Tootfinder

DDS-NAS: Dynamic Data Selection within Neural Architecture Search via On-line Hard Example Mining applied to Image Classification
Matt Poyser, Toby P. Breckon
https://arxiv.org/abs/2506.14667

DDS-NAS: Dynamic Data Selection within Neural Architecture Search via On-line Hard Example Mining applied to Image Classification
In order to address the scalability challenge within Neural Architecture Search (NAS), we speed up NAS training via dynamic hard example mining within a curriculum learning framework. By utilizing an autoencoder that enforces an image similarity embedding in latent space, we construct an efficient kd-tree structure to order images by furthest neighbour dissimilarity in a low-dimensional embedding. From a given query image from our subsample dataset, we can identify the most dissimilar image wit…

Netflix überträgt in Frankreich lineares Fernsehen
Gemeinsam mit der Mediengesellschaft TF1 will Netflix in Frankreich bald lineares Fernsehen im Stream anbieten. Die Inhalte kommen ins normale Abo.
https://…

Cowboys ink 2 veterans to deals following individual workouts https://insidethestar.com/cowboys-ink-2-veterans-to-deals-following-individual-workouts

Quick snap from a smaller #cycling loop today. Now relaxing and recovering for the mountain tomorrow.
#benediktbeuern #KochelAmSee

Similarly, hostility to education cloaks itself as support by saying that education should be useful, should be practical, should be focused only on what students need, should be narrowed to what students need, should narrow students, should narrow students into being only what capitalism needs.
I wrote extensively about this dangerous line of thought here:
https://innig.net/teaching/liberal-arts-manifesto
6/

Happy #AutisticPrideDay! ♾️💙
I’m proudly autistic, my brain works in its own unique way, full of different thoughts and feelings all at once. Being autistic is part of who I am, not something to fix. 🧠🧠
I’m also queer and genderfluid, and that’s just another part of my colorful identity. Some days I feel one way, some days another, and that’s okay. 🏳️‍🌈☂️
Neurodiver…

FedWSIDD: Federated Whole Slide Image Classification via Dataset Distillation
Haolong Jin, Shenglin Liu, Cong Cong, Qingmin Feng, Yongzhi Liu, Lina Huang, Yingzi Hu
https://arxiv.org/abs/2506.15365

FedWSIDD: Federated Whole Slide Image Classification via Dataset Distillation
Federated learning (FL) has emerged as a promising approach for collaborative medical image analysis, enabling multiple institutions to build robust predictive models while preserving sensitive patient data. In the context of Whole Slide Image (WSI) classification, FL faces significant challenges, including heterogeneous computational resources across participating medical institutes and privacy concerns. To address these challenges, we propose FedWSIDD, a novel FL paradigm that leverages datas…

ViSTA: Visual Storytelling using Multi-modal Adapters for Text-to-Image Diffusion Models
Sibo Dong, Ismail Shaheen, Maggie Shen, Rupayan Mallick, Sarah Adel Bargal
https://arxiv.org/abs/2506.12198

ViSTA: Visual Storytelling using Multi-modal Adapters for Text-to-Image Diffusion Models
Text-to-image diffusion models have achieved remarkable success, yet generating coherent image sequences for visual storytelling remains challenging. A key challenge is effectively leveraging all previous text-image pairs, referred to as history text-image pairs, which provide contextual information for maintaining consistency across frames. Existing auto-regressive methods condition on all past image-text pairs but require extensive training, while training-free subject-specific approaches ens…

Recognition through Reasoning: Reinforcing Image Geo-localization with Large Vision-Language Models
Ling Li, Yao Zhou, Yuxuan Liang, Fugee Tsung, Jiaheng Wei
https://arxiv.org/abs/2506.14674

Recognition through Reasoning: Reinforcing Image Geo-localization with Large Vision-Language Models
Previous methods for image geo-localization have typically treated the task as either classification or retrieval, often relying on black-box decisions that lack interpretability. The rise of large vision-language models (LVLMs) has enabled a rethinking of geo-localization as a reasoning-driven task grounded in visual cues. However, two major challenges persist. On the data side, existing reasoning-focused datasets are primarily based on street-view imagery, offering limited scene diversity and…

Cost-Aware Routing for Efficient Text-To-Image Generation
Qinchan (Wing), Li (Tina), Kenneth Chen (Tina), Changyue (Tina), Su, Wittawat Jitkrittum, Qi Sun, Patsorn Sangkloy
https://arxiv.org/abs/2506.14753

Cost-Aware Routing for Efficient Text-To-Image Generation
Diffusion models are well known for their ability to generate a high-fidelity image for an input prompt through an iterative denoising process. Unfortunately, the high fidelity also comes at a high computational cost due the inherently sequential generative process. In this work, we seek to optimally balance quality and computational cost, and propose a framework to allow the amount of computation to vary for each prompt, depending on its complexity. Each prompt is automatically routed to the m…