Method generates visual explanations for similarity models without classification.
problem Lack of visual explanations for similarity models trained without classification loss.
method Gradient-based visual attention using learned feature embeddings.
result Attention maps improve model performance and can be used as constraints.
We propose a method to visualize class similarity in large-scale classifiers.
problem Analyzing hierarchical structures and relationships in large-scale classification.
method Compute class similarity based on prediction scores and visualize the class similarity matrix.
result Visualizing class similarity matrices reveals hierarchical structures and relationships.
Kernelized Taylor diagram visualizes data populations with fewer assumptions.
problem Limitations of Taylor diagram in capturing non-linear relationships and sensitivity to outliers.
method Proposes a kernelized version of the Taylor diagram that uses maximum mean discrepancy and kernel mean embedding.
result Kernelized Taylor diagram visualizes data populations with minimal assumptions of data distributions.
Proposes a method to measure model parameter similarity for visual tasks.
problem Estimating relations between different visual tasks.
method LPS method using a second-order neural network to align model parameters and learn second-order similarity.
result Extensive experiments validate the effectiveness of the proposed method.
Method screens similar capsule endoscopic images, reducing doctor workload and improving accuracy.
problem Time-consuming and high error rate in manual inspection of large numbers of similar capsule endoscopic images.
method Structural similarity analysis of visually salient areas and hierarchical clustering.
result 76% reduction in similar images, 100% lesion recall, 18-minute average play time.
Few-shot visual reasoning model learns analogical relationships from small data.
problem Training deep models on few samples for visual reasoning tasks.
method Meta-analogical contrastive learning to enforce structural similarity between training and test samples.
result Method outperforms state-of-the-art on RAVEN dataset with scarce training data.
SAFE detects fake news by analyzing text and image similarities.
problem Detecting fake news with less focus on text-image similarity.
method SAFE uses neural networks to extract text and visual features, then learns their relationship to predict fake news.
result SAFE effectively recognizes fake news based on text, images, or mismatches.
Selecting an optimal set of icons is a crucial step in the pipeline of visual design to structure and navigate through content. However, designing the icons sets is usually a difficult task for which expert knowledge is required. In this work, to ease the process of icon set selection to the users, we propose a similar…
PerceptNet mimics human vision to estimate image quality.
problem Estimating perceptual distance between images and their perturbations.
method Inspired by human visual system, PerceptNet uses convolutional neural network architecture.
result PerceptNet outperforms traditional image quality metrics and deep learning methods.
Introduces CHL, a new loss function for continuous similarity learning.
problem Binary similarity learning limitations.
method CHL is a novel loss function that generalizes histogram loss to continuous similarities.
result CHL solves a wider range of tasks including similarity learning, representation learning, and data visualization.
Entangled bisimulation improves policy learning from visual input.
problem Learning generalizeable policies from visual input in the presence of visual distractions.
method Proposes entangled bisimulation, a bisimulation metric for continuous state and action spaces.
result Entangled bisimulation improves policy learning on the Distracting Control Suite (DCS).
Self-supervised and supervised methods learn similar intermediate visual representations but diverge in final layers.
problem Comparing self-supervised and supervised methods for visual learning.
method Comparison of contrastive self-supervised and supervised methods on simple image data.
result Contrastive and supervised methods learn similar intermediate representations but diverge in final layers.
DCNs are fooled by Gabor noise patterns similar to adversarial perturbations.
problem Sensitivity of DCNs to Gabor noise patterns.
method Examined different DCN architectures and their sensitivity to Gabor noise.
result DCNs are fooled by Gabor noise patterns similar to adversarial perturbations.
Using different methods for laying out a graph can lead to very different visual appearances, with which the viewer perceives different information. Selecting a "good" layout method is thus important for visualizing a graph. The selection can be highly subjective and dependent on the given task. A common approach to se…
We investigate ways in which to improve the interpretability of LDA topic models by better analyzing and visualizing their outputs. We focus on examining what we refer to as topic similarity networks: graphs in which nodes represent latent topics in text collections and links represent similarity among topics. We descr…
Proposes neural similarity for CNNs to enhance flexibility and performance.
problem Limited flexibility of inner product-based convolution in CNNs.
method Introduces neural similarity as a learnable parametric similarity measure, and proposes NSL for adaptive learning from data.
result Dynamic neural similarity improves flexibility and performance in visual recognition and few-shot learning.
DSNE visualizes data velocity in lower dimensions.
problem Understanding movement patterns in high-dimensional data.
method DSNE is a variation of Stochastic Neighbor Embedding that learns velocity embeddings using Euclidean distances on a unit sphere.
result DSNE enables visualization of data movement in lower dimensions.
Twitmo analyzes geo-tagged Twitter data for topic modeling and visualization.
problem Analyzing public discourse on Twitter for various topics, parties, or individuals.
method Collects and preprocesses geo-tagged Tweets, applies LDA, CTM, STM, and visualizes results.
result Automatic pooling of Tweets into pseudo-documents improves topic coherence.
Two new algorithms select matrix rows and columns to preserve distances.
problem Preserving distances in large matrix visualizations.
method Selects rows and columns to preserve distances.
result Preserves distances as closely as possible.
Low dimensional embeddings that capture the main variations of interest in collections of data are important for many applications. One way to construct these embeddings is to acquire estimates of similarity from the crowd. However, similarity is a multi-dimensional concept that varies from individual to individual. Ex…
As machine learning becomes more pervasive, there is an urgent need for interpretable explanations of predictive models. Prior work has developed effective methods for visualizing global model behavior, as well as generating local (instance-specific) explanations. However, relatively little work has addressed regional …
We study the problem of large scale, multi-label visual recognition with a large number of possible classes. We propose a method for augmenting a trained neural network classifier with auxiliary capacity in a manner designed to significantly improve upon an already well-performing model, while minimally impacting its c…
We present an autoencoder that leverages learned representations to better measure similarities in data space. By combining a variational autoencoder with a generative adversarial network we can use learned feature representations in the GAN discriminator as basis for the VAE reconstruction objective. Thereby, we repla…
Visualizes deep neural networks for speech recognition using learned topographic filter maps.
problem Unintuitive internal structure of deep neural networks complicates activation visualization.
method Trains a convolutional speech recognition model with filters arranged in a 2D grid, highlighting similar filters.
result Topographic filter maps visualize artificial neuron activations more intuitively.
Visual spoofing bypasses spam filters and plagiarism detection.
problem Vulnerability in spam filters that can be exploited by visually similar but differently encoded characters.
method Replaces characters with visually similar but differently encoded characters from a different alphabet.
result Spammers can create messages that bypass existing spam filters.
Cross-domain visual data matching is one of the fundamental problems in many real-world vision tasks, e.g., matching persons across ID photos and surveillance videos. Conventional approaches to this problem usually involves two steps: i) projecting samples from different domains into a common space, and ii) computing (…
A CBR approach helps fraud analysts trust machine learning predictions.
problem Understanding the trustworthiness of machine learning predictions for fraud analysts.
method Case-based reasoning (CBR) approach to visualize similar previous instances and their local post-hoc explanations.
result Empirically, the visualization of similar previous instances is useful and easy to use for fraud analysts.
FDive helps analysts create relevant patterns in high-dimensional datasets.
problem Difficult detection of relevant patterns in large, high-dimensional datasets.
method FDive uses a visual active learning system with pattern-based similarity measures to rank and classify data.
result FDive enhances the quality and understanding of relevance models, leading to new insights.
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.
cGAP visualizes high-dimensional categorical data with interpretable geometric structure.
problem Lack of visualization tools for high-dimensional categorical data.
method cGAP uses Homogeneity Analysis (HOMALS) to embed data in a 3D space and maps it to colors.
result cGAP reveals coherent clusters, outliers, and local-to-global structure in categorical data.
cGAP visualizes high-dimensional categorical data with interpretable geometric structure.
problem Lack of visualization tools for high-dimensional categorical data.
method cGAP uses Homogeneity Analysis (HOMALS) to embed data in a 3D space and maps it to colors for visualization.
result cGAP reveals coherent clusters, outliers, and local-to-global structure in categorical data.
Generates music with video emotion using deep neural networks.
problem Generating music with video emotion.
method Hybrid deep neural network combining ANFIS and LSTM.
result Low mean absolute errors and similar global features in spectrograms.
DEN creates interpretable visualizations using Siamese networks.
problem Creating interpretable visualizations of complex datasets.
method Differentiating Embedding Networks (DEN) using Siamese neural networks and loss functions.
result DEN outperforms existing techniques on FashionMNIST and interpretable features are identified.
This work proves the continuum limit of t-SNE for data visualization.
problem Understanding the theoretical basis of t-SNE from a continuum limit perspective.
method Proving the Kullback-Leibler divergence consistency as no∞ for t-SNE. result The continuum variational problem involving non-convex gradient regularization and penalty on probability density function magnitude.
Visualizes DNNs using topographic maps for better understanding.
problem Difficulty in understanding how DNNs solve tasks.
method Adapting neuroscience methods to visualize DNN activations.
result Improved transparency and interpretability of DNN-based systems.
Spring-electrical models predict network links based on node proximity.
problem Predicting links in networks.
method Spring-electrical models applied to network layouts.
result The Euclidean distance in network layouts correlates with link probabilities.
Method retrieves similar fashion items from images and text, enabling style refinement.
problem Lack of intuitive, interactive refinement in search engines for fashion items.
method Joint visual-textual embedding training, Mini-Batch Match Retrieval, attribute extraction.
result Improved performance in multimodal style search, demonstrated through benchmark.
ClusterGraph visualizes and simplifies multidimensional data clusters for better understanding.
problem Lack of global structure information in clustering results.
method Combining clustering with Topological Data Analysis to provide global structure.
result ClusterGraph provides global layout information about clusters.
Two solutions for multi-modal record linkage using Deep Learning inspired by Visual Question Answering.
problem Matching records from multiple sources representing the same entity.
method Two fusion modules: Recurrent Neural Network + Convolutional Neural Network and Stacked Attention Network. A Siamese Neural Network computes similarity.
result Recurrent Neural Network + Convolutional Neural Network fusion module outperforms a simple model.
Study shows perceptual boost of visual attention varies with task difficulty and size.
problem Understanding how task-dependent the perceptual boost of visual attention is in natural settings.
method Designed and trained neural networks on various visual tasks, comparing results to baseline.
result Perceptual boost of attention is stronger with more difficult tasks and weaker with larger task sets.
Centroid-Encoder reduces high-dimensional data for better visualization.
problem Visualizing high-dimensional data efficiently and accurately.
method Centroid-Encoder integrates label information to keep similar objects close in reduced space.
result Centroid-Encoder outperforms other techniques in visualizing high-dimensional data.
MIK improves t-SNE's local structure preservation in biological sequence data.
problem Efficiently preserving local structure in high-dimensional biological sequence data.
method Modified Isolation Kernel (MIK) using adaptive density estimation.
result MIK preserves local and global structure better than Gaussian and isolation kernels.
Paper tackles zero-shot learning for semantic image interpretation.
problem Extracting structured semantic descriptions from images requires complete training sets, which are often unavailable.
method Uses Logic Tensor Networks to leverage logical constraints and similarities among relationships in the training set.
result Background knowledge can alleviate the incompleteness of training sets, improving zero-shot learning performance.
Efficient CNN for VQA achieves similar performance to standard models.
problem Computational intensity of standard VQA models.
method Proposes a sparsely activated CNN architecture.
result Sparsely activated CNN achieves comparable performance.
Proposes a deep Auto-Encoder-like framework for visual-tactile fusion object clustering.
problem Combining visual and tactile information for better object clustering.
method Deep Auto-Encoder-like Non-negative Matrix Factorization framework, graph regularizer, modality-level consensus regularizer, alternating minimization strategy.
result Improves object clustering performance by leveraging both visual and tactile modalities.
Proposes MR-SNE for multimodal data visualization.
problem Visualizing data from multiple domains with relations across them.
method Extends t-SNE to compute augmented relations and jointly embed them in a low-dimensional space.
result Demonstrates promising performance in visualizing Flickr and Animal with Attributes 2 datasets.
We present a novel clustering approach for moving object trajectories that are constrained by an underlying road network. The approach builds a similarity graph based on these trajectories then uses modularity-optimization hiearchical graph clustering to regroup trajectories with similar profiles. Our experimental stud…
Visual question answering is a recently proposed artificial intelligence task that requires a deep understanding of both images and texts. In deep learning, images are typically modeled through convolutional neural networks, and texts are typically modeled through recurrent neural networks. While the requirement for mo…