• Publications
  • Influence
Learning to detect unseen object classes by between-class attribute transfer
The experiments show that by using an attribute layer it is indeed possible to build a learning object detection system that does not require any training images of the target classes, and assembled a new large-scale dataset, “Animals with Attributes”, of over 30,000 animal images that match the 50 classes in Osherson's classic table of how strongly humans associate 85 semantic attributes with animal classes.
iCaRL: Incremental Classifier and Representation Learning
iCaRL can learn many classes incrementally over a long period of time where other strategies quickly fail, and distinguishes it from earlier works that were fundamentally limited to fixed data representations and therefore incompatible with deep learning architectures.
Attribute-Based Classification for Zero-Shot Visual Object Categorization
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
Zero-Shot Learning—A Comprehensive Evaluation of the Good, the Bad and the Ugly
A new zero-shot learning dataset is proposed, the Animals with Attributes 2 (AWA2) dataset which is made publicly available both in terms of image features and the images themselves and compares and analyzes a significant number of the state-of-the-art methods in depth.
Beyond sliding windows: Object localization by efficient subwindow search
A simple yet powerful branch-and-bound scheme that allows efficient maximization of a large class of classifier functions over all possible subimages and converges to a globally optimal solution typically in sublinear time is proposed.
Seed, Expand and Constrain: Three Principles for Weakly-Supervised Image Segmentation
It is shown experimentally that training a deep convolutional neural network using the proposed loss function leads to substantially better segmentations than previous state-of-the-art methods on the challenging PASCAL VOC 2012 dataset.
Efficient Subwindow Search: A Branch and Bound Framework for Object Localization
A simple yet powerful branch and bound scheme that allows efficient maximization of a large class of quality functions over all possible subimages and converges to a globally optimal solution typically in linear or even sublinear time, in contrast to the quadratic scaling of exhaustive or sliding window search.
Learning to Localize Objects with Structured Output Regression
This work proposes to treat object localization in a principled way by posing it as a problem of predicting structured data: it model the problem not as binary classification, but as the prediction of the bounding box of objects located in images.
Structured Learning and Prediction in Computer Vision
This monograph introduces the reader to the most popular classes of structured models in computer vision including discrete undirected graphical models and methods for parameter learning where the classic maximum likelihood based methods are distinguished from the more recent prediction-based parameter learning methods.
Unsupervised Object Discovery: A Comparison
The goal of this paper is to discover the objects present in the images by analyzing unlabeled data and searching for re-occurring patterns, and a rigorous framework for evaluating unsupervised object discovery methods is proposed.