MaskSplit: Self-supervised Meta-learning for Few-shot Semantic Segmentation

Amac, Mustafa Sercan
Sencan, Ahmet
Baran, Orhun Buğra
Ikizler-Cinbis, Nazli
Cinbiş, Ramazan Gökberk
Just like other few-shot learning problems, few-shot segmentation aims to minimize the need for manual annotation, which is particularly costly in segmentation tasks. Even though the few-shot setting reduces this cost for novel test classes, there is still a need to annotate the training data. To alleviate this need, we propose a self-supervised training approach for learning few-shot segmentation models. We first use unsupervised saliency estimation to obtain pseudo-masks on images. We then train a simple prototype based model over different splits of pseudo masks and augmentations of images. Our extensive experiments show that the proposed approach achieves promising results, highlighting the potential of self-supervised training. To the best of our knowledge this is the first work that addresses unsupervised few-shot segmentation problem on natural images.
22nd IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2022


Feature Dimensionality Reduction with Variational Autoencoders in Deep Bayesian Active Learning
Ertekin Bolelli, Şeyda (2021-06-09)
Data annotation for training of supervised learning algorithms has been a very costly procedure. The aim of deep active learning methodologies is to acquire the highest performance in supervised deep learning models by annotating as few data points as possible. As the feature space of data grows, the application of linear models in active learning settings has become insufficient. Therefore, Deep Bayesian Active Learning methodology which represents model uncertainty has been widely studied. In this paper, ...
Competing labels: a heuristic approach to pseudo-labeling in deep semi-supervised learning
Bayrak, Hamdi Burak; Ertekin Bolelli, Şeyda; Yücel, Hamdullah; Department of Scientific Computing (2022-2-10)
Semi-supervised learning is one of the dominantly utilized approaches to reduce the reliance of deep learning models on large-scale labeled data. One mostly used method of this approach is pseudo-labeling. However, pseudo-labeling, especially its originally proposed form tends to remarkably suffer from noisy training when the assigned labels are false. In order to mitigate this problem, in our work, we investigate the gradient sent to the neural network and propose a heuristic method, called competing label...
Time memory trade off attack on symmetric ciphers
Saran, A. Nurdan; Doğanaksoy, Ali; Department of Cryptography (2009)
Time Memory Trade O (TMTO) is a cryptanalytic method that aims to develop an attack which has a lower memory complexity than lookup table and a lower online time complexity than exhaustive search. TMTO methods are widely studied in the literature and used for inverting various cryptosystems. We focus on the design and the analysis of TMTO on symmetric ciphers in this thesis. Firstly, the summary of the random mapping statistics from the view point of TMTO is presented. We also recalculate some expected valu...
Learning semi-supervised nonlinear embeddings for domain-adaptive pattern recognition
Vural, Elif (null; 2019-05-20)
We study the problem of learning nonlinear data embeddings in order to obtain representations for efficient and domain-invariant recognition of visual patterns. Given observations of a training set of patterns from different classes in two different domains, we propose a method to learn a nonlinear mapping of the data samples from different domains into a common domain. The nonlinear mapping is learnt such that the class means of different domains are mapped to nearby points in the common domain in order to...
Semi-supervised generative guidance for zero-shot semantic segmentation
Önem, Abdullah Cem; Cinbiş, Ramazan Gökberk; Department of Computer Engineering (2022-1)
Collecting fully-annotated data to train deep networks for semantic image segmentation can be prohibitively costly due to difficulty of making pixel-by-pixel annotations. In this context, zero-shot learning based formulations relax the labelled data requirements by enabling the recognition of classes without training examples. Recent studies on zero-shot learning of semantic segmentation models, however, highlight the difficulty of the problem. This thesis proposes techniques towards improving zero-shot gen...
Citation Formats
M. S. Amac, A. Sencan, O. B. Baran, N. Ikizler-Cinbis, and R. G. Cinbiş, “MaskSplit: Self-supervised Meta-learning for Few-shot Semantic Segmentation,” presented at the 22nd IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2022, Hawaii, Amerika Birleşik Devletleri, 2022, Accessed: 00, 2022. [Online]. Available: