32 citations · 39 across the 10 of their papers we have counts for
11 papers
SOCO: Benchmarking Semantic Object Correspondence in Vision Foundation Models
Olaf Dünkel, Basavaraj Sunagad, Haoran Wang +3
Measuring structured object understanding in vision foundation models remains challenging due to inconsistent evaluation protocols and limited part-level supervision. Semantic corr…
No Hard Negatives Required: Concept Centric Learning Leads to Compositionality without Degrading Zero-shot Capabilities of Contrastive Models
Hai X. Pham, David T. Hoffmann, Ricardo Guerrero +1
Contrastive vision-language (V&L) models remain a popular choice for various applications. However, several limitations have emerged, most notably the limited ability of V&L models…
Common Data Properties Limit Object-Attribute Binding in CLIP
Bijay Gurung, David T. Hoffmann, Thomas Brox
Contrastive vision-language models like CLIP are used for a large variety of applications, such as zero-shot classification or as vision encoder for multi-modal models. Despite the…
Floxels: Fast Unsupervised Voxel Based Scene Flow Estimation
David T. Hoffmann, Syed Haseeb Raza, Hanqiu Jiang +3
Scene flow estimation is a foundational task for many robotic applications, including robust dynamic object detection, automatic labeling, and sensor synchronization. Two types of…
Unlocking In-Context Learning for Natural Datasets Beyond Language Modelling
Jelena Bratulić, Sudhanshu Mittal, David T. Hoffmann +5
Large Language Models (LLMs) exhibit In-Context Learning (ICL), which enables the model to perform new tasks conditioning only on the examples provided in the context without updat…
Two Effects, One Trigger: On the Modality Gap, Object Bias, and Information Imbalance in Contrastive Vision-Language Models
Simon Schrodi, David T. Hoffmann, Max Argus +2
Contrastive vision-language models (VLMs), like CLIP, have gained popularity for their versatile applicability to various downstream tasks. Despite their successes in some tasks, l…
Eureka-Moments in Transformers: Multi-Step Tasks Reveal Softmax Induced Optimization Problems
David T. Hoffmann, Simon Schrodi, Jelena Bratulić +3
In this work, we study rapid improvements of the training loss in transformers when being confronted with multi-step decision tasks. We found that transformers struggle to learn th…
Ranking Info Noise Contrastive Estimation: Boosting Contrastive Learning via Ranked Positives
David T. Hoffmann, Nadine Behrmann, Juergen Gall +2
This paper introduces Ranking Info Noise Contrastive Estimation (RINCE), a new member in the family of InfoNCE losses that preserves a ranked ordering of positive samples. In contr…
AGORA: Avatars in Geography Optimized for Regression Analysis
Priyanka Patel, Chun-Hao P. Huang, Joachim Tesch +3
While the accuracy of 3D human pose estimation from images has steadily improved on benchmark datasets, the best methods still fail in many real-world scenarios. This suggests that…
Learning Multi-Human Optical Flow
Anurag Ranjan, David T. Hoffmann, Dimitrios Tzionas +3
The optical flow of humans is well known to be useful for the analysis of human action. Recent optical flow methods focus on training deep networks to approach the problem. However…
Learning to Train with Synthetic Humans
David T. Hoffmann, Dimitrios Tzionas, Micheal J. Black +1
Neural networks need big annotated datasets for training. However, manual annotation can be too expensive or even unfeasible for certain tasks, like multi-person 2D pose estimation…