A new framework decouples CNN features into intra-class and semantic differences.
problem Learning visual representations in CNNs is challenging.
method Proposes a decoupled learning framework that models intra-class variation and semantic difference independently.
result Decoupled reparameterization leads to significant performance gains and easier convergence.
Paper proposes a deep learning method for person re-identification using set to set distance.
problem Matching images of the same person across different camera views with large appearance variations.
method Uses deep learning to model set to set (S2S) distance, focusing on intra-class compactness and inter-class separation.
result The method effectively finds matched targets in video galleries, outperforming state-of-the-art approaches.
Blind source separation is a common processing tool to analyse the constitution of pixels of hyperspectral images. Such methods usually suppose that pure pixel spectra (endmembers) are the same in all the image for each class of materials. In the framework of remote sensing, such an assumption is no more valid in the p…
Paper proposes angular loss for better face recognition and object classification.
problem Improving intra-class compactness and preventing overfitting in face recognition and object classification.
method Angular loss function to maximize angular gradient, reducing overfitting and requiring only one adjustable constant.
result Our method outperforms other methods in accuracy, discriminative information, and time-efficiency.
A new method learns features for one-class classification using intra-class splitting.
problem Challenges in one-class classification due to limited normal class samples.
method Intra-class splitting and joint training of typical and atypical samples with loss functions.
result The method outperforms other models in one-class classification tasks.
We introduce a conditional generative model for learning to disentangle the hidden factors of variation within a set of labeled observations, and separate them into complementary codes. One code summarizes the specified factors of variation associated with the labels. The other summarizes the remaining unspecified vari…
D-CBRS manages memory for continual learning by accounting for intra-class diversity.
problem Forgetting in continual learning, especially with class-imbalanced data.
method D-CBRS introduces a novel approach to store instances in memory, considering intra-class diversity.
result D-CBRS outperforms existing methods on data sets with intra-class diversity.
Graph filtering reduces intra-class noise for improved classification accuracy.
problem Noise in training data affects classifier performance.
method Graph filtering to connect similar samples within a class.
result Asymptotic reduction of intra-class variance while maintaining mean.
A deep clustering method for hyperspectral images improves clustering performance by constraining intra-class distances.
problem Clustering performance degradation in hyperspectral images due to high dimensionality.
method Intra-class distance constrained deep clustering algorithm using auto-encoder network.
result The proposed algorithm outperforms state-of-the-art methods in clustering hyperspectral images.
This paper refines MMD for domain adaptation by balancing intra-class and inter-class distances.
problem Balancing intra-class and inter-class distances for better feature discriminability in domain adaptation.
method The paper theoretically proves two facts about MMD and proposes a novel discriminative MMD method to balance intra-class and inter-class distances.
result The proposed method improves feature discriminability and outperforms state-of-the-art methods.
A new model classifies surface anomalies in 3D point cloud data.
problem Accurate classification of surface anomalies in manufacturing processes.
method Deep subspace learning approach for 3D point cloud data.
result The method effectively identifies new types of anomalies.
End-to-end open-set recognition using intra-class splitting.
problem Open-set recognition with limited known samples.
method Intra-class data splitting to model unknown classes.
result Outperformed baselines and improved state-of-the-art methods.
Proposes GM Score to evaluate GANs considering diversity, disentanglement, and discriminability.
problem Evaluation of GANs for sample quality and diversity.
method Integrates various factors including intra-class and inter-class diversity, disentanglement, and discriminability metrics.
result Demonstrates improved evaluation of GANs on MNIST dataset.
The paper analyzes how well classes are separated in neural network feature space.
problem Understanding class separability in neural network feature space.
method Theoretical analysis of intra-class and inter-class distances in feature space.
result A lower bound for the probability of inter-class distance being greater than intra-class distance as a function of loss value.
A new loss function HUG decouples and generalizes neural collapse.
problem Neural collapse limits in deep learning models.
method Hyperspherical uniformity gap (HUG) as a unified framework.
result HUG decouples and generalizes neural collapse, improving model flexibility and robustness.
New method regularizes deep networks by distilling self-knowledge.
problem Overfitting in deep neural networks.
method Self-knowledge distillation to regularize class-wise predictions.
result Significant improvement in generalization and calibration.
This paper uses deep neural networks for one-class classification by splitting normal data into typical and atypical subsets.
problem Training deep neural networks with only one class of data for one-class classification.
method Intra-class splitting to create typical and atypical subsets, using binary loss and auxiliary subnetworks.
result The method outperformed seven baselines and had comparable performance to state-of-the-art methods on image datasets.
Traditional nearest points methods use all the samples in an image set to construct a single convex or affine hull model for classification. However, strong artificial features and noisy data may be generated from combinations of training samples when significant intra-class variations and/or noise occur in the image s…
Graph attention improves node classification by distinguishing important edges.
problem Node classification in graph-based learning models.
method Theoretical analysis of graph attention networks for node classification.
result Graph attention can perfectly classify nodes in an 'easy' regime but fails in a 'hard' regime.
Two novel methods improve network embedding for completely-imbalanced labels.
problem Improving network embedding for networks with completely-imbalanced labels.
method Two novel semi-supervised network embedding methods: RSDNE and RECT.
result Experimental results show the superiority of the proposed methods.
COBRA reduces modality gap in cross-modal tasks.
problem Joint embedding spaces fail to sufficiently reduce modality gap in multi-modal tasks.
method COBRA trains image and text modalities in a joint fashion using Contrastive Predictive Coding and Noise Contrastive Estimation.
result COBRA significantly reduces the modality gap and generates robust joint-embedding space.
ECGs improve GNNs for non-homophilic data.
problem Improving GNNs for datasets where nodes are not likely to belong to the same class.
method ECGs rewire GNNs' computation graph to connect nodes likely in the same class using weaker classifiers.
result ECGs improve GNN performance on non-homophilic datasets.
New theory explains contrastive learning via overlapping augmented views.
problem Lack of theoretical understanding of contrastive learning.
method Augmentation overlap perspective to improve downstream performance.
result Asymptotically closed bounds for downstream performance under weaker assumptions.
Graph-based methods are known to be successful in many machine learning and pattern classification tasks. These methods consider semi-structured data as graphs where nodes correspond to primitives (parts, interest points, segments, etc.) and edges characterize the relationships between these primitives. However, these …
This work explores the relationship between expressivity and generalization in GNNs.
problem Understanding the trade-off between expressivity and generalization in GNNs.
method Introducing a novel framework that connects GNN generalization to the variance in graph structures they can capture.
result Theoretical findings align with empirical results, offering a deeper understanding of how expressivity enhances GNN generalization.
PSC classifier improves HDLSS classification on class-imbalanced data.
problem Classification on high-dimension low-sample-size data with class imbalance.
method Population Structure-learned Classifier (PSC) maximizing inter-class and intra-class scatter matrices.
result PSC outperforms state-of-the-art methods on IHDLSS.
DS-UI improves DNN uncertainty inference by combining a DNN classifier with MoGMM.
problem Improving uncertainty inference in DNN-based image recognition.
method Combines DNN classifier with MoGMM for probabilistic interpretation of features.
result DS-UI outperforms state-of-the-art UI methods in misclassification detection.
AdaCAD improves semi-supervised classification by focusing on intra-class nodes.
problem Improving semi-supervised classification by addressing inter-class connections in graphs.
method AdaCAD uses a class-attentive diffusion process to adaptively aggregate nodes based on their class similarity.
result AdaCAD significantly outperforms state-of-the-art methods in semi-supervised classification.
Fine-grained visual categorization (FGVC) is to categorize objects into subordinate classes instead of basic classes. One major challenge in FGVC is the co-occurrence of two issues: 1) many subordinate classes are highly correlated and are difficult to distinguish, and 2) there exists the large intra-class variation (e…
Proposes multi-neighborhood LBPs for land use classification.
problem Challenges in classifying land use images due to intra class variability and inter class similarities.
method Uses multi-neighborhood LBPs combined with nearest neighbor classifier.
result Achieved an accuracy of 77.76% on UC Merced 21 class land use image dataset.
Unified model for age-invariant face recognition with photorealistic face synthesis.
problem Reliable face recognition across ages remains challenging due to significant intra-class variations.
method Unified deep architecture for cross-age face synthesis and recognition, continuous face rejuvenation/aging, disentangled age-invariant face representations.
result Superior performance on CAFR and other cross-age datasets, promising generalizability to unconstrained face recognition.
OLÉ simplifies deep learning by enforcing class orthogonality.
problem Training deep networks for image classification without enforcing intra-class similarity and inter-class margin.
method OLÉ collapses class features into a learned subspace and pushes subspaces to be orthogonal.
result OLÉ improves classification performance and robustness.
DUPLE tackles cross-deployment recognition in fiber-optic perimeter security with meta-learning.
problem Cross-deployment recognition challenges in fiber-optic perimeter security due to label scarcity and distribution shifts.
method DUPLE employs statistically guided meta-learning to enhance recognition robustness across unseen deployments.
result DUPLE consistently outperforms traditional and meta-learning baselines in cross-deployment DFOS benchmarks.
We propose a novel method for automatic pain intensity estimation from facial images based on the framework of kernel Conditional Ordinal Random Fields (KCORF). We extend this framework to account for heteroscedasticity on the output labels(i.e., pain intensity scores) and introduce a novel dynamic features, dynamic ra…
ISDA augments deep networks by adding semantic transformations.
problem Improving deep network generalization through semantic data augmentation.
method ISDA augments deep feature space by estimating covariance and drawing random vectors.
result ISDA consistently improves deep model performance on various datasets.
Cross-entropy loss together with softmax is arguably one of the most common used supervision components in convolutional neural networks (CNNs). Despite its simplicity, popularity and excellent performance, the component does not explicitly encourage discriminative learning of features. In this paper, we propose a gene…
Efficient system classifies EEG signals for cognitive tasks using nuclear features.
problem Classification of raw EEG signals for cognitive tasks is challenging.
method Singular value decomposition for computing dominant variances of EEG signals, using them as nuclear features, and a simple classifier.
result Nuclear features from frontal brain region achieved 100% prediction accuracy.
Deep transfer learning from Persian handwriting improves offline signature verification.
problem Challenges in offline signature verification, especially with skilled forgeries and limited training data.
method Transfer learning approach from Persian handwriting to multi-language OSV, using Residual CNNs for feature learning and SVMs for verification.
result Significant improvement in Equal Error Rate (EER) on UT-Sig dataset (9.80% EER), surpassing state-of-the-art methods.
A deep network classifies images by scattering and dictionary learning.
problem Classifying images with high accuracy using deep learning.
method Sparse scattering transform followed by ℓ1 dictionary learning in a deep convolutional network. result Higher classification accuracy than AlexNet on ImageNet dataset.
We introduce a novel loss max-pooling concept for handling imbalanced training data distributions, applicable as alternative loss layer in the context of deep neural networks for semantic image segmentation. Most real-world semantic segmentation datasets exhibit long tail distributions with few object categories compri…
SupSiam and SupBYOL improve supervised representation learning with ANCL.
problem Improving supervised representation learning with ANCL.
method Proposed supervised ANCL framework leveraging labels to avoid collapse.
result Supervised ANCL improves representation learning across various datasets and tasks.
Boosts neural network performance by improving weight separability.
problem Improving the separability of weight vectors in neural networks.
method Proposes a new evaluation metric and feed-backward reconstruction loss to encourage weight separability.
result Improves visual recognition performance across various tasks.
Kernel methods are widespread in machine learning; however, they are limited by the quadratic complexity of the construction, application, and storage of kernel matrices. Low-rank matrix approximation algorithms are widely used to address this problem and reduce the arithmetic and storage cost. However, we observed tha…
ForestHash combines random forests and CNNs for efficient data hashing.
problem Efficiently hashing large datasets while preserving similarity.
method Random forests with light-weight CNNs, grouping classes, and information-theoretic aggregation.
result Significantly outperforms state-of-the-art hashing methods for image retrieval.
Paper proposes a method for faster object detection annotation in indoor scenes.
problem Efficiently annotate object detection datasets in indoor scenes.
method Two-stage annotation process: manual annotation of a part of the dataset, followed by automatic annotation of the rest.
result The two-stage method significantly reduces the total workload compared to manual annotation of the entire dataset.
Improves low-shot learning with novel GAN for diverse example generation.
problem Overfitting and forgetting in small data settings.
method Covariance-Preserving Adversarial Augmentation Networks (CPGANs).
result Significant improvement on ImageNet benchmark.
New bounds improve graph node classification using optimal transport.
problem Improving transductive generalization bounds for graph node classification.
method Representation-based generalization bounds via optimal transport, expressed in terms of Wasserstein distances.
result Strong correlation between derived bounds and empirical generalization in graph node classification.
Graph data augmentation improves GNN performance in node classification.
problem Improving generalizability of graph neural networks (GNNs) in semi-supervised node classification.
method Introduces GAug framework for graph data augmentation using neural edge predictors.
result GAug framework improves GNN-based node classification performance across various architectures and datasets.