Unsupervised object discovery via self-organisation

Kinnunen, Teemu; Kämäräinen, Joni-Kristian; Lensu, Lasse; Kälviäinen, Heikki

doi:10.1016/j.patrec.2012.07.013

Cited by 11 publications

(12 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The extraction of visual perceptions consists of detecting and describing numerically the parts of the object present in the image. In this article, we follow the literature of Unsupervised Object Discovery (Weber et al, 2000;Tuytelaars et al, 2010;Kinnunen et al, 2012), and we use the Scale Invariant Feature Transform (SIFT) to detect Points of Interest (POIs) and describe each POI as a vector of 128 values (Lowe, 1999), called "POI descriptor". These POI descriptors are normalized by an L2 normalization.…”

Section: The Visual Sensory-perceptive Mappingmentioning

confidence: 99%

A neural network architecture for learning word–referent associations in multiple contexts

Bassani

Araújo

2019

Neural Networks

View full text Add to dashboard Cite

This article proposes a biologically inspired neurocomputational architecture which learns associations between words and referents in different contexts, considering evidence collected from the literature of Psycholinguistics and Neurolinguistics. The multi-layered architecture takes as input raw images of objects (referents) and streams of word's phonemes (labels), builds an adequate representation, recognizes the current context, and associates label with referents incrementally, by employing a Self-Organizing Map which creates new association nodes (prototypes) as required, adjusts the existing prototypes to better represent the input stimuli and removes prototypes that become obsolete/unused. The model takes into account the current context to retrieve the correct meaning of words with multiple meanings. Simulations show that the model can reach up to 78% of word-referent association accuracy in ambiguous situations and approximates well the learning rates of humans as reported by three different authors in five Cross-Situational Word Learning experiments, also displaying similar learning patterns in the different learning conditions.

show abstract

Section: The Visual Sensory-perceptive Mappingmentioning

confidence: 99%

A neural network architecture for learning word–referent associations in multiple contexts

Bassani

Araújo

2019

Neural Networks

View full text Add to dashboard Cite

show abstract

“…Recently, unsupervised attribute discovery has gained more attention owing to its superiority to saving the involvement of manpower. Methods for completely unsupervised visual object classification (no labels or bounding boxes) have been proposed [10,11,27], but due to their large accuracy gap to the state-of-the-art supervised methods [5,12,25] they have not received enough attention. Attributes may still be beneficial in certain cases, such as zeroshot learning [14], with only a small number of training images [2], fine-grained classification [9] or utilising scene attributes to improve detection [16,19].…”

Section: Related Workmentioning

confidence: 99%

Discovering Multi-relational Latent Attributes by Visual Similarity Networks

Yancheshmeh

Kämäräinen

Chen

2015

Computer Vision - ACCV 2014 Workshops

View full text Add to dashboard Cite

Abstract. The key problems in visual object classification are: learning discriminative feature to distinguish between two or more visually similar categories ( e.g. dogs and cats), modeling the variation of visual appearance within instances of the same class (e.g. Dalmatian and Chihuahua in the same category of dogs), and tolerate imaging distortion (3D pose). These account to within and between class variance in machine learning terminology, but in recent works these additional pieces of information, latent dependency, have been shown to be beneficial for the learning process. Latent attribute space was recently proposed and verified to capture the latent dependent correlation between classes. Attributes can be annotated manually, but more attempting is to extract them in an unsupervised manner. Clustering is one of the popular unsupervised approaches, and the recent literature introduces similarity measures that help to discover visual attributes by clustering. However, the latent attribute structure in real life is multi-relational, e.g. two different sport cars in different poses vs. a sport car and a family car in the same posewhat attribute can dominate similarity? Instead of clustering, a network (graph) containing multiple connections is a natural way to represent such multi-relational attributes between images. In the light of this, we introduce an unsupervised framework for network construction based on pairwise visual similarities and experimentally demonstrate that the constructed network can be used to automatically discover multiple discrete (e.g. sub-classes) and continuous (pose change) latent attributes. Illustrative examples with publicly benchmarking datasets can verify the effectiveness of capturing multi-relation between images in the unsupervised style by our proposed network.

show abstract

“…It is important to observe who knows the ground truth, and why and how. To facilitate these steps in general, a lot of research methods exist: randomized hough transform (RHT) for geometric primitives detection [4][5][6][7][8][9][10][11][12][13], Gabor filtering for object detection [14][15][16][17][18], Gaussian mixture models for object classification [19,20], SOMand PCA-based image compression and representation of spectral images [21][22][23], surface analysis for 2D and 3D images [24][25][26], unsupervised methods for visual object categorization (VOC) [27][28][29][30][31], tracking methods for computer vision [32][33][34] It must be considered whether there are challenges to be expected in imaging and whether multimodal information is needed.…”

Section: From Human Vision To Machine Visionmentioning

confidence: 99%

“…An unsupervised VOC (UVOC) approach [27,29] is Connecting physical measurements and subjective quality attributes. Different areas, that is, objects, are considered to affect the quality differently.…”

Section: Image Quality Assessment and Visual Object Categorizationmentioning

confidence: 99%