A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
A new perceptual adjustment query for metric learning reduces complexity in high-dimensional data.
Perceptual ad-blocking is a novel approach that detects online advertisements based on their visual content. Compared to traditional filter lists, the use of perceptual signals is believed to be less prone to an arms race with web publishers and ad networks. We demonstrate that this may not be the case. We describe att…
In order to design haptic icons or build a haptic vocabulary, we require a set of easily distinguishable haptic signals to avoid perceptual ambiguity, which in turn requires a way to accurately estimate the perceptual (dis)similarity of such signals. In this work, we present a novel method to learn such a perceptual me…
Metric functions for phoneme perception capture the similarity structure among phonemes in a given language and therefore play a central role in phonology and psycho-linguistics. Various phenomena depend on phoneme similarity, such as spoken word recognition or serial recall from verbal working memory. This study prese…
PeL separates sensory interface optimization from decision learning.
New SSIM measure improves adversarial attacks' perceptual quality.
Perceptual Kalman filters maintain human-perceptual quality while processing data.
New finding: Perceptually-aligned gradients occur in adversarially-robust classifiers.
PerceptNet mimics human vision to estimate image quality.
New method defends against unseen threat models using perceptual adversarial training.
Conventional SVM-based image coding methods are founded on independently restricting the distortion in every image coefficient at some particular image representation. Geometrically, this implies allowing arbitrary signal distortions in an -dimensional rectangle defined by the -insensitivity zone in eac…
Paper introduces adversarial lossy compression for video artifacts reduction.
Study shows perceptual boost of visual attention varies with task difficulty and size.
New method compresses facial videos using GANs and latent space optimization.
Improved image generation with private data using perceptual features.
New method disentangles perceptual uncertainty and behavioral costs in partially observable systems.
Stabilizes training of DNN for speech enhancement using PESQ scores.
Introduces PCG for better counterfactual explanations in vision models.
Humans perceive the seemingly chaotic world in a structured and compositional way with the prerequisite of being able to segregate conceptual entities from the complex visual scenes. The mechanism of grouping basic visual elements of scenes into conceptual entities is termed as perceptual grouping. In this work, we pro…
Stochastic encoders outperform deterministic ones in 'perfect perceptual quality'.
Quaternion Conformer GAN (QC-GAN) is a parameter-efficient speech enhancement framework that combines a Quaternion Conformer generator with MetricGAN-based training.
Improves deep learning interpretability through logical network construction.
Recent work has shown that additive threat models, which only permit the addition of bounded noise to the pixels of an image, are insufficient for fully capturing the space of imperceivable adversarial examples. For example, small rotations and spatial transformations can fool classifiers, remain imperceivable to human…
Neural network VQ-VAE with WaveNet decodes speech at 1.6 kbps with high quality.
Existing model-based reinforcement learning methods often study perception modeling and decision making separately. We introduce joint Perception and Control as Inference (PCI), a general framework to combine perception and control for partially observable environments through Bayesian inference. Based on the fact that…
Lossy compression algorithms are typically designed and analyzed through the lens of Shannon's rate-distortion theory, where the goal is to achieve the lowest possible distortion (e.g., low MSE or high SSIM) at any given bit rate. However, in recent years, it has become increasingly accepted that "low distortion" is no…
This paper presents a novel CNN-based approach for synthesizing high-resolution LiDAR point cloud data. Our approach generates semantically and perceptually realistic results with guidance from specialized loss-functions. First, we utilize a modified per-point loss that addresses missing LiDAR point measurements. Secon…
In recent years there has been a growing interest in image generation through deep learning. While an important part of the evaluation of the generated images usually involves visual inspection, the inclusion of human perception as a factor in the training process is often overlooked. In this paper we propose an altern…
Slot Attention extracts object-centric representations from images.
Perceptual manifolds arise when a neural population responds to an ensemble of sensory signals associated with different physical features (e.g., orientation, pose, scale, location, and intensity) of the same perceptual object. Object recognition and discrimination requires classifying the manifolds in a manner that is…
New RL framework learns task completion without prior knowledge.
GAN normalizes CT scans for consistent radiomic feature values.
Generative classifiers show surprising human-like performance.
Learning a model of perceptual similarity from a collection of objects is a fundamental task in machine learning underlying numerous applications. A common way to learn such a model is from relative comparisons in the form of triplets: responses to queries of the form "Is object a more similar to b than it is to c?". I…
A new approach to learning in brain-like networks using adversarial algorithms.
Deep learning has brought an unprecedented progress in computer vision and significant advances have been made in predicting subjective properties inherent to visual data (e.g., memorability, aesthetic quality, evoked emotions, etc.). Recently, some research works have even proposed deep learning approaches to modify i…
A new loss function for VAEs improves image quality and efficiency.
Paper presents a new video generation model using diffusion probabilistic methods.
This paper generalizes graph representation for diverse data types.
Enhanced text-to-speech synthesizes expressive speech from a single example.
Active localization is the problem of generating robot actions that allow it to maximally disambiguate its pose within a reference map. Traditional approaches to this use an information-theoretic criterion for action selection and hand-crafted perceptual models. In this work we propose an end-to-end differentiable meth…
PICLE uses probabilistic models to efficiently evaluate and compose modules for continual learning.
New hierarchical VQ-VAE scheme improves image compression quality and features at low bitrates.
Our understanding of reinforcement learning (RL) has been shaped by theoretical and empirical results that were obtained decades ago using tabular representations and linear function approximators. These results suggest that RL methods that use temporal differencing (TD) are superior to direct Monte Carlo estimation (M…
The Gestalt laws of perceptual organization, which describe how visual elements in an image are grouped and interpreted, have traditionally been thought of as innate despite their ecological validity. We use deep-learning methods to investigate whether natural scene statistics might be sufficient to derive the Gestalt …
This research explores a modified VAE model to learn disentangled representations for object recognition.
In this paper we present Percival, a browser-embedded, lightweight, deep learning-powered ad blocker. Percival embeds itself within the browser's image rendering pipeline, which makes it possible to intercept every image obtained during page execution and to perform blocking based on applying machine learning for image…
In this paper, we address the problem of measuring and analysing sensation, the subjective magnitude of one's experience. We do this in the context of the method of triads: the sensation of the stimulus is evaluated via relative judgments of the form: "Is stimulus S_i more similar to stimulus S_j or to stimulus S_k?". …