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.
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.
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.
Paper proposes a new framework for hypothesis testing in imaging.
problem Challenges in hypothesis testing for imaging data.
method Combines self-supervised imaging, vision-language models, and non-parametric hypothesis testing.
result Demonstrates improved power and robust error control in image-based phenotyping.
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.
Model learns Lagrangian dynamics from images for better prediction and control.
problem Lack of interpretability and applicability to high-dimensional data like images.
method Unsupervised neural network model that learns Lagrangian dynamics from images using a coordinate-aware VAE.
result Model infers interpretable Lagrangian dynamics, enabling long-term prediction and synthesis of controllers.
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.
In the recent years Generative Adversarial Networks (GANs) have demonstrated significant progress in generating authentic looking data. In this work we introduce our simple method to exploit the advancements in well established image-based GANs to synthesise single channel time series data. We implement Wasserstein GAN…
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.
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…
A neural network approach to compute stable metrics for numerical simulation data.
problem Computing stable and generalizing metrics for diverse numerical simulation data.
method A Siamese neural network architecture with a specialized loss function trained on a controlled data generation setup.
result LSiM outperforms existing metrics for vector spaces and image-based metrics.
Improved model-free RL from images with stable training.
problem Training RL agents from high-dimensional images is challenging.
method Used variational autoencoders with auxiliary losses to stabilize training.
result Proposed techniques improve sample efficiency and robustness.
Automated system identifies and counts insects from images.
problem Manual sorting and identification of insect samples is time-consuming and limits biodiversity mapping.
method Robot-enabled image-based identification machine using CNNs.
result Classification accuracy of 0.980 for initial dataset. Reinforcement learning algorithms struggle when the reward signal is very sparse. In these cases, naive random exploration methods essentially rely on a random walk to stumble onto a rewarding state. Recent works utilize intrinsic motivation to guide the exploration via generative models, predictive forward models, or …
Planning has been very successful for control tasks with known environment dynamics. To leverage planning in unknown environments, the agent needs to learn the dynamics from interactions with the world. However, learning dynamics models that are accurate enough for planning has been a long-standing challenge, especiall…
This paper presents a module of vehicle reidentification based on make/model and color classification. It could be used by the Automated Vehicular Surveillance (AVS) or by the fast analysis of video data. Many of problems, that are related to this topic, had to be addressed. In order to facilitate and accelerate the pr…
Proposes DLGPD model to learn dynamics from images for planning.
problem Planning in unknown, indirectly observable environments.
method Deep latent Gaussian process dynamics model trained jointly with neural networks.
result Demonstrates improved data efficiency and transfer learning.
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.
Paper uses CNN to predict process parameters from molten pool data in WLAM.
problem Achieving high quality in WLAM through real-time process control.
method Proposes a multi-modality CNN architecture to predict process parameters from molten pool sensor data.
result Improved prediction performance of multi-modal CNN compared to uni-modal approach.
In this paper, we consider the problem of malware detection and classification based on image analysis. We convert executable files to images and apply image recognition using deep learning (DL) models. To train these models, we employ transfer learning based on existing DL models that have been pre-trained on massive …
Paper tackles score following in full-page sheet music images.
problem Score following in unprocessed sheet music images.
method Directly predicts score positions from audio and image input.
result Outperforms state-of-the-art methods in alignment precision.
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.
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…
A method for self-supervised representation learning in partially observable environments.
problem Sparse rewards and stochasticity in partially observable environments.
method World model in latent space for estimating missing information.
result Significant improvement in exploration compared to prior work.
A novel method automates quality control of fMRI scans, improving accuracy and generalizability.
problem Lack of automated QC for fMRI scans limits clinical neuroscience research.
method Train machine learning classifiers using runtime log features to predict scan quality.
result Classifiers trained on FLAG-QC features outperform previous methods (AUC=0.79 vs AUC=0.56).
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.
Generative model improves time series prediction quality.
problem Lack of effective generative models for time series data.
method Proposed XIRP for time series, trained with WGAN-GP.
result XIRP significantly outperforms RNN-based models in predictive ability.
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.
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…
Combines BC and GAIL for efficient imitation learning.
problem Efficient imitation learning without reward signals.
method Integrates Behavior Cloning and Generative Adversarial Imitation Learning.
result Combination leads to stable and sample-efficient learning.
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.
BCRL learns a Bellman complete representation for offline RL policy evaluation.
problem Learning a Q-function efficiently from offline data.
method BCRL learns a linear Bellman complete representation directly from data, enabling efficient OPE.
result BCRL achieves competitive OPE error and outperforms FQE in certain scenarios.
HTRPO tackles sparse rewards in RL with improved stability and performance.
problem Sparse rewards in reinforcement learning.
method HTRPO extends TRPO with hindsight and QKL for better policy update stability.
result HTRPO consistently outperforms TRPO and HPG in various sparse reward tasks.
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.
A CNN-based model improves stock price prediction accuracy.
problem Overfitting in image-based stock prediction models.
method SMSFR-CNN combining CNN and image features.
result SMSFR-CNN achieves high predictive accuracy on A-share stocks.
Robust detection and tracking of objects is crucial for the deployment of autonomous vehicle technology. Image based benchmark datasets have driven development in computer vision tasks such as object detection, tracking and segmentation of agents in the environment. Most autonomous vehicles, however, carry a combinatio…
DSM improves visual quality of fetoscopic videos by mosaicking.
problem Challenges in identifying all vascular connections during fetoscopy due to low visual quality and drift.
method Proposes a Deep Sequential Mosaicking (DSM) framework using deep learning techniques to handle visual variations and reduce drift.
result DSM framework reduces accumulated drift and improves visual quality of fetoscopic videos.
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.
In image-based camera localization systems, information about the environment is usually stored in some representation, which can be referred to as a map. Conventionally, most maps are built upon hand-crafted features. Recently, neural networks have attracted attention as a data-driven map representation, and have show…
Turbo-DDCM speeds up zero-shot image compression.
problem Slowness and high computational demand in zero-shot diffusion-based compression.
method Modified DDCM framework with Turbo-DDCM, combining noise vectors and improved encoding.
result Turbo-DDCM achieves faster compression than state-of-the-art methods.
Study finds visual explanations do not significantly improve human accuracy or trust in model predictions.
problem Measuring the impact of visual explanations on human accuracy and trust in model predictions.
method Randomized controlled trial with image-based age prediction task, varying levels of explanation quality.
result Visual explanations do not significantly alter human accuracy or trust in the model.
Multi-StyleGAN simulates live cell microscopy imagery.
problem Costly and complex live cell experiments.
method Generative adversarial network (GAN) synthesizing multi-domain time-lapse images.
result Captures biophysical factors and time dependencies in cell imagery.
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.
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)≤5 disproves the conjecture. 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.
Distributed Acoustic Sensing (DAS) using fiber optic cables is a promising new technology for pipeline monitoring and protection. In this work, we applied and compared two approaches for event detection using DAS: Classic machine learning approach and the approach based on image processing and deep learning. Although w…
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.
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…