Research
On-device research index

arXiv research

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.

169,051 papers · 148 categories

Trend · papers per month

14.7%29.5%44.2%59.0% · Jun 202019922001200920182026
48 results for Image-based Learning

SLAC learns latent representations for image-based RL tasks.

problem Challenges in learning policies from high-dimensional image observations.
method SLAC separates representation learning and task learning, using a latent variable model.
result SLAC outperforms model-free and model-based methods in image-based control tasks.

CURL uses contrastive learning to improve reinforcement learning performance.

problem Improving reinforcement learning performance on complex tasks.
method Contrastive learning to extract high-level features from raw pixels, followed by off-policy control.
result CURL outperforms prior methods on DeepMind Control Suite and Atari Games.

Study uncovers uncertainty in traffic prediction models across cities.

problem Lack of interpretability in deep learning models for traffic prediction.
method Investigated uncertainty quantification methods for image-based traffic prediction.
result Meaningful uncertainty estimates can be recovered for traffic prediction.

Convolutional autoencoders improve personalized recommendations from image-based data.

problem Lack of personalized recommendations in gastronomic platforms using image data.
method Used convolutional autoencoders to extract features from images and improve personalized recommendations.
result Convolutional autoencoders outperform standard deep features in image-based personalized recommendation systems.

A novel feature representation method for non-image based features.

problem Inability of Convolutional Neural Networks for non-image based features or features without spatial correlations.
method REFINED: Representation of Features as Images with Neighborhood Dependencies.
result Higher prediction accuracy compared to existing methodologies.

Framework improves agent's ability to learn from noisy images.

problem Agents tend to focus on distracting regions in unsupervised image-based goal exploration.
method Proposes a novel framework combining absolute Learning Progress with unsupervised image-based goal exploration.
result Agents successfully identify and ignore distracting regions, improving overall performance.

ContraBAR uses contrastive learning to learn Bayes-optimal policies in RL.

problem Learning optimal policies for unknown tasks sampled from a known distribution.
method Proposes ContraBAR, a meta RL algorithm using contrastive predictive coding (CPC) for belief inference.
result ContraBAR achieves comparable performance to state-of-the-art methods and is computationally efficient.

Labels distilled from images improve model training efficiency and flexibility.

problem Creating synthetic labels for a small set of real images to train models effectively.
method Introduce a more robust and flexible meta-learning algorithm for distillation and an effective first-order strategy based on convex optimization layers.
result Label distillation leads to improved results and greater flexibility in neural architectures.

DeepAveragers solves offline RL by solving derived MDPs from static data.

problem Offline reinforcement learning with limited data.
method Solves derived non-parametric MDPs (DAC-MDPs) using deep representations and costs for under-represented parts.
result The approach can lower-bound performance and scale to complex offline RL problems.

PlaNet learns latent dynamics from images for better planning in unknown environments.

problem Leveraging planning in unknown environments with accurate dynamics models.
method Deep Planning Network (PlaNet) learns dynamics from images using latent space and multi-step variational inference.
result PlaNet achieves high performance in continuous control tasks with contact dynamics and sparse rewards.

Percival uses deep learning to block ads in real-time, minimizing performance impact.

problem Real-time ad blocking in browsers with minimal performance overhead.
method Deep learning for image classification integrated into browser's rendering pipeline.
result Percival achieves 96.76% accuracy in blocking ads, comparable to block lists.

A method uses RL to learn abstractions for planning, improving robot navigation and manipulation tasks.

problem Planning requires suitable abstractions for states and transitions, which RL struggles with for temporally extended tasks.
method Goal-conditioned policies learned with RL are incorporated into planning, with a latent variable model representing valid states.
result Our method significantly outperforms prior work on image-based robot navigation and manipulation tasks.

Numerous important problems can be framed as learning from graph data. We propose a framework for learning convolutional neural networks for arbitrary graphs. These graphs may be undirected, directed, and with both discrete and continuous node and edge attributes. Analogous to image-based convolutional networks that op…

2016-05-17abs ↗pdf ↗

Deep learning outperforms classic machine learning in DAS event detection.

problem Event detection in Distributed Acoustic Sensing (DAS).
method Comparison of classic machine learning and image-based deep learning approaches.
result Image-based deep learning offers significantly faster event detection and execution times.

Generative Map learns interpretable neural network maps for camera localization.

problem Creating interpretable maps for neural network-based camera localization.
method Combining generative models with Kalman filters and incorporating additional sensor information.
result Generative Map predicts images closely resembling the true scene and achieves comparable localization performance.

EchoFusion tracks and reconstructs fetal images without external trackers.

problem Limited capture range and view-dependent artefacts in fetal ultrasound imaging.
method Combining deep learning and SLAM for image-based tracking and volume reconstruction.
result Demonstrated robust tracking and accurate volume reconstruction in fetal ultrasound.

Personalizes query completion in digital commerce with image-based vectors.

problem High bounce rate and low recurring users in query completion.
method Injects dense vectors from product images into a noisy channel model.
result Image-based personalization improves query completion and user experience.

DeepIST uses CNNs to estimate travel time from path images.

problem Accurately estimating travel time for a path in urban transportation systems.
method Proposes DeepIST, a neural network framework that converts paths into generalized images and uses PathCNN and 1D CNN to capture spatial and temporal patterns.
result DeepIST significantly outperforms existing models in travel time estimation.

A new method uses online mixtures of tasks to improve meta-learning efficiency.

problem Difficulty in meta-learning when tasks are dissimilar or change over time.
method Proposes a Dirichlet process mixture of hierarchical Bayesian models for task-dependent hyperparameter selection.
result Better handles latent distribution shift on evolving few-shot learning benchmarks.

Ano-SuPs detects anomalies in images of manufactured products by identifying suspected patches.

problem Challenges in detecting anomalies in image-based manufacturing systems, including complexity of background and various anomaly patterns.
method Two-stage strategy anomaly detection method: first, remove suspected patches; second, refine anomaly identification using normal patches.
result Demonstrated effectiveness through simulation and case studies, identifying key parameters and steps impacting model performance and efficiency.

Paper introduces SALE for better state-action learning in RL.

problem Challenges in representation learning for low-level states in RL.
method Introduces SALE, a novel approach for learning embeddings of state-action interactions.
result TD7 algorithm significantly outperforms existing continuous control algorithms.

Study improves semantic segmentation of LiDAR point clouds for autonomous vehicles.

problem Semantic understanding of 3D LiDAR data for autonomous vehicles.
method Image-based semantic segmentation architectures, network size optimization, improved point cloud projection, soft Dice loss, reduced weight-sharing convolution.
result 3.2% increase in mIoU segmentation performance with 42% reduction in inference time.

A deep generative model is developed for representation and analysis of images, based on a hierarchical convolutional dictionary-learning framework. Stochastic {\em unpooling} is employed to link consecutive layers in the model, yielding top-down image generation. A Bayesian support vector machine is linked to the top-…

2015-12-23abs ↗pdf ↗

XRAI improves saliency maps for deep neural networks.

problem Improving understanding of deep neural networks through better saliency methods.
method XRAI is a region-based attribution method built upon integrated gradients, with new evaluation methods and sanity checks.
result XRAI produces better results than other saliency methods for common models and the ImageNet dataset.

A counterexample disproves the unknotting number conjecture for a specific knot combination.

problem Disproving the unknotting number conjecture for a particular knot combination.
method Used Snappy to discover and verify a counterexample.
result A counterexample showing u(71#71)5u(7_1\#\overline{7_1})\leq 5 disproves the conjecture.

Paper proposes tensor-based method for semiconductor manufacturing process control.

problem Challenges of traditional process control methods in high-dimensional image-based overlay errors.
method Builds a high-dimensional process model, proposes tensor-on-vector regression algorithms, designs EWMA controller for tensor data.
result The method reduces overlay errors using limited control recipes and is superior especially when disturbances are not stable.

A key challenge in complex visuomotor control is learning abstract representations that are effective for specifying goals, planning, and generalization. To this end, we introduce universal planning networks (UPN). UPNs embed differentiable planning within a goal-directed policy. This planning computation unrolls a for…

2018-04-02abs ↗pdf ↗

Improved image ranking model using ordinal distance metric learning and multidimensional scaling.

problem Ranking images based on known ranked images.
method Proposes an improved linear ordinal distance metric learning approach using multidimensional scaling.
result Demonstrates improved ranking performance and speed over the linear distance metric learning model.

Many advanced Learning from Demonstration (LfD) methods consider the decomposition of complex, real-world tasks into simpler sub-tasks. By reusing the corresponding sub-policies within and between tasks, they provide training data for each policy from different high-level tasks and compose them to perform novel ones. E…

2018-03-02abs ↗pdf ↗

We consider the problem of anomaly detection in images, and present a new detection technique. Given a sample of images, all known to belong to a "normal" class (e.g., dogs), we show how to train a deep neural model that can detect out-of-distribution images (i.e., non-dog objects). The main idea behind our scheme is t…

2018-05-28abs ↗pdf ↗

Study integrates deep learning with financial data for improved trading strategies.

problem Enhancing predictive performance in algorithmic trading and portfolio optimization.
method Developed embedding techniques to treat limit order book snapshots as image-based input channels.
result Achieved state-of-the-art performance in high-frequency trading algorithms.

A CNN-based method detects and counts corn kernels from images.

problem Manual counting of corn kernels is labor-intensive and prone to error.
method Sliding window approach with CNN for detection and NMS for overlapping removal.
result The method successfully detects and counts kernels with low error.