Anna Khoreva (PhD Student)

MSc Anna Khoreva

Max-Planck-Institut für Informatik
Saarland Informatics Campus
Campus E1 4
66123 Saarbrücken
E1 4 - Room 618
+49 681 9325 2118
+49 681 9325 1899
Get email via email

Personal Information

Research Interests

  • Computer Vision
  • Machine Learning


Research Projects


See my Google Scholar profile.


Exploiting Saliency for Object Segmentation from Image Level Labels
S. J. Oh, R. Benenson, A. Khoreva, Z. Akata, M. Fritz and B. Schiele
Technical Report, 2017
(arXiv: 1701.08261)
There have been remarkable improvements in the semantic labelling task in the recent years. However, the state of the art methods rely on large-scale pixel-level annotations. This paper studies the problem of training a pixel-wise semantic labeller network from image-level annotations of the present object classes. Recently, it has been shown that high quality seeds indicating discriminative object regions can be obtained from image-level labels. Without additional information, obtaining the full extent of the object is an inherently ill-posed problem due to co-occurrences. We propose using a saliency model as additional information and hereby exploit prior knowledge on the object extent and image statistics. We show how to combine both information sources in order to recover 80% of the fully supervised performance - which is the new state of the art in weakly supervised training for pixel-wise semantic labelling.
Weakly Supervised Object Boundaries
A. Khoreva, R. Benenson, M. Omran, M. Hein and B. Schiele
29th IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2016), 2016
State-of-the-art learning based boundary detection methods require extensive training data. Since labelling object boundaries is one of the most expensive types of annotations, there is a need to relax the requirement to carefully annotate images to make both the training more affordable and to extend the amount of training data. In this paper we propose a technique to generate weakly supervised annotations and show that bounding box annotations alone suffice to reach high-quality object boundaries without using any object-specific boundary annotations. With the proposed weak supervision techniques we achieve the top performance on the object boundary detection task, outperforming by a large margin the current fully supervised state-of-the-art methods.
Improved Image Boundaries for Better Video Segmentation
A. Khoreva, R. Benenson, F. Galasso, M. Hein and B. Schiele
Computer Vision -- ECCV 2016 Workshops, 2016
Graph-based video segmentation methods rely on superpixels as starting point. While most previous work has focused on the construction of the graph edges and weights as well as solving the graph partitioning problem, this paper focuses on better superpixels for video segmentation. We demonstrate by a comparative analysis that superpixels extracted from boundaries perform best, and show that boundary estimation can be significantly improved via image and time domain cues. With superpixels generated from our better boundaries we observe consistent improvement for two video segmentation methods in two different datasets.
Simple Does It: Weakly Supervised Instance and Semantic Segmentation
A. Khoreva, R. Benenson, J. Hosang, M. Hein and B. Schiele
Technical Report, 2016
(arXiv: 1603.07485)
Semantic labelling and instance segmentation are two tasks that require particularly costly annotations. Starting from weak supervision in the form of bounding box detection annotations, we propose to recursively train a convnet such that outputs are improved after each iteration. We explore which aspects affect the recursive training, and which is the most suitable box-guided segmentation to use as initialisation. Our results improve significantly over previously reported ones, even when using rectangles as rough initialisation. Overall, our weak supervision approach reaches ~95% of the quality of the fully supervised model, both for semantic labelling and instance segmentation.
Learning Video Object Segmentation from Static Images
A. Khoreva, F. Perazzi, R. Benenson, B. Schiele and A. Sorkine-Hornung
Technical Report, 2016
(arXiv: 1612.02646)
Inspired by recent advances of deep learning in instance segmentation and object tracking, we introduce video object segmentation problem as a concept of guided instance segmentation. Our model proceeds on a per-frame basis, guided by the output of the previous frame towards the object of interest in the next frame. We demonstrate that highly accurate object segmentation in videos can be enabled by using a convnet trained with static images only. The key ingredient of our approach is a combination of offline and online learning strategies, where the former serves to produce a refined mask from the previous frame estimate and the latter allows to capture the appearance of the specific object instance. Our method can handle different types of input annotations: bounding boxes and segments, as well as incorporate multiple annotated frames, making the system suitable for diverse applications. We obtain competitive results on three different datasets, independently from the type of input annotation.
Classifier Based Graph Construction for Video Segmentation
A. Khoreva, F. Galasso, M. Hein and B. Schiele
IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2015), 2015
Learning Must-Link Constraints for Video Segmentation Based on Spectral Clustering
A. Khoreva, F. Galasso, M. Hein and B. Schiele
Pattern Recognition (GCPR 2014), 2014