Timo Milbich
YOU?
Author Swipe
View article: Characterizing Generalization under Out-Of-Distribution Shifts in Deep\n Metric Learning
Characterizing Generalization under Out-Of-Distribution Shifts in Deep\n Metric Learning Open
Deep Metric Learning (DML) aims to find representations suitable for\nzero-shot transfer to a priori unknown test distributions. However, common\nevaluation protocols only test a single, fixed data split in which train and\ntest classes ar…
View article: Characterizing Generalization under Out-Of-Distribution Shifts in Deep Metric Learning
Characterizing Generalization under Out-Of-Distribution Shifts in Deep Metric Learning Open
Deep Metric Learning (DML) aims to find representations suitable for zero-shot transfer to a priori unknown test distributions. However, common evaluation protocols only test a single, fixed data split in which train and test classes are a…
View article: iPOKE: Poking a Still Image for Controlled Stochastic Video Synthesis
iPOKE: Poking a Still Image for Controlled Stochastic Video Synthesis Open
How would a static scene react to a local poke? What are the effects on other parts of an object if you could locally push it? There will be distinctive movement, despite evident variations caused by the stochastic nature of our world. The…
View article: Understanding Object Dynamics for Interactive Image-to-Video Synthesis
Understanding Object Dynamics for Interactive Image-to-Video Synthesis Open
What would be the effect of locally poking a static scene? We present an approach that learns naturally-looking global articulations caused by a local manipulation at a pixel level. Training requires only videos of moving objects but no in…
View article: Behavior-Driven Synthesis of Human Dynamics
Behavior-Driven Synthesis of Human Dynamics Open
Generating and representing human behavior are of major importance for various computer vision applications. Commonly, human video synthesis represents behavior as sequences of postures while directly predicting their likely progressions o…
View article: Stochastic Image-to-Video Synthesis using cINNs
Stochastic Image-to-Video Synthesis using cINNs Open
Video understanding calls for a model to learn the characteristic interplay between static scene content and its dynamics: Given an image, the model must be able to predict a future progression of the portrayed scene and, conversely, a vid…
View article: S2SD: Simultaneous Similarity-based Self-Distillation for Deep Metric Learning
S2SD: Simultaneous Similarity-based Self-Distillation for Deep Metric Learning Open
Deep Metric Learning (DML) provides a crucial tool for visual similarity and zero-shot applications by learning generalizing embedding spaces, although recent work in DML has shown strong performance saturation across training objectives. …
View article: Sharing Matters for Generalization in Deep Metric Learning
Sharing Matters for Generalization in Deep Metric Learning Open
Learning the similarity between images constitutes the foundation for numerous vision tasks. The common paradigm is discriminative metric learning, which seeks an embedding that separates different training classes. However, the main chall…
View article: PADS: Policy-Adapted Sampling for Visual Similarity Learning
PADS: Policy-Adapted Sampling for Visual Similarity Learning Open
Learning visual similarity requires to learn relations, typically between triplets of images. Albeit triplet approaches being powerful, their computational complexity mostly limits training to only a subset of all possible training triplet…
View article: Revisiting Training Strategies and Generalization Performance in Deep Metric Learning
Revisiting Training Strategies and Generalization Performance in Deep Metric Learning Open
Deep Metric Learning (DML) is arguably one of the most influential lines of research for learning visual similarities with many proposed approaches every year. Although the field benefits from the rapid progress, the divergence in training…
View article: Unsupervised Representation Learning by Discovering Reliable Image\n Relations
Unsupervised Representation Learning by Discovering Reliable Image\n Relations Open
Learning robust representations that allow to reliably establish relations\nbetween images is of paramount importance for virtually all of computer vision.\nAnnotating the quadratic number of pairwise relations between training images\nis …
View article: Unsupervised Part-Based Disentangling of Object Shape and Appearance
Unsupervised Part-Based Disentangling of Object Shape and Appearance Open
Large intra-class variation is the result of changes in multiple object characteristics. Images, however, only show the superposition of different variable factors such as appearance or shape. Therefore, learning to disentangle and represe…
View article: Unsupervised Video Understanding by Reconciliation of Posture Similarities
Unsupervised Video Understanding by Reconciliation of Posture Similarities Open
Understanding human activity and being able to explain it in detail surpasses mere action classification by far in both complexity and value. The challenge is thus to describe an activity on the basis of its most fundamental constituents, …