Increasing safety is the primary objective of automated vehicles. Achieving this goal requires reliable safety metrics that incorporate safety-relevant factors such as object type, velocity, and criticality. A key capability of such metrics is the distinction between critical and non-critical objects, which is addresse...
J\"org Gamerdinger, Victor Schwarzenberger, Philipp Schmid et al.· 0 citations
It is suggested that physics-guided synthetic HFUS images contain transferable anatomical and textural cues for real-domain skin layer segmentation, although further reduction of the synthetic-real appearance gap is needed to enable greater gains.
A Geometric-to-Semantic Spherical Transfer Learning framework that outperforms fully supervised baselines trained from scratch on variable and tertiary sulci, confirming that learning the cortex shape is highly beneficial for identifying its rarest parts.
Saeb Tounsi, J. Chavas, Pietro Gori et al.· 0 citations
RiPPLE provides a whole-space ranking from a fractional anchor-training budget, with comparisons interpreted under their respective evaluation and cost protocols, and the results examine ranking quality, label efficiency, architecture selection, and the roles of readout, coverage, and propagation.
Yi-Fan Yang, Zhao-Yan Wang, Zheng-Guang Gao et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
A dataset-independent metric called the CREDibility Score (CREDS) is proposed for OOD prediction and credibility curves are introduced to study the maximum credibility a model can attain and credibility heat maps are introduced to characterize pre-hoc model behavior across different datasets.
V. Bansal, Himanshu Buckchash, B. Raman et al.· 0 citations
State-of-the-art action-conditioned video models are typically restricted to a single robot embodiment, preventing them from leveraging the vast corpus of heterogeneous video data that contains rich signals for learning generalizable physics. To bridge this gap, we introduce CLAP, a framework for cross-embodiment actio...
Dense prediction tasks in surgical computer vision, such as segmentation and surgical zone prediction, can provide valuable guidance for laparoscopic and robotic surgery. However, these models often suffer from distribution shifts, as training datasets rarely cover the variability encountered during deployment, leading...
Guiqiu Liao, Matja\v{z} Jogan, Daniel A. Hashimoto· 0 citations
A unified conditional-flow framework that casts generation, semantic editing, and intra-structural retargeting as condition-modulated transport within one text- and skeleton-conditioned rectified-flow model, replacing separate pipelines with a single conditional motion transport model while keeping the same-topology re...
Junli Li, Xin Song, Si-Qi Wang et al.· arXiv.org· 1 citation
Ptychographic imaging at synchrotron and X-ray free-electron laser sources requires densely overlapping scans, which limits throughput and increases dose; extending coherent diffractive imaging to overlap-free operation on extended samples remains an open problem. We present a self-supervised inverse-mapping network fo...
Oliver Hoidn, Steven Henke, Albert Vong et al.· 0 citations
This work explores post-training to achieve fully unified text-image generation, where a model autonomously transitions from textual reasoning to visual synthesis within a single inference process, and enables improvements in multimodal image generation across four diverse, independent T2I benchmarks.
Jiahui Chen, Philippe Hansen-Estruch, Xiao-Chuang Han et al.· arXiv.org· 1 citation
A novel online test-time domain generalization framework for CTTA, dubbed TestDG, which aims to learn features invariant to both current and previous test domains on the fly during testing, improving the potential for effective generalization to future domains.
Sohyun Lee, Nayeong Kim, Juwon Kang et al.· 0 citations
It is demonstrated that separately encoding text and visual instructions, combined with co-training using shallow feature control, is essential to mitigate task ambiguity and enhance multi-task generalization and pave the way for more robust and generalizable low-level vision systems.
Yuandong Pu, Le Zhuo, Kaiwen Zhu et al.· arXiv.org· 19 citations
Exploring how generative AI could make machine vision more accessible to businesses. The post GenEye in a Box: Making Machine Vision Something You Can Just Ask For appeared first on GPT-Lab.
Jennifer Neville did not want to go into computer science—but that’s exactly where she landed. Neville discusses the starts and stops that led to her professional sweet spot and her work identifying “surprising failures” making it hard for AI to handle complexity. The post What AI gets wrong and what failure teaches us appeared first on Microsoft Research.
Computer scientist, entrepreneur, and philanthropist will collaborate with the MIT Schwarzman College of Computing to advance AI and scientific discovery.
