Related papers: Deep few-shot learning for bi-temporal building ch…

We tackle the problem of visual localization under changing conditions, such as time of day, weather, and seasons. Recent learned local features based on deep neural networks have shown superior performance over classical hand-crafted local…

In this work, we address the problem of few-shot multi-class object counting with point-level annotations. The proposed technique leverages a class agnostic attention mechanism that sequentially attends to objects in the image and extracts…

Conventional methods for object detection typically require a substantial amount of training data and preparing such high-quality training data is very labor-intensive. In this paper, we propose a novel few-shot object detection network…

We introduce SubGD, a novel few-shot learning method which is based on the recent finding that stochastic gradient descent updates tend to live in a low-dimensional parameter subspace. In experimental and theoretical analyses, we show that…

Recently, deep learning technology have been extensively used in the field of image recognition. However, its main application is the recognition and detection of ordinary pictures and common scenes. It is challenging to effectively and…

This paper presents a comparative study of near-duplicate image detection techniques in a real-world use case scenario, where a document management company is commissioned to manually annotate a collection of scanned photographs. Detecting…

This paper presents a novel method for rare event detection from an image pair with class-imbalanced datasets. A straightforward approach for event detection tasks is to train a detection network from a large-scale dataset in an end-to-end…

Despite its astounding success in learning deeper multi-dimensional data, the performance of deep learning declines on new unseen tasks mainly due to its focus on same-distribution prediction. Moreover, deep learning is notorious for poor…

Transfer learning based approaches have recently achieved promising results on the few-shot detection task. These approaches however suffer from ``catastrophic forgetting'' issue due to finetuning of base detector, leading to sub-optimal…

Visual change detection, aiming at segmentation of video frames into foreground and background regions, is one of the elementary tasks in computer vision and video analytics. The applications of change detection include anomaly detection,…

Training deep neural networks from few examples is a highly challenging and key problem for many computer vision tasks. In this context, we are targeting knowledge transfer from a set with abundant data to other sets with few available…

Change detection (CD) is an important yet challenging task in the Earth observation field for monitoring Earth surface dynamics. The advent of deep learning techniques has recently propelled automatic CD into a technological revolution.…

Humans are capable of learning new concepts from small numbers of examples. In contrast, supervised deep learning models usually lack the ability to extract reliable predictive rules from limited data scenarios when attempting to classify…

We present a novel, training-free approach to scene change detection. Our method leverages tracking models, which inherently perform change detection between consecutive frames of video by identifying common objects and detecting new or…

Deep neural networks are becoming increasingly powerful and large and always require more labelled data to be trained. However, since annotating data is time-consuming, it is now necessary to develop systems that show good performance while…

For change detection in remote sensing, constructing a training dataset for deep learning models is difficult due to the requirements of bi-temporal supervision. To overcome this issue, single-temporal supervision which treats change labels…

Remote sensing image semantic segmentation is an important problem for remote sensing image interpretation. Although remarkable progress has been achieved, existing deep neural network methods suffer from the reliance on massive training…

Most change detection methods assume that pre-change and post-change images are acquired by the same sensor. However, in many real-life scenarios, e.g., natural disaster, it is more practical to use the latest available images before and…

In recent years, building change detection methods have made great progress by introducing deep learning, but they still suffer from the problem of the extracted features not being discriminative enough, resulting in incomplete regions and…

Few-shot classification is a challenging problem as only very few training examples are given for each new task. One of the effective research lines to address this challenge focuses on learning deep representations driven by a similarity…