Paper develops an algorithm with PAC guarantees for detecting alien categories.
problem Detecting alien categories not seen in training data reliably.
method Develops an algorithm with PAC-style guarantees for alien detection under known upper bounds on alien fraction.
result Empirical results show the algorithm's effectiveness in detecting aliens.
The Familiarity Hypothesis explains deep open set methods' success in detecting novel objects.
problem Detecting novel objects in open set recognition problems.
method Logits-based detection of absence of familiar features.
result Familiarity-based detection fails in scenarios with both novel and familiar objects.
Survey of deep learning methods for anomaly detection.
problem Detecting anomalies in various applications.
method Review of deep learning techniques for anomaly detection.
result Comprehensive overview of deep learning methods for anomaly detection.
Classi-Fly uses machine learning to infer aircraft categories from open data.
problem Lack of metadata for aircraft in open data sources.
method Machine learning approach based on aircraft movement patterns.
result Correct aircraft category inference with over 88% accuracy.
Research improves open-set learning by leveraging unlabelled data.
problem Learning between observed and unobserved novel categories.
method Unified policy of positive and unlabelled learning, semi-supervised learning, and open-set recognition.
result Achieves state-of-the-art results in open-set learning.
Study compares community detection methods in various networks.
problem Determine which community detection method is best for specific network types.
method Comprehensive empirical analysis of multiple methods on diverse network categories.
result Identifies different types of communities produced by various methods.
Motivated by the Moore-Segal axioms for an open-closed topological field theory, we consider planar open string topological field theories. We rigorously define a category 2Thick whose objects and morphisms can be thought of as open strings and diffeomorphism classes of planar open string worldsheets. Just as the categ…
New method detects novel node categories in graphs with distribution shifts.
problem Detecting novel node categories in graphs with distribution shifts.
method Recall-Constrained Optimization with Selective Link Prediction (RECO-SLIP).
result RECO-SLIP outperforms existing methods in detecting novel node categories.
Learning automatically the structure of object categories remains an important open problem in computer vision. In this paper, we propose a novel unsupervised approach that can discover and learn landmarks in object categories, thus characterizing their structure. Our approach is based on factorizing image deformations…
Open 2D TFTs extend to closed theories with circle value as Hochschild homology.
problem Extending open 2D TFTs to closed theories.
method Using symmetric monoidal ∞-categories and Hochschild homology.
result Open 2D TFTs admit initial open-closed extensions.
Studies amenable category's monotonicity and its relation to topological complexity.
problem Monotonicity of amenable category for degree-one maps.
method Uses amenable covers and compares with topological complexity.
result Establishes a relation between amenable category and topological complexity.
In this paper we study the topology of the cobordism category of open and closed strings. This is a 2-category in which the objects are compact one-manifolds whose boundary components are labeled by an indexing set (the set of "D-branes"), the 1-morphisms are cobordisms of manifolds with boundary, and the 2-morphisms a…
Paper detects duality obstruction in smooth calibrations.
problem Detecting duality obstruction in smooth calibrations.
method Examine Lawlor cones and calibrations, use gluing results.
result Existence of Lawlor cones without smooth calibrations.
OpenViewer tackles multi-view learning challenges with interpretability and generalization.
problem Lack of interpretability and insufficient generalization in multi-view learning models.
method OpenViewer introduces a Pseudo-Unknown Sample Generation Mechanism, Expression-Enhanced Deep Unfolding Network, and Perception-Augmented Open-Set Training Regime.
result OpenViewer effectively addresses openness challenges and enhances recognition performance for both known and unknown samples.
Study on polynomiality and outer nature of functors from Jacobi diagrams to group homomorphisms.
problem Understanding polynomiality and outer nature of functors from Jacobi diagrams to group homomorphisms.
method Analyzing polynomiality and outer nature of functors from Jacobi diagrams to group homomorphisms.
result Results generalize previous work by Katada and study polynomiality and outer nature of these functors.
Solves open problem on Lie groupoids equivalence.
problem Whether Lie groupoids Morita equivalent are diffeologically Morita equivalent.
method Localisation of 2-categories, anafunctors, Lie groupoids, diffeological groupoids.
result Two Lie groupoids diffeologically Morita equivalent are Morita equivalent in the Lie sense.
Deep learning improves anomaly detection across various fields.
problem Detecting anomalies in data with advanced approaches.
method Survey of deep learning methods for anomaly detection.
result Advancements in deep anomaly detection address unique challenges.
As we enter into the big data age and an avalanche of images have become readily available, recognition systems face the need to move from close, lab settings where the number of classes and training data are fixed, to dynamic scenarios where the number of categories to be recognized grows continuously over time, as we…
Completes reduction scheme in Lagrange-Poincaré category.
problem Lagrangian reduction by stages in the whole category.
method Analyzes Noether theorem, Hamiltonian reduction, geometric aspects.
result Affirmative answer to open question of Lagrangian reduction.
This paper reviews information theory in open-world machine learning.
problem Lack of a unified theoretical foundation for open-world machine learning.
method Synthesis of information theoretic approaches.
result Established a pathway toward provable and trustworthy open world intelligence.
Constructs a cyclic, filtered, strictly unital curved A∞ category for Lagrangian submanifolds and develops Floer theory.
problem Proving that any Lagrangian submanifold equipped with a weak bounding cochain lies in the category split-generated by a given collection of Lagrangian submanifolds.
method Develops a cyclic, filtered, strictly unital curved A∞ category and uses it to prove the above statement. result Any Lagrangian submanifold equipped with a weak bounding cochain lies in the category split-generated by a given collection of Lagrangian submanifolds.
New invariants detect exotic smooth structures in 4-manifolds.
problem Detect exotic smooth structures in 4-manifolds using invariants of 2-handlebodies.
method Investigates invariants of 4-dimensional 2-handlebodies from the Temperley-Lieb category in positive characteristic.
result Height n=2 invariant vanishes on CP2, CP2, and S2imesS2 for p>3. This paper introduces tangent display maps to simplify tangent category theory.
problem The category of smooth manifolds does not admit all pullbacks, complicating tangent category theory.
method Develops tangent display maps as a special class of maps well-behaved with respect to pullbacks.
result Tangent display maps simplify previous work in tangent categories and provide a new way to define open subobjects.
Functor connects 4D 2-handlebodies to ribbon categories, detecting non-deformation diffeomorphisms.
problem Detecting non-deformation diffeomorphisms in 4D 2-handlebodies.
method Constructs a braided monoidal functor from 4D 2-handlebodies to unimodular ribbon categories.
result Functor J4 detects non-deformation diffeomorphisms when H∗ is not semisimple and H is not factorizable. New algorithm detects rare categories with few labels.
problem Detecting rare categories with limited labeled data.
method Dimension-driven statistics and kappa-profile.
result Algorithm performs well on separable and non-separable classes.
A new method detects epileptic events in EEG signals by integrating labeler categories.
problem Human oversight of brief epileptic events in EEG signals leads to inaccurate diagnoses.
method Integrates EEG signal features with one-hot encoded labeler categories for improved detection.
result The method outperforms consensus-trained detectors and maintains confidence bounds.
Detects right-veering properties in open books using combinatorial methods.
problem Determining the right-veering property of contact structures.
method Combinatorial approach to detect left-veering arcs in open books.
result Existence of an algorithm to detect right-veering for compact surfaces.
Dataset for object detection at Oktoberfest beer tent.
problem Realistic object detection in a busy, diverse setting.
method Hand-annotated 1,110 images, provided trained models.
result Challenging dataset for object detection.
Many systems of interest in science and engineering are made up of interacting subsystems. These subsystems, in turn, could be made up of collections of smaller interacting subsystems and so on. In a series of papers David Spivak with collaborators formalized these kinds of structures (systems of systems) as algebras o…
Robotic clothing manipulation improved with fashion image analysis techniques.
problem Automated identification of clothing categories and landmarks for robotic tasks.
method Training data augmentation methods and rotation invariant convolutions.
result Our approach outperforms state-of-the-art models on unseen datasets.
With the proliferation of social media, fashion inspired from celebrities, reputed designers as well as fashion influencers has shortened the cycle of fashion design and manufacturing. However, with the explosion of fashion related content and large number of user generated fashion photos, it is an arduous task for fas…
Study categorizes and analyzes emotions in sexist tweets.
problem Lack of defined categories for sexism in NLP.
method Used a new dataset from SemEval-2018 to classify and analyze emotions in sexist tweets.
result Demonstrated the mental state and affectual state of users who tweet in different categories of sexism.
OpenHAIV integrates OOD detection and incremental learning for open-world models.
problem Challenges in open-world recognition, especially in model knowledge updates and OOD detection.
method Unified pipeline combining OOD detection, new class discovery, and incremental fine-tuning.
result Models can autonomously acquire and update knowledge in open-world environments.
Survey examines anomaly detection methods for deep learning.
problem Out-of-distribution and adversarial examples in deep learning.
method Taxonomy of existing anomaly detection techniques.
result Discussion of strengths and weaknesses of techniques.
WSGN detects actions from weak supervision, improving performance on THUMOS14 and Charades.
problem Challenging action detection requires detailed manual supervision.
method WSGN learns action detection from video-level labels, exploiting both video-specific and dataset-wide statistics.
result WSGN achieves significant gains in action detection for THUMOS14 and Charades datasets.
Geometric Graph Alignment enhances IoT intrusion detection using NID data.
problem Data scarcity hinders IoT intrusion detection accuracy.
method Geometric Graph Alignment (GGA) approach to transfer knowledge between network intrusion detection and IoT intrusion detection domains.
result GGA approach boosts IoT intrusion detection performance on multiple datasets.
Local-HDP learns independent topics for each 3D object category in real-time.
problem Learning independent topics for each 3D object category in real-time.
method Local-Hierarchical Dirichlet Process (Local-HDP) with online variational inference.
result Local-HDP outperforms other approaches in accuracy, scalability, and memory efficiency.
Proposes IFCDA framework to improve cross-domain adaptation.
problem Negative transfer and difficulty in handling category-irrelevant losses in DA.
method Importance filtered mechanism to generate filtered soft labels, combined with graph-based label propagation.
result Significantly improves performance in both Closed-Set and Open-Set DA scenarios.
New geometric construction of spectral sequences from Khovanov homology.
problem Understanding spectral sequences from Khovanov homology.
method Cylindrical model to compute Fukaya categories of Hilbert schemes.
result New geometric construction of spectral sequences from Khovanov homology.
Develops a framework for continual learning in anomaly detection.
problem Deterioration of monitoring performance due to new defect categories.
method Pseudo replay-based class incremental learning with oversampling.
result Enhanced monitoring performance and flexibility in model architecture.
Smooth FFT from B-fields and D-branes.
problem Constructing a smooth functorial field theory from B-fields and D-branes.
method Definition of a smooth bordism category, transgression, functoriality, thin homotopy invariance, positive reflection structure.
result Generalizes open-closed TQFTs to include target spaces and open strings.
We consider the bulk algebra and topological D-brane category arising from the differential model of the open-closed B-type topological Landau-Ginzburg theory defined by a pair (X,W), where X is a non-compact Calabi-Yau manifold and W has compact critical set. When X is a Stein manifold (but not restricted to b…
This paper proposes the adaptation of Support Vector Data Description (SVDD) to the multiple kernel case (MK-SVDD), based on SimpleMKL. It also introduces a variant called Slim-MK-SVDD that is able to produce a tighter frontier around the data. For the sake of comparison, the equivalent methods are also developed for O…
The aim of this paper is to use the so-called Cayley transform to compute the LS category of Lie groups and homogeneous spaces by giving explicit categorical open coverings. When applied to U(n), U(2n)/Sp(n) and U(n)/O(n) this method is simpler than those formerly known. We also show that the Cayley transform is re…
New approach detects racial segregation patterns in machine learning systems.
problem Challenges of fairness in machine learning systems due to racial identity.
method Unsupervised learning to detect patterns of segregation.
result Mitigates root cause of social disparities without reifying race.
Unified detection of isolated and overlapping audio events using CNN-RNN.
problem Detecting both isolated and overlapping audio events simultaneously.
method Multi-label multi-task framework based on CNN-RNN, with sequential losses.
result Good generalization on isolated and overlapping audio event detection datasets.
Study of B-type LG models on open Riemann surfaces.
problem Understanding triangulated structures and D-branes in open Riemann surface models.
method Investigation of B-type topological Landau-Ginzburg models with arbitrary open Riemann surfaces.
result Complete description of the triangulated structure of the category of topological D-branes.
We develop a generalization of manifold calculus in the sense of Goodwillie-Weiss where the manifold is replaced by a simplicial complex. We consider functors from the category of open subsets of a fixed simplical complex into the category of topological spaces and prove an analogue of the approximation theorem. Namely…