A foundation encoder is pretrained once on a large image corpus and then reused with its weights frozen. Each new task is solved by training a small head on the features it produces. This setup is common in medical imaging, where labeled cases are scarce and a frozen encoder can be reused across findings. All downstrea...
Soroosh Tayebi Arasteh, Sven Nebelung, Daniel Truhn· 0 citations
Deep learning models for online handwriting recognition have been shown effective and are increasingly deployed in practical applications. However, their vulnerability to adversarial attacks is still a challenge. Existing adversarial methods are predominantly designed for image-based inputs and typically rely on additi...
Yataro Tamura, Brian Kenji Iwana, Jiseok Lee· 0 citations
Clinical decision-making in oncology requires forecasting how disease evolves under treatment, yet most AI systems remain static predictors that cannot model longitudinal, treatment-conditioned progression. Although generative and world models have demonstrated strong capabilities in general domains, their adaptation t...
Tianxingjian Ding, Yuanhao Zou, Chen Chen et al.· 0 citations
Mixed-Precision Quantization (MPQ) liberates Deep Neural Networks (DNNs) from the Out-Of-Memory (OOM) bottleneck and has garnered increasing research attention. However, conventional methods either rely on costly differentiable optimization search, which is neither efficient nor flexible, or learn a quantized DNN from...
Haidong Kang, Jun Du, Guo Yu· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Adapting vision models for time series analysis is compelling, yet all existing approaches are falling short of dedicated time series foundation models (TSFMs) in classification. In this work, we propose Time Vision Transformer (TiViT), the first framework that successfully unlocks the representational power of frozen...
Simon Roschmann, Quentin Bouniot, Vasilii Feofanov et al.· 0 citations
This study provides a comprehensive overview of mobile image-based healthcare solutions and their potential to support low-cost disease diagnosis and monitoring, particularly for underserved populations in remote and resource-constrained settings.
Syed Muhammad Ibne Zulfiker, F. Islam, Marina Arifin et al.· 0 citations
Mitotic figure (MF) analysis supports tumor grading and prognostic assessment, but automated models remain sensitive to differences in tissue type and image acquisition. We present MiTHras, a task-specific pretraining framework that combines pseudo-label-guided image- and token-level contrastive learning with masked re...
Trinh T. L. Vuong, Simon Graham, Quoc Dang Vu et al.· 0 citations
Model merging aims to combine multiple fine-tuned models derived from a common pretrained model into a single multi-task model without additional joint training. Recent spectral merging methods improve over simple weight averaging by exploiting low-rank structures of task-specific updates, but they commonly assign the...
Intelligent transportation systems require Incremental Learning (IL) to continually improve their overall performance in dynamic environments. However, most edge devices lack the computational resources to support on-device IL, requiring updates to be transmitted from centralized servers. We propose using this setup to...
Matthias Neuwirth-Trapp, Maarten Bieshaar, Danda Paudel et al.· 0 citations
Recognizing hand-drawn geometric shapes is a foundational sub-problem of sketch recognition, with applications in education, human-computer interaction, and diagram digitization. This paper presents the design, implementation, and evaluation of a desktop application that recognizes four basic hand-drawn geometric shape...
Mechanistic interpretability of vision transformers seeks to decompose model computation into human-readable units, but learned representations entangle many concepts in each neuron. Feature superposition is widely treated as the central obstacle to this decomposition, yet most mitigations (sparse autoencoders, diction...
Gautam Ranka, S. Pandere, Aiden Dsouza· 0 citations
New Guinea is the world's richest island flora (~2,856 orchid species), yet most species are represented by only a handful of photographs, far fewer than direct species-level classification requires. Methods for fine-grained identification in such species-rich, data-poor floras are needed, and it remains unclear which...
Reza Saputra, D. H. Apriyanti, A. Schuiteman et al.· 0 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.
