Christoph H. Lampert

Christoph H. Lampert
Institute of Science and Technology Austria (ISTA) | IST

Dr. rer. nat.

About

94
Publications
20,823
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
9,041
Citations

Publications

Publications (94)
Preprint
We examine the question of whether SGD-based optimization of deep neural networks (DNNs) can be adapted to produce models which are both highly-accurate and easily-compressible. We propose a new compression-aware minimizer dubbed CrAM, which modifies the SGD training iteration in a principled way, in order to produce models whose local loss behavio...
Preprint
The availability of large amounts of user-provided data has been key to the success of machine learning for many real-world tasks. Recently, an increasing awareness has emerged that users should be given more control about how their data is used. In particular, users should have the right to prohibit the use of their data for training machine learn...
Preprint
Fairness-aware learning aims at constructing classifiers that not only make accurate predictions, but do not discriminate against specific groups. It is a fast-growing area of machine learning with far-reaching societal impact. However, existing fair learning methods are vulnerable to accidental or malicious artifacts in the training data, which ca...
Preprint
Our goal in this work is to generate realistic videos given just one initial frame as input. Existing unsupervised approaches to this task do not consider the fact that a video typically shows a 3D environment, and that this should remain coherent from frame to frame even as the camera and objects move. We address this by developing a model that fi...
Preprint
Fine-tuning is a popular way of exploiting knowledge contained in a pre-trained convolutional network for a new visual recognition task. However, the orthogonal setting of transferring knowledge from a pretrained network to a visually different yet semantically close source is rarely considered: This commonly happens with real-life data, which is n...
Preprint
A natural approach to generative modeling of videos is to represent them as a composition of moving objects. Recent works model a set of 2D sprites over a slowly-varying background, but without considering the underlying 3D scene that gives rise to them. We instead propose to model a video as the view seen while moving through a scene with multiple...
Preprint
State-of-the-art detection systems are generally evaluated on their ability to exhaustively retrieve objects densely distributed in the image, across a wide variety of appearances and semantic categories. Orthogonal to this, many real-life object detection applications, for example in remote sensing, instead require dealing with large images that c...
Article
Full-text available
We study the problem of automatically detecting if a given multi-class classifier operates outside of its specifications (out-of-specs), i.e. on input data from a different distribution than what it was trained for. This is an important problem to solve on the road towards creating reliable computer vision systems for real-world applications, becau...
Article
Full-text available
The original version of this article contained a mistake in the denominator of equation (1).
Chapter
Computer vision systems for automatic image categorization have become accurate and reliable enough that they can run continuously for days or even years as components of real-world commercial applications. A major open problem in this context, however, is quality control. Good classification performance can only be expected if systems run under th...
Preprint
In this paper we propose a new model for detecting visual relationships. Our main technical novelty is a Box Attention mechanism that allows modelling pairwise interactions between objects in visual scenes using standard object detection pipelines. The resulting model is conceptually clean, expressive and relies on well-justified training and predi...
Article
Computer vision systems for automatic image categorization have become accurate and reliable enough that they can run continuously for days or even years as components of real-world commercial applications. A major open problem in this context, however, is quality control. Good classification performance can only be expected if systems run under th...
Article
We develop a probabilistic technique for colorizing grayscale natural images. In light of the intrinsic uncertainty of this task, the proposed probabilistic framework has numerous desirable properties. In particular, our model is able to produce multiple plausible and vivid colorizations for a given grayscale image and is one of the first colorizat...
Article
We introduce a new technique for probabilistic modeling of natural images that combines the advantages of classic multi-scale and modern deep learning models. By explicitly representing natural images at different scales we derive a model that can capture high level image structure in a computationally efficient way. We show experimentally that our...
Article
Full-text available
A major open problem on the road to artificial intelligence is the development of incrementally learning systems that learn about more and more concepts over time from a stream of data. In this work, we introduce a new training strategy, iCaRL, that allows learning in such a class-incremental way: only the training data for a small number of classe...
Conference Paper
We introduce a new loss function for the weakly-supervised training of semantic image segmentation models based on three guiding principles: to seed with weak localization cues, to expand objects based on the information about which classes can occur in an image, and to constrain the segmentations to coincide with object boundaries. We show experim...
Article
Weakly-supervised object localization methods tend to fail for object classes that consistently co-occur with the same background elements, e.g. trains on tracks. We propose a method to overcome these failures by adding a very small amount of model-specific additional annotation. The main idea is to cluster a deep network's mid-level representation...
Article
We introduce a new loss function for the weakly-supervised training of semantic image segmentation models based on three guiding principles: to seed with weak location cues, to expand objects based on the information about which classes can occur, and to constrain the segmentations to coincide with image boundaries. We show experimentally that trai...
Conference Paper
We present LS-CRF, a new method for training cyclic Conditional Random Fields (CRFs) from large datasets that is inspired by classical closed-form expressions for the maximum likelihood parameters of a generative graphical model with tree topology. Training a CRF with LS-CRF requires only solving a set of independent regression problems, each of wh...
Book
The 38th Annual Workshop of the Austrian Association for Pattern Recognition (ÖAGM) will be held at IST Austria, on May 22-23, 2014. The workshop provides a platform for researchers and industry to discuss traditional and new areas of computer vision. This year the main topic is: Pattern Recognition: interdisciplinary challenges and opportunities.
Article
We study the problem of object recognition for categories for which we have no training examples, a task also called zero--data or zero-shot learning. This situation has hardly been studied in computer vision research, even though it occurs frequently; the world contains tens of thousands of different object classes, and image collections have been...
Conference Paper
Many visual datasets are traditionally used to analyze the performance of different learning techniques. The evaluation is usually done within each dataset, therefore it is questionable if such results are a reliable indicator of true generalization ability. We propose here an algorithm to exploit the existing data resources when learning on a new...
Conference Paper
We propose a new learning method to infer a mid-level feature representation that combines the advantage of semantic attribute representations with the higher expressive power of non-semantic features. The idea lies in augmenting an existing attribute-based representation with additional dimensions for which an autoencoder model is coupled with a l...
Article
Full-text available
When searching for characteristic subpatterns in potentially noisy graph data, it appears self-evident that having multiple observations would be better than having just one. However, it turns out that the inconsistencies introduced when different graph instances have different edge sets pose a serious challenge. In this work we address this challe...
Conference Paper
Full-text available
Playing table tennis is a difficult task for robots, especially due to their limitations of acceleration. A key bottle- neck is the amount of time needed to reach the desired hitting position and velocity of the racket for returning the incoming ball. Here, it often does not suffice to simply extrapolate the ball's trajectory after the opponent ret...
Article
Kernel canonical correlation analysis (KCCA) is a general technique for subspace learning that incorporates principal components analysis (PCA) and Fisher linear discriminant analysis (LDA) as special cases. By finding directions that maximize correlation, KCCA learns representations that are more closely tied to the underlying process that generat...
Article
Full-text available
Dynamic tactile sensing is a fundamental ability to recognize materials and objects. However, while humans are born with partially developed dynamic tactile sensing and quickly master this skill, today's robots remain in their infancy. The development of such a sense requires not only better sensors but the right algorithms to deal with these senso...
Conference Paper
Full-text available
We introduce TopoCut: a new way to integrate knowledge about topological properties (TPs) into random field image segmentation model. Instead of including TPs as additional constraints during minimization of the energy function, we devise an efficient algorithm for modifying the unary potentials such that the resulting segmentation is guaranteed wi...
Article
Full-text available
Powerful statistical models that can be learned efficiently from large amounts of data are currently revolutionizing computer vision. These models possess a rich internal structure reflecting task-specific relations and constraints. This monograph introduces the reader to the most popular classes of structured models in computer vision. Our focus i...
Conference Paper
We address the problem of metric learning for multi-view data, namely the construction of embedding projections from data in different representations into a shared feature space, such that the Euclidean distance in this space provides a meaningful within-view as well as between-view similarity. Our motivation stems from the problem of cross-media...
Conference Paper
Full-text available
We study the problem of multimodal dimensionality reduction assuming that data samples can be missing at training time, and not all data modalities may be present at application time. Maximum covariance analysis, as a generalization of PCA, has many desirable properties, but its application to practical problems is limited by its need for perfectly...
Conference Paper
We introduce a method to accelerate the evaluation of object detection cascades with the help of a divide-and-conquer procedure in the space of candidate regions. Compared to the exhaustive procedure that thus far is the state-of-the-art for cascade evaluation, the proposed method requires fewer evaluations of the classifier functions, thereby spee...
Conference Paper
Full-text available
Recent progress in per-pixel object class labeling of natural images can be attributed to the use of multiple types of image features and sound statistical learning approaches. Within the latter, Conditional Random Fields (CRF) are prominently used for their ability to represent interactions between random variables. Despite their popularity in com...
Conference Paper
For object category recognition to scale beyond a small number of classes, it is important that algorithms be able to learn from a small amount of labeled data per additional class. One-shot recognition aims to apply the knowledge gained from a set of categories with plentiful data to categories for which only a single exemplar is available for eac...
Conference Paper
We present a new technique for structured prediction that works in a hybrid generative/discriminative way, using a one-class support vector machine to model the joint probability of (input, output)-pairs in a joint reproducing kernel Hilbert space. Compared to discriminative techniques, like conditional random fields or structured output SVMs, the...
Article
Full-text available
The goal of this paper is to evaluate and compare models and methods for learning to recognize basic entities in images in an unsupervised setting. In other words, we want to discover the objects present in the images by analyzing unlabeled data and searching for re-occurring patterns. We experiment with various baseline methods, methods based on l...
Conference Paper
Full-text available
Hitting and batting tasks, such as tennis forehands, ping-pong strokes, or baseball batting, depend on predictions where the ball can be intercepted and how it can properly be returned to the opponent. These predictions get more accurate over time, hence the behaviors need to be continuously modified. As a result, movement templates with a learned...
Article
Full-text available
We describe RTblob, a high speed vision system that detects objects in cluttered scenes based on their color and shape at a speed of over 800frames/s. Because the system is available as open-source software and relies only on off-the-shelf PC hardware components, it can provide the basis for multiple application scenarios. As an illustrative exampl...
Article
Full-text available
Markov random field (MRF) models, including conditional random field models, are popular in computer vision. However, in order to be computationally tractable, they are limited to incorporating only local interactions and cannot model global properties such as connectedness, which is a potentially useful high-level prior for object segmentation. In...
Conference Paper
Full-text available
Most state-of-the-art systems for content-based video understanding tasks require video content to be represented as collections of many low-level descriptors, e.g. as histograms of the color, texture or motion in local image regions. In order to preserve as much of the information contained in the original video as possible, these representations...
Article
Full-text available
Discriminative techniques, such as conditional random fields (CRFs) or structure aware maximum-margin techniques (maximum margin Markov networks (M3N), structured output support vector machines (S-SVM)), are state-of-the-art in the prediction of structured data. However, to achieve good results these techniques require complete and reliable ground...
Article
Full-text available
Most successful object recognition systems rely on binary classification, deciding only if an object is present or not, but not providing information on the actual object location. To estimate the object's location, one can take a sliding window approach, but this strongly increases the computational cost because the classifier or similarity functi...
Conference Paper
Full-text available
High-speed smooth and accurate visual tracking of objects in arbitrary, unstructured environments is essential for robotics and human motion analysis. However, building a system that can adapt to arbitrary objects and a wide range of lighting conditions is a challenging problem, especially if hard real-time constraints apply like in robotics scenar...
Conference Paper
We study the task of detecting the occurrence of objects in large image collections or in videos, a problem that combines aspects of content based image retrieval and object localization. While most previous approaches are either limited to special kinds of queries, or do not scale to large image sets, we propose a new method, efficient subimage re...
Conference Paper
Full-text available
Markov random field (MRF, CRF) models are popular in computer vision. However, in order to be computationally tractable they are limited to incorporate only local interactions and cannot model global properties, such as connectedness, which is a potentially useful high-level prior for object segmentation. In this work, we overcome this limitation b...
Conference Paper
Full-text available
We study the problem of object classification when training and test classes are disjoint, i.e. no training examples of the target classes are available. This setup has hardly been studied in computer vision research, but it is the rule rather than the exception, because the world contains tens of thousands of different object classes and for only...
Article
Full-text available
An important cue to high level scene understanding is to analyze the objects in the scene and their behavior and interactions. In this paper, we study the problem of classification of activities in videos, as this is an integral component of any scene understanding system, and present a novel approach for recognizing human action categories in vide...
Conference Paper
Recent research has shown that the use of contextual cues significantly improves performance in sliding window type localization systems. In this work, we propose a method that incorporates both global and local context information through appropriately defined kernel functions. In particular, we make use of a weighted combination of kernels define...
Article
Over the last years, kernel methods have established themselves as powerful tools for computer vision researchers as well as for practitioners. In this tutorial, we give an introduction to kernel methods in computer vision from a geometric perspective, introducing not only the ubiquitous support vector machines, but also less known techniques for r...
Conference Paper
Sliding window classifiers are among the most successful and widely applied techniques for object localization. However, training is typically done in a way that is not specific to the localization task. First a binary classifier is trained using a sample of positive and negative examples, and this classifier is subsequently applied to multiple reg...
Conference Paper
Kernel canonical correlation analysis (KCCA) is a dimensionality reduction technique for paired data. By finding directions that maximize correlation, KCCA learns representations that are more closely tied to the underlying semantics of the data rather than noise. However, meaningful directions are not only those that have high correlation to anoth...
Conference Paper
Full-text available
Most successful object recognition systems rely on binary classification, deciding only if an object is present or not, but not providing information on the actual object location. To perform localization, one can take a sliding window approach, but this strongly increases the computational cost, because the classifier function has to be evaluated...
Conference Paper
We present a new method for spectral clustering with paired data based on kernel canonical correlation analysis, called correlational spectral clustering. Paired data are common in real world data sources, such as images with text captions. Traditional spectral clustering algorithms either assume that data can be represented by a single similarity...
Conference Paper
We propose a new method to partition an unlabeled dataset, called Discriminative Context Partitioning (DCP). It is motivated by the idea of splitting the dataset based only on how well the resulting parts can be separated from a context class of disjoint data points. This is in contrast to typical clustering techniques like K-means that are based o...
Conference Paper
Most current methods for multi-class object classification and localization work as independent 1-vs-rest classifiers. They decide whether and where an object is visible in an image purely on a per-class basis. Joint learning of more than one object class would generally be preferable, since this would allow the use of contextual information such a...
Conference Paper
Full-text available
Distributed denial of service (DDoS) attacks are today the most destabilizing factor in the global internet and there is a strong need for sophisticated solutions. We introduce a formal statistical framework and derive a Bayes optimal packet classifier from it. Our proposed practical algorithm "adaptive history-based IP filtering" (AHIF) mitigates...
Article
Most successful object recognition systems rely on binary classification, deciding only if an object is present or not, but not providing information on the actual object location. To perform localization, one can take a sliding window approach, but this strongly increases the computational cost, because the classifier function has to be evaluated...
Conference Paper
Full-text available
The extraction of a parametric global motion from a motion field is a task with several applications in video processing. We present two probabilistic formulations of the problem and carry out optimization using the RAST algorithm, a geometric matching method novel to motion estimation in video. RAST uses an exhaustive and adaptive search of transf...
Conference Paper
Full-text available
The detection of counterfeit in printed documents is currently based mainly on built-in security features or on human expertise. We propose a classification system that supports non-expert users to distinguish original documents from PC-made forgeries by analyzing the printing technique used. Each letter in a document is classified using a support...
Article
We give an analytical and geometrical treatment of what it means to separate a Gaussian kernel along arbitrary axes in R(n), and we present a separation scheme that allows us to efficiently implement anisotropic Gaussian convolution filters for data of arbitrary dimensionality. Based on our previous analysis we show that this scheme is optimal with...
Conference Paper
Full-text available
This paper describes a new system for ”Finding Satellite Tracks” in astronomical images based on the modern geometric approach. There is an increasing need of using methods with solid mathematical and statistical foundation in astronomical image processing. Where the computational methods are serving in all disciplines of science, they are becoming...
Conference Paper
Gaussian filtering in one, two or three dimensions is among the most commonly needed tasks in signal and image processing. Finite impulse response filters in the time domain with Gaussian masks are easy to implement in either floating or fixed point arithmetic, because Gaussian kernels are strictly positive and bounded. But these implementations ar...
Conference Paper
Full-text available
We propose a simple and effective method for tire dequantization of color images, effectively interpolating the colors from quantized levels to a continuous range of brightness values. The method is designed to be applied to images that either heave undergone a manipulation like image brightness adjustment, or are going to be processed in such a wa...
Conference Paper
Video Compression currently is dominated by engineering and fine-tuned heuristic methods. In this paper, we propose to instead apply the well-developed machinery of machine learning in order to support the optimization of existing video encoders and the creation of new ones. Exemplarily, we show how by machine learning we can improve one encoding s...
Conference Paper
Full-text available
Digital cameras have become almost ubiquitous and their use for fast and casual capturing of natural images is unchallenged. For making images of documents, however, they have not caught up to flatbed scanners yet, mainly because camera images tend to suffer from distortion due to the perspective and are therefore limited in their further use for a...
Conference Paper
Full-text available
Ever since text processors became popular, users have dreamt of handling documents printed on paper as comfortably as electronic ones, with full text search typically appearing very close to the top of the wish list. This paper presents the design of a prot