A Recurrent and Meta-learned Model of Weakly Supervised Object Localization

Date

2022-01-01

Author

Sariyildiz, Mert Bulent
Sumbul, Gencer
Cinbiş, Ramazan Gökberk

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

75
views

0
downloads

The object localization and detection has improved greatly over the past decade, thanks to developments in deep learning based representations and localization models. However, a major bottleneck remains at the reliance on fully-supervised datasets, which can be difficult to gather in many real-world scenarios. In this work, we focus on the problem of weakly-supervised localization, where the goal is to localize instances of objects based on simple image-level class annotations. In particular, instead of engineering a specific weakly-supervised localization model, we aim to meta-learn a recurrent neural network based model that aims to take series of training images of a novel class, and progressively discover the foreground pattern over them. We experimentally explore the model over scenes composed of MNIST digits and noisy patches as distractors.

Subject Keywords

meta learning, recurrent neural networks, Weakly supervised object localization

URI

https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85142794359&origin=inward
https://hdl.handle.net/11511/101546

DOI

https://doi.org/10.1109/ismsit56059.2022.9932735

Conference Name

6th International Symposium on Multidisciplinary Studies and Innovative Technologies, ISMSIT 2022

Collections

Department of Computer Engineering, Conference / Seminar

Suggestions

OpenMETU
Core

Closed-form sample probing for training generative models in zero-shot learning Çetin, Samet; Cinbiş, Ramazan Gökberk; Department of Computer Engineering (2022-2-10) Generative modeling based approaches have led to significant advances in generalized zero-shot learning over the past few-years. These approaches typically aim to learn a conditional generator that synthesizes training samples of classes conditioned on class embeddings, such as attribute based class definitions. The final zero-shot learning model can then be obtained by training a supervised classification model over the real and/or synthesized training samples of seen and unseen classes, combined. Therefor...
An Approach to manage variability in object-oriented applications with feature models Bulut, Ender; Şener, Cevat; Department of Computer Engineering (2014) In this thesis, an approach to manage variability in object-oriented applications by using a feature modeling language and a simple source code generation technique has been designed and developed. This approach provides developing configurable object oriented applications in a practical way. That is, an application developed with our approach takes just a configuration file including user selections in a pre-defined domain as input and then automatically configure and manage itself with respect to these se...
A method for quadruplet sample selection in deep feature learning Derin Öznitelik Öǧrenme için Dördüz Örnek Seçme Yöntemi Karaman, Kaan; Gundogdu, Erhan; Koc, Aykut; Alatan, Abdullah Aydın (2018-07-05) Recently, the deep learning based feature learning methodologies have been developed to recognize the objects in fine-grained detail. In order to increase the discriminativeness and robustness of the utilized features, this paper proposes a sample selection methodology for the quadruplet based feature learning. The feature space is manipulated by using the hierarchical structure of the training set. In the training process, the quadruplets are selected by considering the distances between the samples in the...
Weakly Supervised Object Localization with Multi-Fold Multiple Instance Learning Cinbiş, Ramazan Gökberk; Schmid, Cordelia (2017-01-01) Object category localization is a challenging problem in computer vision. Standard supervised training requires bounding box annotations of object instances. This time-consuming annotation process is sidestepped in weakly supervised learning. In this case, the supervised information is restricted to binary labels that indicate the absence/presence of object instances in the image, without their locations. We follow a multiple-instance learning approach that iteratively trains the detector and infers the obj...
A new approach to mathematical water quality modeling in reservoirs: Neural networks Karul, C; Soyupak, S; Germen, E (1998-01-01) Neural Networks are becoming more and more valuable tools for system modeling and function approximation as computing power of microcomputers increase. Modeling of complex ecological systems such as reservoir limnology is very difficult since the ecological interactions within a reservoir are difficult to define mathematically and are usually system specific. To illustrate the potential use of Neural Networks in ecological modeling, a software was developed to train the data from Keban Dam Reservoir by back...

Citation Formats

M. B. Sariyildiz, G. Sumbul, and R. G. Cinbiş, “A Recurrent and Meta-learned Model of Weakly Supervised Object Localization,” presented at the 6th International Symposium on Multidisciplinary Studies and Innovative Technologies, ISMSIT 2022, Ankara, Türkiye, 2022, Accessed: 00, 2023. [Online]. Available: https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85142794359&origin=inward.