We address few-shot object detection with vision-language models (VLMs) in out-of-domain settings such as aerial, industrial, and medical imagery, using only ten annotated images for supervision. Existing adaptation methods are discrete prompt optimization and LoRA fine-tuning. We revisit a third option: soft prompting...
Gautam Rajendrakumar Gare, Si-Ying Li, He-Wei Wang et al.· 1 citation
A deep-learning pipeline for enhancing the detection of faint moving objects in optical space situational awareness (SSA) imagery through automated star removal and background reconstruction is presented, thereby providing an effective data-driven preprocessing strategy for faint moving-object detection in optical SSA...
Angela Cratere, Luca Ghilardi, Vishnu Reddy et al.· 0 citations
Control ablations show that gains in cross-regime adaptive propagation are not explained by single-basis propagation, an additional same-family branch, or within-family adaptive order alone, supporting complementary two-basis propagation as an effective design principle for visual representation learning.
This paper proposes a meta-learning framework that leverages a comprehensive set of meta-features capturing dataset complexity to predict classifier performance without exhaustive training, and achieves an average ranking prediction accuracy exceeding 86%, demonstrating its effectiveness in guiding model selection.
Zahra Nabizadeh-ShahreBabak, Farzaneh Koohestani, Nader Karimi et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Whether vision language models can decide when to answer immediately and, when more evidence is needed, which experiment to perform is studied to reveal limitations in physical reasoning that conventional answer accuracy can overlook.
Sourajit Saha, Shubhashis Roy Dipta, Nobin Sarwar et al.· 0 citations
Crystal-orientation maps are physical fields defined only up to crystal symmetry; electron backscatter diffraction (EBSD) resolves them experimentally, but acquisition-time constraints limit spatial resolution. Unlike conventional images, EBSD data lie on the quotient space $\mathrm{SO}(3)/G$, where $G$ is the crystal-...
Umang Garg, Warren Zamudio, M. Echlin et al.· 0 citations
The results show that class disjointness alone is insufficient to remove the influence of target-domain data, highlighting the need to move beyond in-domain pre-training as the default few-shot evaluation protocol, since it can overestimate performance in realistic scenarios where target-domain data are scarce.
Alejandro Gal'an-Cuenca, Marcelo Saval-Calvo, Antonio Javier Gallego· 0 citations
On a 97-patient development cohort, cross-FOV fusion improved lesion-level precision and F1 while substantially reducing false positives relative to the individual models, supporting cross-FOV probability fusion as a simple and computationally practical strategy for improving the precision-false-positive trade-off in 3...
S. Jaume, Hong-Ming Wang, S. Warfield· 0 citations
Velocity-aware pitch control is standard, but under a broadcast viewport half the players are off screen and on-screen velocities come from a drifting calibration. We ask at which layer of broadcast off-ball analysis velocity changes the answer. Inheriting our off-screen imputation protocol (three Metrica matches, 44 m...
A few-shot regression framework that combines Vision Transformer feature embeddings, clustering-based task construction, and gradient-based meta-learning is proposed, and it is shown that task construction in embedding space is a primary driver of performance.
Sheikh Hasan Elahi, R. Dewage, Habib Ullah et al.· 0 citations
A robotization pipeline is developed that converts heterogeneous human videos into robot-aligned observations and action trajectories while inferring missing intermediate signals across annotation levels and constructs the HuRo dataset, comprising about 630K robotized episodes and 142M processed frames from five human-...
Jinho Jeong, Se June Joo, Jaehyun Kang et al.· 2 citations
This work introduces CoRA-NAS (COarse Ranking + Anchor-residual), a two-stage framework combining a static ranking prior with low-cost learning-curve refinement that combines cross-space ranking robustness with low-cost architecture selection.
Yi-Fan Yang, Zhao-Yan Wang, Zhengguang Gao et al.· 1 citation
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.
