D2
Computer Vision and Machine Learning

Max Losch (PhD Student)

MSc Max Maria Losch

Address
Max-Planck-Institut für Informatik
Saarland Informatics Campus
Campus E1 4
66123 Saarbrücken
Standort
E1 4 - 608
Telefon
+49 681 9325 2000
Fax
+49 681 9325 2099

Personal Information

Research Interests

  • Computer Vision
  • Machine Learning

Education

Other

See my Google Scholar profile.

Publications

2021
Semantic Bottlenecks: Quantifying and Improving Inspectability of Deep Representations
M. Losch, M. Fritz and B. Schiele
International Journal of Computer Vision, Volume 129, 2021
2020
Analyzing the Dependency of ConvNets on Spatial Information
Y. Fan, Y. Xian, M. M. Losch and B. Schiele
Pattern Recognition (GCPR 2020), 2020
Semantic Bottlenecks: Quantifying & Improving Inspectability of Deep Representations
M. Losch, M. Fritz and B. Schiele
Pattern Recognition (GCPR 2020), 2020
Analyzing the Dependency of ConvNets on Spatial Information
Y. Fan, Y. Xian, M. M. Losch and B. Schiele
Technical Report, 2020
(arXiv: 2002.01827)
Abstract
Intuitively, image classification should profit from using spatial<br>information. Recent work, however, suggests that this might be overrated in<br>standard CNNs. In this paper, we are pushing the envelope and aim to further<br>investigate the reliance on spatial information. We propose spatial shuffling<br>and GAP+FC to destroy spatial information during both training and testing<br>phases. Interestingly, we observe that spatial information can be deleted from<br>later layers with small performance drops, which indicates spatial information<br>at later layers is not necessary for good performance. For example, test<br>accuracy of VGG-16 only drops by 0.03% and 2.66% with spatial information<br>completely removed from the last 30% and 53% layers on CIFAR100, respectively.<br>Evaluation on several object recognition datasets (CIFAR100, Small-ImageNet,<br>ImageNet) with a wide range of CNN architectures (VGG16, ResNet50, ResNet152)<br>shows an overall consistent pattern.<br>
2019
Interpretability Beyond Classification Output: Semantic Bottleneck Networks
M. Losch, M. Fritz and B. Schiele
Technical Report, 2019
(arXiv: 1907.10882)
Abstract
Today's deep learning systems deliver high performance based on end-to-end<br>training. While they deliver strong performance, these systems are hard to<br>interpret. To address this issue, we propose Semantic Bottleneck Networks<br>(SBN): deep networks with semantically interpretable intermediate layers that<br>all downstream results are based on. As a consequence, the analysis on what the<br>final prediction is based on is transparent to the engineer and failure cases<br>and modes can be analyzed and avoided by high-level reasoning. We present a<br>case study on street scene segmentation to demonstrate the feasibility and<br>power of SBN. In particular, we start from a well performing classic deep<br>network which we adapt to house a SB-Layer containing task related semantic<br>concepts (such as object-parts and materials). Importantly, we can recover<br>state of the art performance despite a drastic dimensionality reduction from<br>1000s (non-semantic feature) to 10s (semantic concept) channels. Additionally<br>we show how the activations of the SB-Layer can be used for both the<br>interpretation of failure cases of the network as well as for confidence<br>prediction of the resulting output. For the first time, e.g., we show<br>interpretable segmentation results for most predictions at over 99% accuracy.<br>