Related papers: Unsupervised learning based object detection using…

Online tracking of multiple objects in videos requires strong capacity of modeling and matching object appearances. Previous methods for learning appearance embedding mostly rely on instance-level matching without considering the temporal…

Deep learning techniques have achieved great success in remote sensing image change detection. Most of them are supervised techniques, which usually require large amounts of training data and are limited to a particular application.…

Learning discriminative representations of unlabelled data is a challenging task. Contrastive self-supervised learning provides a framework to learn meaningful representations using learned notions of similarity measures from simple pretext…

Despite their irresistible success, deep learning algorithms still heavily rely on annotated data. On the other hand, unsupervised settings pose many challenges, especially about determining the right inductive bias in diverse scenarios.…

As the digital landscape becomes more interconnected, the frequency and severity of zero-day attacks, have significantly increased, leading to an urgent need for innovative Intrusion Detection Systems (IDS). Machine Learning-based IDS that…

The recent rise of unsupervised and self-supervised learning has dramatically reduced the dependency on labeled data, providing effective image representations for transfer to downstream vision tasks. Furthermore, recent works employed…

Supervised learning for semantic segmentation requires a large number of labeled samples, which is difficult to obtain in the field of remote sensing. Self-supervised learning (SSL), can be used to solve such problems by pre-training a…

In this paper, we focus on semi-supervised object detection to boost performance of proposal-based object detectors (a.k.a. two-stage object detectors) by training on both labeled and unlabeled data. However, it is non-trivial to train…

Learning to recognize actions from only a handful of labeled videos is a challenging problem due to the scarcity of tediously collected activity labels. We approach this problem by learning a two-pathway temporal contrastive model using…

Learning representations of images that are invariant to sensitive or unwanted attributes is important for many tasks including bias removal and cross domain retrieval. Here, our objective is to learn representations that are invariant to…

Prior research on self-supervised learning has led to considerable progress on image classification, but often with degraded transfer performance on object detection. The objective of this paper is to advance self-supervised pretrained…

Representation learning approaches typically rely on images of objects captured from a single perspective that are transformed using affine transformations. Additionally, self-supervised learning, a successful paradigm of representation…

We propose an adversarial contextual model for detecting moving objects in images. A deep neural network is trained to predict the optical flow in a region using information from everywhere else but that region (context), while another…

Localizing objects in image collections without supervision can help to avoid expensive annotation campaigns. We propose a simple approach to this problem, that leverages the activation features of a vision transformer pre-trained in a…

A key requirement for the success of supervised deep learning is a large labeled dataset - a condition that is difficult to meet in medical image analysis. Self-supervised learning (SSL) can help in this regard by providing a strategy to…

This paper presents a self-supervised feature learning method for hyperspectral image classification. Our method tries to construct two different views of the raw hyperspectral image through a cross-representation learning method. And then…

The need to count and localize repeating objects in an image arises in different scenarios, such as biological microscopy studies, production lines inspection, and surveillance recordings analysis. The use of supervised Convoutional Neural…

Contrastive self-supervised learning has outperformed supervised pretraining on many downstream tasks like segmentation and object detection. However, current methods are still primarily applied to curated datasets like ImageNet. In this…

Supervised (pre-)training currently yields state-of-the-art performance for representation learning for visual recognition, yet it comes at the cost of (1) intensive manual annotations and (2) an inherent restriction in the scope of data…

Deep learning has emerged as an effective solution for solving the task of object detection in images but at the cost of requiring large labeled datasets. To mitigate this cost, semi-supervised object detection methods, which consist in…