AVRA automatically rates brain atrophy from MRI images, achieving high agreement with human radiologists.
problem Manual visual rating of brain atrophy by radiologists is time-consuming and inconsistent.
method AVRA uses machine learning, trained on 2350 ratings, to automatically rate various atrophy scales.
result AVRA achieves substantial agreement with human radiologists, with Cohen's weighted kappa values of 0.74-0.74.
Paper proposes a new black-box attack approach to minimize visual distortion.
problem Constructing adversarial examples that minimize visual distortion in a black-box threat model.
method Learning the noise distribution of adversarial examples to approximate the gradient of a non-differentiable loss function.
result The proposed attack results in much lower visual distortion compared to state-of-the-art black-box attacks.
Achieving artificial visual reasoning - the ability to answer image-related questions which require a multi-step, high-level process - is an important step towards artificial general intelligence. This multi-modal task requires learning a question-dependent, structured reasoning process over images from language. Stand…
AV-ASR system improves speech recognition with visual context.
problem Improving speech recognition accuracy with visual information.
method Transformer-based architecture with multiresolution and multimodal training.
result Multiresolution training speeds up convergence and improves WER by 18%.
Following widely used in visual recognition concept of relative attributes, the article establishes definition of the relative PCA attributes for a class of objects defined by vectors of their parameters. A new rating model (RELARM) is built using relative PCA attribute ranking functions for rating object description a…
Paper introduces Balanced Meta-Softmax for better long-tailed visual recognition.
problem Long-tailed distribution mismatch between training and testing data.
method Balanced Meta-Softmax, an unbiased extension of Softmax, using a Meta Sampler.
result Balanced Meta-Softmax outperforms state-of-the-art solutions on visual recognition and instance segmentation.
Person re-identification (re-id), an emerging problem in visual surveillance, deals with maintaining entities of individuals whilst they traverse various locations surveilled by a camera network. From a visual perspective re-id is challenging due to significant changes in visual appearance of individuals in cameras wit…
Neural network training relies on our ability to find "good" minimizers of highly non-convex loss functions. It is well-known that certain network architecture designs (e.g., skip connections) produce loss functions that train easier, and well-chosen training parameters (batch size, learning rate, optimizer) produce mi…
A similarity metric for icon sets simplifies design selection.
problem Designing optimal icon sets is challenging and requires expert knowledge.
method Proposed a Siamese Neural Network trained on human-rated data.
result The model effectively captures style and visual identity similarities.
We employ the Bayesian framework to define a cointegration measure aimed to represent long term relationships between time series. For visualization of these relationships we introduce a dissimilarity matrix and a map based on the Sorting Points Into Neighborhoods (SPIN) technique, which has been previously used to ana…
Large dataset of e-retailer images for improving visual search and product classification.
problem Improving the relevancy of visual search and product recommendation systems.
method Sharing a large dataset of 12M images from an online store classified into 5K categories.
result Demonstrates the effectiveness of deep learning in image classification.
Develops algorithms for efficient visual data compression and search.
problem High-dimensional, large-scale visual data representation.
method Discrete synthesis and analysis models, RRQ and ML-STC frameworks.
result Fast query times and shorter database storage for similarity search.
Theoretical analysis of t-SNE for visualizing clustered data.
problem Understanding t-SNE for visualizing high-dimensional clustered data.
method Gradient descent approach and power iterations based on graph Laplacian.
result Asymptotic equivalence and limiting behavior of t-SNE's early exaggeration stage.
The paper develops a neural network to predict wind speed from visual observations.
problem Accurate wind speed prediction for renewable energy and weather forecasting.
method Coupled Convolutional and Recurrent Neural Network architecture trained on visual flow-structure interactions.
result The model accurately predicts wind speeds with low error compared to cup anemometer measurements.
The paper analyzes how speech enhancement and recognition can be improved in noisy environments.
problem Improving speech recognition in multi-talker scenarios with limited resources.
method Developed and trained two LSTM-based models for speech enhancement and phone recognition, then studied their joint optimization.
result Joint optimization of speech enhancement and recognition leads to a significant reduction in Phone Error Rate (PER).
JD.com uses a new CNN model to improve ad click prediction.
problem Improving CTR prediction for ads with visual content.
method Proposes Category-specific CNN (CSCNN) to incorporate category knowledge early in the feature extraction process.
result CSCNN outperforms existing methods in CTR prediction.
Capsule networks detect and diagnose adversarial images better than CNNs.
problem Detecting and diagnosing adversarial images in neural networks.
method Class-conditional capsule reconstruction and reconstructive attack.
result Capsule networks outperform CNNs in detecting and diagnosing adversarial images.
Search queries are appropriate when users have explicit intent, but they perform poorly when the intent is difficult to express or if the user is simply looking to be inspired. Visual browsing systems allow e-commerce platforms to address these scenarios while offering the user an engaging shopping experience. Here we …
In recent years, deep learning poses a deep technical revolution in almost every field and attracts great attentions from industry and academia. Especially, the convolutional neural network (CNN), one representative model of deep learning, achieves great successes in computer vision and natural language processing. How…
Mobile app uses CNN to help visually impaired cross streets.
problem Helping visually impaired cross streets safely.
method LytNetV2 deep learning model for pedestrian traffic light detection.
result 96% classification accuracy and 6.15 degree angle error.
Although deep learning techniques have been successfully applied to many tasks, interpreting deep neural network models is still a big challenge to us. Recently, many works have been done on visualizing and analyzing the mechanism of deep neural networks in the areas of image processing and natural language processing.…
Framework uses machine learning to distinguish major COVID-19 variants.
problem Discriminate and visualize associations between major COVID-19 variants based on genome sequences.
method Unsupervised machine learning methods, including k-mer analysis, PCA, t-SNE, UMAP, and agglomerative hierarchical clustering.
result Framework effectively distinguishes between major variants and identifies emerging variants.
Large learning rates improve neural network generalization, study shows.
problem Understanding why large learning rates lead to better neural network generalization.
method Visual analysis of training and testing loss landscapes, introduction of a nonlinear model.
result Extended phase with large learning rates leads to near-optimal generalization.
This work explores how XAI methods can visualize the diversity of feature representations in Bayesian Neural Networks.
problem Explaining the diversity of feature representations learned by Bayesian Neural Networks.
method Application of global XAI methods to visualize and quantify the diversity of feature representations.
result The diversity of learned feature representations correlates with uncertainty estimates and network width.
Tangled String visualizes stock market changes at various timescales.
problem Explaining multi-scale contextual shifts in stock market prices.
method Sequence visualization tool based on metaphor of tangled strings.
result Change points in stock prices coincide with real changes.
This paper rates robustness of multi-modal time-series forecasting models.
problem Robustness of AI systems in time-series forecasting is crucial for stakeholders.
method Causal analysis to assess robustness of MM-TSFM models.
result Multi-modal forecasting models are more robust than numeric models.
regvis.net offers a visual survey of regulatory visualization.
problem Lack of a comprehensive resource for regulatory visualization.
method Collection and manual tagging of 80+ publications, creation of a searchable webpage.
result First publication set tailored for regulatory visualization.
SQWA improves low-precision DNNs with model averaging and quantization.
problem Designing good generalization DNNs with quantized weights.
method Floating-point model training, direct quantization, multiple low-precision models, weight averaging, re-quantization, fine-tuning, loss visualization.
result State-of-the-art results for 2-bit QDNNs on CIFAR-100 and ImageNet datasets.
New study shows tradeoffs between compression quality, distortion, and perception.
problem Optimizing compression for low distortion often sacrifices perceptual quality.
method Adopted Blau & Michaeli's perceptual quality definition and studied the rate-distortion-perception tradeoff.
result Restricting perceptual quality to high generally requires a trade-off between rate and distortion.
We study how to leverage off-the-shelf visual and linguistic data to cope with out-of-vocabulary answers in visual question answering task. Existing large-scale visual datasets with annotations such as image class labels, bounding boxes and region descriptions are good sources for learning rich and diverse visual conce…
Paper proposes a method to encrypt faces while maintaining visual similarity.
problem Protecting personal data from unauthorized face recognition.
method Targeted identity-protection iterative method (TIP-IM) to generate adversarial identity masks.
result TIP-IM provides 95%+ protection success rate against face recognition models.
Net2Vis automates CNN visualization for publications.
problem Lack of consistent visual representations in deep learning papers.
method Proposes a visual grammar and automated system for generating publication-ready CNN visualizations.
result Reduces time and ambiguity in generating network visualizations.
Diffusion models improve image compression at low bit-rates.
problem Efficiently compressing images at very low bit-rates.
method Encoding into an embedding, using diffusion models to refine the embedding iteratively.
result Realistic reconstructions can be generated at extremely low bit-rates.
Learning from small amounts of labeled data is a challenge in the area of deep learning. This is currently addressed by Transfer Learning where one learns the small data set as a transfer task from a larger source dataset. Transfer Learning can deliver higher accuracy if the hyperparameters and source dataset are chose…
Objective: To evaluate unsupervised clustering methods for identifying individual-level behavioral-clinical phenotypes that relate personal biomarkers and behavioral traits in type 2 diabetes (T2DM) self-monitoring data. Materials and Methods: We used hierarchical clustering (HC) to identify groups of meals with simila…
Study on implied certainty equivalent rates in financial markets and electric vehicles.
problem Investment risk in financial markets.
method Mathematical derivation of implied certainty equivalent rate, empirical analysis of stock and option data.
result Positive implied certainty equivalent rates are more suitable for investment than negative ones, but higher values increase risk.
Proposes a spectral method to assess and combine multiple data visualizations.
problem Evaluating and combining the strengths of different data visualization algorithms.
method Spectral method for assessing and combining multiple visualizations.
result Proposes a visualization eigenscore to quantify relative performance and a consensus visualization.
The convergence rate and final performance of common deep learning models have significantly benefited from heuristics such as learning rate schedules, knowledge distillation, skip connections, and normalization layers. In the absence of theoretical underpinnings, controlled experiments aimed at explaining these strate…
AV-CPL uses continuous pseudo-labels for AVSR combining labeled and unlabeled data.
problem Improving AVSR performance with labeled and unlabeled data.
method Semi-supervised method using continuous pseudo-labels generated by the same AVSR model.
result Significant improvements in VSR performance on LRS3 dataset.
This paper improves MDS visualization by adjusting Wasserstein distances for heavy-tailed data.
problem Enhancing Multidimensional Scaling (MDS) for better pattern recognition with heavy-tailed distributions.
method Introduces Max-D-SW, a metric adjustment of Max-Sliced Wasserstein distance that aggregates over orthonormal bases.
result Max-D-SW provides a clear numerical advantage in MDS outcomes, especially for heavy-tailed distributions.
A new method improves SSVEP BCI to recognize responses in sub-second time with high accuracy.
problem Achieving high accuracy in SSVEP BCI with short response times.
method CSTA (Combining Spatial-Filtering and Temporal Alignment) method.
result CSTA achieves maximum mean accuracy of 97.43% in sub-second response time.
Visualizes futures markets using particle physics tools.
problem Understanding high-velocity data in futures markets.
method Uses ROOT, an open-source data-analysis tool, to reconstruct and visualize message-based data.
result Allows stakeholders to gain a better understanding of markets and monitor effectively.
New report on machine learning visualization techniques and trends.
problem Improving trust in machine learning models through visualization.
method Analysis of peer-reviewed articles on machine learning visualization techniques.
result Rapid growth in machine learning visualization techniques over the past three years.
The abstract discusses how humans use visualizations in machine learning.
problem The reliance on human involvement in AI systems and analytics.
method Review of seven steps in the ML process and different visualization techniques.
result Different visualizations are used at various stages of the ML process.
IANN visualizes all input variables effects simultaneously.
problem Inability to visualize all input variables effects simultaneously in black-box functions.
method Interpretable Architecture Neural Network (IANN) approach.
result Visualization of all input variables effects directly and simultaneously.
VINE visualizes statistical interactions in complex models.
problem Lack of utilities for regional explanations in black box models.
method VINE algorithm to extract and visualize statistical interaction effects.
result VINE provides a novel evaluation metric for visualizations.
Consensus dimension reduction combines multiple visualizations to identify shared patterns.
problem Conflicting visualizations from different dimension reduction methods.
method Multi-view learning to identify stable patterns across multiple views.
result Consensus visualization effectively identifies shared low-dimensional data structure.
Robotic table tennis learns efficient policies to return balls at 100Hz.
problem Developing efficient robotic table tennis strategies.
method Model-free reinforcement learning using evolutionary search on CNN-based policies.
result Robots can develop multi-modal styles (forehand and backhand) with 80% return rate.