Celeba
PulseAugur coverage of Celeba — every cluster mentioning Celeba across labs, papers, and developer communities, ranked by signal.
6 day(s) with sentiment data
-
New framework audits AI face analysis for hidden fairness risks
Researchers have developed a new framework called CIFA (Contextual-Intersectional Fairness Auditing) to identify hidden vulnerabilities in face analysis systems. This framework goes beyond traditional demographic fairne…
-
DeepForgeSeal uses latent space watermarking for robust deepfake detection
Researchers have developed DeepForgeSeal, a novel deep learning framework designed to combat the growing challenge of deepfakes. This system utilizes a semi-fragile watermark embedded in the latent space of images, allo…
-
New research tackles diffusion model watermarking and attack methods
Two new research papers introduce novel methods for watermarking diffusion models and attacking existing watermarks. The first paper, FARI, proposes a fast, one-step inversion framework that improves robustness and sign…
-
New research explores flow matching model enhancements and vulnerabilities · 9 sources tracked
Researchers are exploring novel approaches to enhance flow matching models, a popular paradigm for generative tasks. One paper introduces "denoising acceleration" (accel) as a cost-free proxy for estimating uncertainty …
-
New diffusion model offers concept-based visual counterfactual explanations
Researchers have developed C-VCE, a novel diffusion model framework designed to provide concept-based visual counterfactual explanations for AI predictions. Unlike previous methods that rely on external, potentially fra…
-
New regularization method tackles bias in self-supervised learning
Researchers have introduced Unbiased Open World Regularization (UOWReg), a novel framework designed to mitigate biases in self-supervised learning (SSL) and Joint-Embedding Predictive Architectures (JEPAs). Unlike previ…
-
New framework characterizes utility-separation trade-off in ML models
Researchers have developed a new information-theoretic framework to characterize the trade-off between utility and separation in machine learning models. This framework proves the concavity of the utility-separation Par…
-
New XFactors framework enables weakly-supervised disentangled representation learning
Researchers have introduced XFactors, a novel weakly-supervised variational auto-encoder framework designed for disentangled representation learning. This method decomposes representations into specific factor subspaces…
-
New AI model SwinIFS enhances facial images while preserving identity
Researchers have developed SwinIFS, a new framework for enhancing low-resolution facial images into high-resolution ones while preserving identity. This method integrates facial landmark information with a Swin Transfor…
-
New Association Restoration Test evaluates AI unlearning effectiveness
Researchers have introduced the Association Restoration Test (ART), a new diagnostic tool designed to evaluate the effectiveness of association unlearning in AI models. This method specifically assesses whether learned …
-
New method enhances ML model robustness against spurious correlations
Researchers have introduced Invariance Pair Guidance (IPG), a novel method designed to enhance the robustness of machine learning models against spurious correlations. Unlike existing techniques that often require exten…
-
New methods probe generative models for bias and improve performance
Researchers have developed new methods, Attribution Graphs (AGs) and Causal Probing, to analyze the internal workings of generative models. These techniques aim to identify and correct issues like spurious correlations,…
-
New research advances diffusion models for image editing, data augmentation, and unlearning
Researchers are exploring advanced techniques for diffusion models, focusing on improving image editing, data augmentation, and unlearning capabilities. New methods aim to enhance stability and fidelity in image editing…
-
Trigger color significantly impacts federated learning backdoor attack success
Researchers have demonstrated that the color of visual triggers significantly impacts the success rate of backdoor attacks in federated learning. By manipulating trigger colors on semantic objects like masks and sunglas…
-
New theory explains flow-based solvers, proposes efficient sampling method
Researchers have developed a new theoretical framework for understanding flow-based inverse solvers, which are used to solve imaging inverse problems. The new approach, termed posterior-transport, reveals that condition…
-
Flow Map Denoisers offer continuous control over image restoration tradeoffs
Researchers have introduced a novel method called Flow Map Denoisers, which addresses the fundamental tradeoff in image restoration between minimizing error and maximizing perceptual quality. This new approach utilizes …
-
InfantFace model enhances neonatal face detection in clinical settings
Researchers have developed InfantFace, a specialized face detection model based on the YOLOv11m architecture, designed for use in neonatal clinical environments. The model addresses challenges like cluttered backgrounds…
-
Lightweight U-Net uses YOLO-World heatmaps for face super-resolution
Researchers have developed a lightweight U-Net architecture for face super-resolution, capable of reconstructing high-resolution images from severely degraded inputs with an 8x magnification. A novel approach uses heatm…
-
polyDAG framework improves causal discovery in visual graphs
Researchers have developed polyDAG, a new framework for efficiently discovering causal relationships in visual semantic graphs. This method replaces computationally expensive acyclicity constraints with a polynomial tra…
-
Flow model optimizes compressed sensing for image reconstruction
Researchers have developed a novel flow-based generative model designed to optimize sampling policies in compressed sensing applications. This framework, which adapts the Flow Matching training paradigm, learns to selec…