically guarantee that our algorithms achieve near-optimal linear predictions at each budget when a feature group is chosen. With a novel analysis of OMP, we improve its theoretical bound to the same strength as that of FR. In addition, we develop a novel algorithm that consumes cost $4B$ to approximate the optimal performance of \textit{any} cost $B$, and prove that with cost less than $4B$, such an approximation is impossible. To our knowledge, these are the first anytime bounds at \textit{all} budgets. We test our algorithms on two real-world data-sets and evaluate them in terms of anytime linear prediction performance against cost-weighted Group Lasso and alternative greedy algorithms.

cs.LG↗

arXiv2016

A Discriminative Framework for Anomaly Detection in Large Videos

We address an anomaly detection setting in which training sequences are unavailable and anomalies are scored independently of temporal ordering. Current algorithms in anomaly detection are based on the classical density estimation approach of learning high-dimensional models and finding low-probability events. These algorithms are sensitive to the order in which anomalies appear and require either training data or early context assumptions that do not hold for longer, more complex videos. By defining anomalies as examples that can be distinguished from other examples in the same video, our definition inspires a shift in approaches from classical density estimation to simple discriminative learning. Our contributions include a novel framework for anomaly detection that is (1) independent of temporal ordering of anomalies, and (2) unsupervised, requiring no separate training sequences. We show that our algorithm can achieve state-of-the-art results even when we adjust the setting by removing training sequences from standard datasets.

cs.CV↗

arXiv2016

Learning Transferable Policies for Monocular Reactive MAV Control

The ability to transfer knowledge gained in previous tasks into new contexts is one of the most important mechanisms of human learning. Despite this, adapting autonomous behavior to be reused in partially similar settings is still an open problem in current robotics research. In this paper, we take a small step in this direction and propose a generic framework for learning transferable motion policies. Our goal is to solve a learning problem in a target domain by utilizing the training data in a different but related source domain. We present this in the context of an autonomous MAV flight using monocular reactive control, and demonstrate the efficacy of our proposed approach through extensive real-world flight experiments in outdoor cluttered environments.

cs.RO↗

arXiv2016

Introspective Perception: Learning to Predict Failures in Vision Systems

As robots aspire for long-term autonomous operations in complex dynamic environments, the ability to reliably take mission-critical decisions in ambiguous situations becomes critical. This motivates the need to build systems that have situational awareness to assess how qualified they are at that moment to make a decision. We call this self-evaluating capability as introspection. In this paper, we take a small step in this direction and propose a generic framework for introspective behavior in perception systems. Our goal is to learn a model to reliably predict failures in a given system, with respect to a task, directly from input sensor data. We present this in the context of vision-based autonomous MAV flight in outdoor natural environments, and show that it effectively handles uncertain situations.

cs.RO↗

arXiv2016

Shuffle and Learn: Unsupervised Learning using Temporal Order Verification

In this paper, we present an approach for learning a visual representation from the raw spatiotemporal signals in videos. Our representation is learned without supervision from semantic labels. We formulate our method as an unsupervised sequential verification task, i.e., we determine whether a sequence of frames from a video is in the correct temporal order. With this simple task and no semantic labels, we learn a powerful visual representation using a Convolutional Neural Network (CNN). The representation contains complementary information to that learned from supervised image datasets like ImageNet. Qualitative results show that our method captures information that is temporally varying, such as human pose. When used as pre-training for action recognition, our method gives significant gains over learning without external data on benchmark datasets like UCF101 and HMDB51. To demonstrate its sensitivity to human pose, we show results for pose estimation on the FLIC and MPII datasets that are competitive, or better than approaches using significantly more supervision. Our method can be combined with supervised representations to provide an additional boost in accuracy.

cs.CV↗

arXiv2016

The Future of Computing Research: Industry-Academic Collaborations

IT-driven innovation is an enormous factor in the worldwide economic leadership of the United States. It is larger than finance, construction, or transportation, and it employs nearly 6% of the US workforce. The top three companies, as measured by market capitalization, are IT companies - Apple, Google (now Alphabet), and Microsoft. Facebook, a relatively recent entry in the top 10 list by market capitalization has surpassed Walmart, the nation's largest retailer, and the largest employer in the world. The net income of just the top three exceeds $80 billion - roughly 100 times the total budget of the NSF CISE directorate which funds 87% of computing research. In short, the direct return on federal research investments in IT research has been enormously profitable to the nation. The IT industry ecosystem is also evolving. The time from conception to market of successful products has been cut from years to months. Product life cycles are increasingly a year or less. This change has pressured companies to focus industrial R&D on a pipeline or portfolio of technologies that bring immediate, or almost immediate, value to the companies. To defeat the competition and stay ahead of the pack, a company must devote resources to realizing gains that are shorter term, and must remain agile to respond quickly to market changes driven by new technologies, new startups, evolving user experience expectations, and the continuous consumer demand for new and exciting products. Amidst this landscape, the Computing Community Consortium convened a round-table of industry and academic participants to better understand the landscape of industry-academic interaction, and to discuss possible actions that might be taken to enhance those interactions. We close with some recommendations for actions that could expand the lively conversation we experienced at the round-table to a national scale.

cs.CY↗

arXiv2016

An Uncertain Future: Forecasting from Static Images using Variational Autoencoders

In a given scene, humans can often easily predict a set of immediate future events that might happen. However, generalized pixel-level anticipation in computer vision systems is difficult because machine learning struggles with the ambiguity inherent in predicting the future. In this paper, we focus on predicting the dense trajectory of pixels in a scene, specifically what will move in the scene, where it will travel, and how it will deform over the course of one second. We propose a conditional variational autoencoder as a solution to this problem. In this framework, direct inference from the image shapes the distribution of possible trajectories, while latent variables encode any necessary information that is not available in the image. We show that our method is able to successfully predict events in a wide variety of scenes and can produce multiple different predictions when the future is ambiguous. Our algorithm is trained on thousands of diverse, realistic videos and requires absolutely no human labeling. In addition to non-semantic action prediction, we find that our method learns a representation that is applicable to semantic vision tasks.

cs.CV↗

arXiv2016

Robust Monocular Flight in Cluttered Outdoor Environments

Recently, there have been numerous advances in the development of biologically inspired lightweight Micro Aerial Vehicles (MAVs). While autonomous navigation is fairly straight-forward for large UAVs as expensive sensors and monitoring devices can be employed, robust methods for obstacle avoidance remains a challenging task for MAVs which operate at low altitude in cluttered unstructured environments. Due to payload and power constraints, it is necessary for such systems to have autonomous navigation and flight capabilities using mostly passive sensors such as cameras. In this paper, we describe a robust system that enables autonomous navigation of small agile quad-rotors at low altitude through natural forest environments. We present a direct depth estimation approach that is capable of producing accurate, semi-dense depth-maps in real time. Furthermore, a novel wind-resistant control scheme is presented that enables stable way-point tracking even in the presence of strong winds. We demonstrate the performance of our system through extensive experiments on real images and field tests in a cluttered outdoor environment.

cs.RO↗

arXiv2016

Cross-stitch Networks for Multi-task Learning

Multi-task learning in Convolutional Networks has displayed remarkable success in the field of recognition. This success can be largely attributed to learning shared representations from multiple supervisory tasks. However, existing multi-task approaches rely on enumerating multiple network architectures specific to the tasks at hand, that do not generalize. In this paper, we propose a principled approach to learn shared representations in ConvNets using multi-task learning. Specifically, we propose a new sharing unit: "cross-stitch" unit. These units combine the activations from multiple networks and can be trained end-to-end. A network with cross-stitch units can learn an optimal combination of shared and task-specific representations. Our proposed method generalizes across multiple tasks and shows dramatically improved performance over baseline methods for categories with few training examples.

cs.CV↗

arXiv2016

Learning to Extract Motion from Videos in Convolutional Neural Networks

This paper shows how to extract dense optical flow from videos with a convolutional neural network (CNN). The proposed model constitutes a potential building block for deeper architectures to allow using motion without resorting to an external algorithm, \eg for recognition in videos. We derive our network architecture from signal processing principles to provide desired invariances to image contrast, phase and texture. We constrain weights within the network to enforce strict rotation invariance and substantially reduce the number of parameters to learn. We demonstrate end-to-end training on only 8 sequences of the Middlebury dataset, orders of magnitude less than competing CNN-based motion estimation methods, and obtain comparable performance to classical methods on the Middlebury benchmark. Importantly, our method outputs a distributed representation of motion that allows representing multiple, transparent motions, and dynamic textures. Our contributions on network design and rotation invariance offer insights nonspecific to motion estimation.

cs.CV↗

arXiv2015

Dense Optical Flow Prediction from a Static Image

Given a scene, what is going to move, and in what direction will it move? Such a question could be considered a non-semantic form of action prediction. In this work, we present a convolutional neural network (CNN) based approach for motion prediction. Given a static image, this CNN predicts the future motion of each and every pixel in the image in terms of optical flow. Our CNN model leverages the data in tens of thousands of realistic videos to train our model. Our method relies on absolutely no human labeling and is able to predict motion based on the context of the scene. Because our CNN model makes no assumptions about the underlying scene, it can predict future optical flow on a diverse set of scenarios. We outperform all previous approaches by large margins.

cs.CV↗

arXiv2015

Autonomy Infused Teleoperation with Application to BCI Manipulation

Robot teleoperation systems face a common set of challenges including latency, low-dimensional user commands, and asymmetric control inputs. User control with Brain-Computer Interfaces (BCIs) exacerbates these problems through especially noisy and erratic low-dimensional motion commands due to the difficulty in decoding neural activity. We introduce a general framework to address these challenges through a combination of computer vision, user intent inference, and arbitration between the human input and autonomous control schemes. Adjustable levels of assistance allow the system to balance the operator's capabilities and feelings of comfort and control while compensating for a task's difficulty. We present experimental results demonstrating significant performance improvement using the shared-control assistance framework on adapted rehabilitation benchmarks with two subjects implanted with intracortical brain-computer interfaces controlling a seven degree-of-freedom robotic manipulator as a prosthetic. Our results further indicate that shared assistance mitigates perceived user difficulty and even enables successful performance on previously infeasible tasks. We showcase the extensibility of our architecture with applications to quality-of-life tasks such as opening a door, pouring liquids from containers, and manipulation with novel objects in densely cluttered environments.

cs.RO↗

arXiv2015

Watch and Learn: Semi-Supervised Learning of Object Detectors from Videos

We present a semi-supervised approach that localizes multiple unknown object instances in long videos. We start with a handful of labeled boxes and iteratively learn and label hundreds of thousands of object instances. We propose criteria for reliable object detection and tracking for constraining the semi-supervised learning process and minimizing semantic drift. Our approach does not assume exhaustive labeling of each object instance in any single frame, or any explicit annotation of negative data. Working in such a generic setting allow us to tackle multiple object instances in video, many of which are static. In contrast, existing approaches either do not consider multiple object instances per video, or rely heavily on the motion of the objects present. The experiments demonstrate the effectiveness of our approach by evaluating the automatically labeled data on a variety of metrics like quality, coverage (recall), diversity, and relevance to training an object detector.

cs.CV↗

arXiv2015

Visual Chunking: A List Prediction Framework for Region-Based Object Detection

We consider detecting objects in an image by iteratively selecting from a set of arbitrarily shaped candidate regions. Our generic approach, which we term visual chunking, reasons about the locations of multiple object instances in an image while expressively describing object boundaries. We design an optimization criterion for measuring the performance of a list of such detections as a natural extension to a common per-instance metric. We present an efficient algorithm with provable performance for building a high-quality list of detections from any candidate set of region-based proposals. We also develop a simple class-specific algorithm to generate a candidate region instance in near-linear time in the number of low-level superpixels that outperforms other region generating methods. In order to make predictions on novel images at testing time without access to ground truth, we develop learning approaches to emulate these algorithms' behaviors. We demonstrate that our new approach outperforms sophisticated baselines on benchmark datasets.

cs.CV↗