LSD-C: linearly separable deep clusters

LSD-C: linearly separable deep clusters

We present LSD-C, a novel method to identify clusters in an unlabeled dataset. Our algorithm first establishes pairwise connections in the feature space between the samples of the minibatch based on a similarity metric. Then it regroups in clusters the connected samples and enforces a linear separat...

Fuld beskrivelse

Bibliografiske detaljer
Main Authors:	Rebuffi, SA, Ehrhardt, S, Han, K, Vedaldi, A, Zisserman, A
Format:	Conference item
Sprog:	English
Udgivet:	IEEE 2021

Lignende værker

Automatically discovering and learning new visual categories with ranking statistics
af: Han, K, et al.
Udgivet: (2020)

Semi-supervised learning with scarce annotations
af: Rebuffi, SA, et al.
Udgivet: (2020)

AutoNovel: automatically discovering and learning novel visual categories
af: Han, K, et al.
Udgivet: (2021)

Learning to discover novel visual categories via deep transfer clustering
af: Han, K, et al.
Udgivet: (2020)

Efficient parametrization of multi-domain deep neural networks
af: Rebuffi, S, et al.
Udgivet: (2018)

Learning multiple visual domains with residual adapters
af: Rebuffi, S, et al.
Udgivet: (2018)

Deep face recognition
af: Parkhi, O, et al.
Udgivet: (2015)

Deep Fisher networks for large-scale image classification
af: Simonyan, K, et al.
Udgivet: (2013)

Deep features for text spotting
af: Jaderberg, M, et al.
Udgivet: (2014)

Deep inside convolutional networks: visualising image classification models and saliency maps
af: Simonyan, K, et al.
Udgivet: (2014)

The Role of LSD1 and LSD2 in Cancers of the Gastrointestinal System: An Update
af: Gianluca Malagraba, et al.
Udgivet: (2022-03-01)

Return of the devil in the details: delving deep into convolutional nets
af: Chatfield, K, et al.
Udgivet: (2014)

Return of the devil in the details: delving deep into convolutional nets
af: Chatfield, K, et al.
Udgivet: (2014)

Small steps and giant leaps: minimal newton solvers for deep learning
af: Henriques, J, et al.
Udgivet: (2020)

New Aspects of LSD
af: Michael Beck
Udgivet: (2016-12-01)

Deep structured output learning for unconstrained text recognition
af: Jaderberg, M, et al.
Udgivet: (2015)

Deep structured output learning for unconstrained text recognition
af: Jaderberg, M, et al.
Udgivet: (2014)

There and back again: revisiting backpropagation saliency methods
af: Rebuffi, S-A, et al.
Udgivet: (2020)

Lsd1 and Lsd2 Control Programmed Replication Fork Pauses and Imprinting in Fission Yeast
af: Allyson Holmes, et al.
Udgivet: (2012-12-01)

Artificial hallucination: GPT on LSD?
af: Gernot Beutel, et al.
Udgivet: (2023-04-01)

Using deep LSD to build operators in GANs latent space with meaning in real space
af: J. Quetzalcóatl Toledo-Marín, et al.
Udgivet: (2023-01-01)

Using deep LSD to build operators in GANs latent space with meaning in real space.
af: J Quetzalcóatl Toledo-Marín, et al.
Udgivet: (2023-01-01)

AutoCorrect: Deep inductive alignment of noisy geometric annotations
af: Chen, H, et al.
Udgivet: (2020)

Influence of the input data on learning deep representations
af: Sylvestre-Alvise Rebuffi
Udgivet: (2020)

Dynamic Skyline Computation with LSD Trees
af: Dominik Köppl
Udgivet: (2023-02-01)

The lasting influence of LSD1 in the blood
af: Sharon YR Dent, et al.
Udgivet: (2013-06-01)

LSD: a Line Segment Detector
af: Rafael Grompone von Gioi, et al.
Udgivet: (2012-03-01)

TERRA-LSD1 phase separation promotes R-loop formation for telomere maintenance in ALT cancer cells
af: Meng Xu, et al.
Udgivet: (2024-03-01)

SYNTHESIS, LSD1 INHIBITORY ACTIVITY, AND LSD1 BINDING MODEL OF OPTICALLY PURE LYSINE-PCPA CONJUGATES
af: Yukihiro Itoh, et al.
Udgivet: (2014-02-01)

LSD1 protects against hippocampal and cortical neurodegeneration
af: Michael A. Christopher, et al.
Udgivet: (2017-10-01)

LSD alters dynamic integration and segregation in the human brain
af: Andrea I. Luppi, et al.
Udgivet: (2021-02-01)

The Catalytic-Dependent and -Independent Roles of Lsd1 and Lsd2 Lysine Demethylases in Heterochromatin Formation in <i>Schizosaccharomyces pombe</i>
af: Bahjat F. Marayati, et al.
Udgivet: (2020-04-01)

Open-set recognition: a good closed-set classifier is all you need?
af: Vaze, S, et al.
Udgivet: (2021)

Generalized category discovery
af: Vaze, S, et al.
Udgivet: (2022)

Salicylate-Independent Lesion Formation in Arabidopsis lsd Mutants
af: Michelle D. Hunt, et al.
Udgivet: (1997-07-01)

Structured output regression for detection with partial truncation
af: Vedaldi, A, et al.
Udgivet: (2009)

Efficient additive kernels via explicit feature maps
af: Vedaldi, A, et al.
Udgivet: (2012)

Sparse kernel approximations for efficient classification and detection
af: Vedaldi, A, et al.
Udgivet: (2012)

Self-similar sketch
af: Vedaldi, A, et al.
Udgivet: (2012)

Taking LSD 1 to a new high.
af: Wysocka, J, et al.
Udgivet: (2005)