Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userDeep Unsupervised Similarity Learning using Partially Ordered Sets
92
0
0.0
(
0
)
Added by
Artsiom Sanakoyeu
Publication date
2017
fields
Informatics Engineering
and research's language is
English
Ask ChatGPT about the research
No Arabic abstract
Unsupervised learning of visual similarities is of paramount importance to computer vision, particularly due to lacking training data for fine-grained similarities. Deep learning of similarities is often based on relationships between pairs or triplets of samples. Many of these relations are unreliable and mutually contradicting, implying inconsistencies when trained without supervision information that relates different tuples or triplets to each other. To overcome this problem, we use local estimates of reliable (dis-)similarities to initially group samples into compact surrogate classes and use local partial orders of samples to classes to link classes to each other. Similarity learning is then formulated as a partial ordering task with soft correspondences of all samples to classes. Adopting a strategy of self-supervision, a CNN is trained to optimally represent samples in a mutually consistent manner while updating the classes. The similarity learning and grouping procedure are integrated in a single model and optimized jointly. The proposed unsupervised approach shows competitive performance on detailed pose estimation and object classification.
rate research
Read More
For a (finite) partially ordered set (poset) $P$, we call a dominating set $D$ in the comparability graph of $P$, an order-sensitive dominating set in $P$ if either $xin D$ or else $a<x<b$ in $P$ for some $a,bin D$ for every element $x$ in $P$ which is neither maximal nor minimal, and denote by $gamma_{os}(P)$, the least size of an order-sensitive dominating set of $P$. For every graph $G$ and integer $kgeq 2$, we associate a graded poset $mathscr{P}_k(G)$ of height $k$, and prove that $gamma_{os}(mathscr{P}_3(G))=gamma_{text{R}}(G)$ and $gamma_{os}(mathscr{P}_4(G))=2gamma(G)$ hold, where $gamma(G)$ and $gamma_{text{R}}(G)$ are the domination and Roman domination number of $G$, respectively. Apart from these, we introduce the notion of a Helly poset, and prove that when $P$ is a Helly poset, the computation of order-sensitive domination number of $P$ can be interpreted as a weighted clique partition number of a graph, the middle graph of $P$. Moreover, we show that the order-sensitive domination number of a poset $P$ exactly corresponds to the biclique vertex-partition number of the associated bipartite transformation of $P$. Finally, we prove that the decision problem of order-sensitive domination on posets of arbitrary height is NP-complete, which is obtained by using a reduction from EQUAL-$3$-SAT problem.
The closed cone of flag vectors of Eulerian partially ordered sets is studied. It is completely determined up through rank seven. Half-Eulerian posets are defined. Certain limit posets of Billera and Hetyei are half-Eulerian; they give rise to extreme rays of the cone for Eulerian posets. A new family of linear inequalities valid for flag vectors of Eulerian posets is given.
In this paper, we propose an instance similarity learning (ISL) method for unsupervised feature representation. Conventional methods assign close instance pairs in the feature space with high similarity, which usually leads to wrong pairwise relationship for large neighborhoods because the Euclidean distance fails to depict the true semantic similarity on the feature manifold. On the contrary, our method mines the feature manifold in an unsupervised manner, through which the semantic similarity among instances is learned in order to obtain discriminative representations. Specifically, we employ the Generative Adversarial Networks (GAN) to mine the underlying feature manifold, where the generated features are applied as the proxies to progressively explore the feature manifold so that the semantic similarity among instances is acquired as reliable pseudo supervision. Extensive experiments on image classification demonstrate the superiority of our method compared with the state-of-the-art methods. The code is available at https://github.com/ZiweiWangTHU/ISL.git.
Exemplar learning of visual similarities in an unsupervised manner is a problem of paramount importance to Computer Vision. In this context, however, the recent breakthrough in deep learning could not yet unfold its full potential. With only a single positive sample, a great imbalance between one positive and many negatives, and unreliable relationships between most samples, training of Convolutional Neural networks is impaired. In this paper we use weak estimates of local similarities and propose a single optimization problem to extract batches of samples with mutually consistent relations. Conflicting relations are distributed over different batches and similar samples are grouped into compact groups. Learning visual similarities is then framed as a sequence of categorization tasks. The CNN then consolidates transitivity relations within and between groups and learns a single representation for all samples without the need for labels. The proposed unsupervised approach has shown competitive performance on detailed posture analysis and object classification.
In this report, we present an unsupervised machine learning method for determining groups of molecular systems according to similarity in their dynamics or structures using Wards minimum variance objective function. We first apply the minimum variance clustering to a set of simulated tripeptides using the information theoretic Jensen-Shannon divergence between Markovian transition matrices in order to gain insight into how point mutations affect protein dynamics. Then, we extend the method to partition two chemoinformatic datasets according to structural similarity to motivate a train/validation/test split for supervised learning that avoids overfitting.
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
