Tootfinder

Depth Edge Alignment Loss: DEALing with Depth in Weakly Supervised Semantic Segmentation
Patrick Schmidt, Vasileios Belagiannis, Lazaros Nalpantidis
https://arxiv.org/abs/2509.17702

Depth Edge Alignment Loss: DEALing with Depth in Weakly Supervised Semantic Segmentation
Autonomous robotic systems applied to new domains require an abundance of expensive, pixel-level dense labels to train robust semantic segmentation models under full supervision. This study proposes a model-agnostic Depth Edge Alignment Loss to improve Weakly Supervised Semantic Segmentation models across different datasets. The methodology generates pixel-level semantic labels from image-level supervision, avoiding expensive annotation processes. While weak supervision is widely explored in tr…

Pixel-"Superfans" dürfen neue Top-Smartphones schon früher testen
Google lädt eine kleine Gruppe seiner treuesten Pixel-Nutzer ein, das kommende Pixel 11 vor der offiziellen Markteinführung zu testen und Feedback zu geben.

Cool Chemistry Trick Could Transform Vinegar Into a Powerful Weapon Against Superbugs
https://gizmodo.com/cool-chemistry-trick-could-transform-vinegar-into-a-powerful-weapon-against-superbugs-2000662684

♫No novo tempo
Apesar dos perigos
Da força mais bruta
Da noite que assusta
Estamos na luta
Pra sobreviver
Pra sobreviver
Pra sobreviver
Pra que nossa esperança
Seja mais que vingança
Seja sempre um caminho
Que se deixa de herança♫
https://www.youtube.com/watch?v=jHEfuVacAeU

Meta launches the American Technology Excellence Project, a super PAC to fight AI policy bills at the state level; it previously launched a California PAC (Ashley Gold/Axios)
https://www.axios.com/2025/09/23/meta-superpac-ai-regulation

Exclusive: Meta launches super PAC to fight AI regulation
Meta is targeting what it sees as onerous AI and tech policy bills across the country.

Explainable AI-Enhanced Supervisory Control for Robust Multi-Agent Robotic Systems
Reza Pirayeshshirazinezhad, Nima Fathi
https://arxiv.org/abs/2509.15491 https://

Explainable AI-Enhanced Supervisory Control for Robust Multi-Agent Robotic Systems
We present an explainable AI-enhanced supervisory control framework for multi-agent robotics that combines (i) a timed-automata supervisor for safe, auditable mode switching, (ii) robust continuous control (Lyapunov-based controller for large-angle maneuver; sliding-mode controller (SMC) with boundary layers for precision and disturbance rejection), and (iii) an explainable predictor that maps mission context to gains and expected performance (energy, error). Monte Carlo-driven optimization pro…

Adversarial Graph Fusion for Incomplete Multi-view Semi-supervised Learning with Tensorial Imputation
Zhangqi Jiang, Tingjin Luo, Xu Yang, Xinyan Liang
https://arxiv.org/abs/2509.15955

Adversarial Graph Fusion for Incomplete Multi-view Semi-supervised Learning with Tensorial Imputation
View missing remains a significant challenge in graph-based multi-view semi-supervised learning, hindering their real-world applications. To address this issue, traditional methods introduce a missing indicator matrix and focus on mining partial structure among existing samples in each view for label propagation (LP). However, we argue that these disregarded missing samples sometimes induce discontinuous local structures, i.e., sub-clusters, breaking the fundamental smoothness assumption in LP.…

Towards Sharper Object Boundaries in Self-Supervised Depth Estimation
Aur\'elien Cecille, Stefan Duffner, Franck Davoine, R\'emi Agier, Thibault Neveu
https://arxiv.org/abs/2509.15987

Towards Sharper Object Boundaries in Self-Supervised Depth Estimation
Accurate monocular depth estimation is crucial for 3D scene understanding, but existing methods often blur depth at object boundaries, introducing spurious intermediate 3D points. While achieving sharp edges usually requires very fine-grained supervision, our method produces crisp depth discontinuities using only self-supervision. Specifically, we model per-pixel depth as a mixture distribution, capturing multiple plausible depths and shifting uncertainty from direct regression to the mixture w…

Blind-Spot Guided Diffusion for Self-supervised Real-World Denoising
Shen Cheng, Haipeng Li, Haibin Huang, Xiaohong Liu, Shuaicheng Liu
https://arxiv.org/abs/2509.16091 https://…

Blind-Spot Guided Diffusion for Self-supervised Real-World Denoising
In this work, we present Blind-Spot Guided Diffusion, a novel self-supervised framework for real-world image denoising. Our approach addresses two major challenges: the limitations of blind-spot networks (BSNs), which often sacrifice local detail and introduce pixel discontinuities due to spatial independence assumptions, and the difficulty of adapting diffusion models to self-supervised denoising. We propose a dual-branch diffusion framework that combines a BSN-based diffusion branch, generati…

Enhancing Semantic Segmentation with Continual Self-Supervised Pre-training
Brown Ebouky, Ajad Chhatkuli, Cristiano Malossi, Christoph Studer, Roy Assaf, Andrea Bartezzaghi
https://arxiv.org/abs/2509.17816

Enhancing Semantic Segmentation with Continual Self-Supervised Pre-training
Self-supervised learning (SSL) has emerged as a central paradigm for training foundation models by leveraging large-scale unlabeled datasets, often producing representations with strong generalization capabilities. These models are typically pre-trained on general-purpose datasets such as ImageNet and subsequently adapted to various downstream tasks through finetuning. While recent advances have explored parameter-efficient strategies for adapting pre-trained models, extending SSL pre-training …