28 citations · 41 across the 8 of their papers we have counts for
10 papers
Orbis 2: A Hierarchical World Model for Driving
Sudhanshu Mittal, Arian Mousakhan, Silvio Galesso +4
Current world models operate at a single level of abstraction, with most prioritizing perceptual fidelity while lacking the spatial reasoning and semantic understanding required fo…
On Geometric Understanding and Learned Priors in Feed-forward 3D Reconstruction Models
Jelena Bratulić, Sudhanshu Mittal, Thomas Brox +1
Feed-forward 3D reconstruction models such as DUSt3R, VGGT, and Depth Anything 3 (DA3) are transformer-based foundation models that infer camera geometry and dense scene structure…
Orbis: Overcoming Challenges of Long-Horizon Prediction in Driving World Models
Arian Mousakhan, Sudhanshu Mittal, Silvio Galesso +2
Existing world models for autonomous driving struggle with long-horizon generation and generalization to challenging scenarios. In this work, we develop a model using simple design…
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…
Best Practices in Active Learning for Semantic Segmentation
Sudhanshu Mittal, Joshua Niemeijer, Jörg P. Schäfer +1
Active learning is particularly of interest for semantic segmentation, where annotations are costly. Previous academic studies focused on datasets that are already very diverse and…
Open-vocabulary Attribute Detection
María A. Bravo, Sudhanshu Mittal, Simon Ging +1
Vision-language modeling has enabled open-vocabulary tasks where predictions can be queried using any text prompt in a zero-shot manner. Existing open-vocabulary tasks focus on obj…
Localized Vision-Language Matching for Open-vocabulary Object Detection
Maria A. Bravo, Sudhanshu Mittal, Thomas Brox
In this work, we propose an open-vocabulary object detection method that, based on image-caption pairs, learns to detect novel object classes along with a given set of known classe…
Essentials for Class Incremental Learning
Sudhanshu Mittal, Silvio Galesso, Thomas Brox
Contemporary neural networks are limited in their ability to learn from evolving streams of training data. When trained sequentially on new or evolving tasks, their accuracy drops…
Parting with Illusions about Deep Active Learning
Sudhanshu Mittal, Maxim Tatarchenko, Özgün Çiçek +1
Active learning aims to reduce the high labeling cost involved in training machine learning models on large datasets by efficiently labeling only the most informative samples. Rece…
Semi-Supervised Semantic Segmentation with High- and Low-level Consistency
Sudhanshu Mittal, Maxim Tatarchenko, Thomas Brox
The ability to understand visual information from limited labeled data is an important aspect of machine learning. While image-level classification has been extensively studied in…