arXiv subjects

Laura Leal-Taixé

Publications and source records attributed to Laura Leal-Taixé.

85 records · Page 5Linked to original sources

arXiv2018

Deep Depth From Focus

Depth from focus (DFF) is one of the classical ill-posed inverse problems in computer vision. Most approaches recover the depth at each pixel based on the focal setting which exhibits maximal sharpness. Yet, it is not obvious how to reliably estimate the sharpness level, particularly in low-textured areas. In this paper, we propose `Deep Depth From Focus (DDFF)' as the first end-to-end learning approach to this problem. One of the main challenges we face is the hunger for data of deep neural networks. In order to obtain a significant amount of focal stacks with corresponding groundtruth depth, we propose to leverage a light-field camera with a co-calibrated RGB-D sensor. This allows us to digitally create focal stacks of varying sizes. Compared to existing benchmarks our dataset is 25 times larger, enabling the use of machine learning for this inverse problem. We compare our results with state-of-the-art DFF methods and we also analyze the effect of several key deep architectural components. These experiments show that our proposed method `DDFFNet' achieves state-of-the-art performance in all scenes, reducing depth error by more than 75% compared to the classical DFF methods.

cs.CV↗

arXiv2018

Deep Perm-Set Net: Learn to predict sets with unknown permutation and cardinality using deep neural networks

Many real-world problems, e.g. object detection, have outputs that are naturally expressed as sets of entities. This creates a challenge for traditional deep neural networks which naturally deal with structured outputs such as vectors, matrices or tensors. We present a novel approach for learning to predict sets with unknown permutation and cardinality using deep neural networks. Specifically, in our formulation we incorporate the permutation as unobservable variable and estimate its distribution during the learning process using alternating optimization. We demonstrate the validity of this new formulation on two relevant vision problems: object detection, for which our formulation outperforms state-of-the-art detectors such as Faster R-CNN and YOLO, and a complex CAPTCHA test, where we observe that, surprisingly, our set based network acquired the ability of mimicking arithmetics without any rules being coded.

cs.CV↗

arXiv2018

Modular Vehicle Control for Transferring Semantic Information Between Weather Conditions Using GANs

Even though end-to-end supervised learning has shown promising results for sensorimotor control of self-driving cars, its performance is greatly affected by the weather conditions under which it was trained, showing poor generalization to unseen conditions. In this paper, we show how knowledge can be transferred using semantic maps to new weather conditions without the need to obtain new ground truth data. To this end, we propose to divide the task of vehicle control into two independent modules: a control module which is only trained on one weather condition for which labeled steering data is available, and a perception module which is used as an interface between new weather conditions and the fixed control module. To generate the semantic data needed to train the perception module, we propose to use a generative adversarial network (GAN)-based model to retrieve the semantic information for the new conditions in an unsupervised manner. We introduce a master-servant architecture, where the master model (semantic labels available) trains the servant model (semantic labels not available). We show that our proposed method trained with ground truth data for a single weather condition is capable of achieving similar results on the task of steering angle prediction as an end-to-end model trained with ground truth data of 15 different weather conditions.

cs.LG↗

arXiv2018

Video Object Segmentation Without Temporal Information

Video Object Segmentation, and video processing in general, has been historically dominated by methods that rely on the temporal consistency and redundancy in consecutive video frames. When the temporal smoothness is suddenly broken, such as when an object is occluded, or some frames are missing in a sequence, the result of these methods can deteriorate significantly or they may not even produce any result at all. This paper explores the orthogonal approach of processing each frame independently, i.e disregarding the temporal information. In particular, it tackles the task of semi-supervised video object segmentation: the separation of an object from the background in a video, given its mask in the first frame. We present Semantic One-Shot Video Object Segmentation (OSVOS-S), based on a fully-convolutional neural network architecture that is able to successively transfer generic semantic information, learned on ImageNet, to the task of foreground segmentation, and finally to learning the appearance of a single annotated object of the test sequence (hence one shot). We show that instance level semantic information, when combined effectively, can dramatically improve the results of our previous method, OSVOS. We perform experiments on two recent video segmentation databases, which show that OSVOS-S is both the fastest and most accurate method in the state of the art.

cs.CV↗

arXiv2018

Discrete-Continuous ADMM for Transductive Inference in Higher-Order MRFs

This paper introduces a novel algorithm for transductive inference in higher-order MRFs, where the unary energies are parameterized by a variable classifier. The considered task is posed as a joint optimization problem in the continuous classifier parameters and the discrete label variables. In contrast to prior approaches such as convex relaxations, we propose an advantageous decoupling of the objective function into discrete and continuous subproblems and a novel, efficient optimization method related to ADMM. This approach preserves integrality of the discrete label variables and guarantees global convergence to a critical point. We demonstrate the advantages of our approach in several experiments including video object segmentation on the DAVIS data set and interactive image segmentation.

cs.LG↗

arXiv2018

Fusion of Head and Full-Body Detectors for Multi-Object Tracking

In order to track all persons in a scene, the tracking-by-detection paradigm has proven to be a very effective approach. Yet, relying solely on a single detector is also a major limitation, as useful image information might be ignored. Consequently, this work demonstrates how to fuse two detectors into a tracking system. To obtain the trajectories, we propose to formulate tracking as a weighted graph labeling problem, resulting in a binary quadratic program. As such problems are NP-hard, the solution can only be approximated. Based on the Frank-Wolfe algorithm, we present a new solver that is crucial to handle such difficult problems. Evaluation on pedestrian tracking is provided for multiple scenarios, showing superior results over single detector tracking and standard QP-solvers. Finally, our tracker ranks 2nd on the MOT16 benchmark and 1st on the new MOT17 benchmark, outperforming over 90 trackers.

cs.CV↗

arXiv2017

Image-based localization using LSTMs for structured feature correlation

In this work we propose a new CNN+LSTM architecture for camera pose regression for indoor and outdoor scenes. CNNs allow us to learn suitable feature representations for localization that are robust against motion blur and illumination changes. We make use of LSTM units on the CNN output, which play the role of a structured dimensionality reduction on the feature vector, leading to drastic improvements in localization performance. We provide extensive quantitative comparison of CNN-based and SIFT-based localization methods, showing the weaknesses and strengths of each. Furthermore, we present a new large-scale indoor dataset with accurate ground truth from a laser scanner. Experimental results on both indoor and outdoor public datasets show our method outperforms existing deep architectures, and can localize images in hard conditions, e.g., in the presence of mostly textureless surfaces, where classic SIFT-based methods fail.

cs.CV↗

arXiv2017

One-Shot Video Object Segmentation

This paper tackles the task of semi-supervised video object segmentation, i.e., the separation of an object from the background in a video, given the mask of the first frame. We present One-Shot Video Object Segmentation (OSVOS), based on a fully-convolutional neural network architecture that is able to successively transfer generic semantic information, learned on ImageNet, to the task of foreground segmentation, and finally to learning the appearance of a single annotated object of the test sequence (hence one-shot). Although all frames are processed independently, the results are temporally coherent and stable. We perform experiments on two annotated video segmentation databases, which show that OSVOS is fast and improves the state of the art by a significant margin (79.8% vs 68.0%).

cs.CV↗

arXiv2017

Tracking the Trackers: An Analysis of the State of the Art in Multiple Object Tracking

Standardized benchmarks are crucial for the majority of computer vision applications. Although leaderboards and ranking tables should not be over-claimed, benchmarks often provide the most objective measure of performance and are therefore important guides for research. We present a benchmark for Multiple Object Tracking launched in the late 2014, with the goal of creating a framework for the standardized evaluation of multiple object tracking methods. This paper collects the two releases of the benchmark made so far, and provides an in-depth analysis of almost 50 state-of-the-art trackers that were tested on over 11000 frames. We show the current trends and weaknesses of multiple people tracking methods, and provide pointers of what researchers should be focusing on to push the field forward.

cs.CV↗

arXiv2016

Multiple object tracking with context awareness

Multiple people tracking is a key problem for many applications such as surveillance, animation or car navigation, and a key input for tasks such as activity recognition. In crowded environments occlusions and false detections are common, and although there have been substantial advances in recent years, tracking is still a challenging task. Tracking is typically divided into two steps: detection, i.e., locating the pedestrians in the image, and data association, i.e., linking detections across frames to form complete trajectories. For the data association task, approaches typically aim at developing new, more complex formulations, which in turn put the focus on the optimization techniques required to solve them. However, they still utilize very basic information such as distance between detections. In this thesis, I focus on the data association task and argue that there is contextual information that has not been fully exploited yet in the tracking community, mainly social context and spatial context coming from different views.

cs.CV↗

arXiv2016

Learning by tracking: Siamese CNN for robust target association

This paper introduces a novel approach to the task of data association within the context of pedestrian tracking, by introducing a two-stage learning scheme to match pairs of detections. First, a Siamese convolutional neural network (CNN) is trained to learn descriptors encoding local spatio-temporal structures between the two input image patches, aggregating pixel values and optical flow information. Second, a set of contextual features derived from the position and size of the compared input patches are combined with the CNN output by means of a gradient boosting classifier to generate the final matching probability. This learning approach is validated by using a linear programming based multi-person tracker showing that even a simple and efficient tracker may outperform much more complex models when fed with our learned matching probabilities. Results on publicly available sequences show that our method meets state-of-the-art standards in multiple people tracking.

cs.LG↗

arXiv2016

Tracking with multi-level features

We present a novel formulation of the multiple object tracking problem which integrates low and mid-level features. In particular, we formulate the tracking problem as a quadratic program coupling detections and dense point trajectories. Due to the computational complexity of the initial QP, we propose an approximation by two auxiliary problems, a temporal and spatial association, where the temporal subproblem can be efficiently solved by a linear program and the spatial association by a clustering algorithm. The objective function of the QP is used in order to find the optimal number of clusters, where each cluster ideally represents one person. Evaluation is provided for multiple scenarios, showing the superiority of our method with respect to classic tracking-by-detection methods and also other methods that greedily integrate low-level features.

cs.CV↗

arXiv2015

MOTChallenge 2015: Towards a Benchmark for Multi-Target Tracking

In the recent past, the computer vision community has developed centralized benchmarks for the performance evaluation of a variety of tasks, including generic object and pedestrian detection, 3D reconstruction, optical flow, single-object short-term tracking, and stereo estimation. Despite potential pitfalls of such benchmarks, they have proved to be extremely helpful to advance the state of the art in the respective area. Interestingly, there has been rather limited work on the standardization of quantitative benchmarks for multiple target tracking. One of the few exceptions is the well-known PETS dataset, targeted primarily at surveillance applications. Despite being widely used, it is often applied inconsistently, for example involving using different subsets of the available data, different ways of training the models, or differing evaluation scripts. This paper describes our work toward a novel multiple object tracking benchmark aimed to address such issues. We discuss the challenges of creating such a framework, collecting existing and new data, gathering state-of-the-art methods to be tested on the datasets, and finally creating a unified evaluation system. With MOTChallenge we aim to pave the way toward a unified evaluation framework for a more meaningful quantification of multi-target tracking.

cs.CV↗