Related papers: Self-Pair: Synthesizing Changes from Single Source…
We tackle the problem of learning object detectors without supervision. Differently from weakly-supervised object detection, we do not assume image-level class labels. Instead, we extract a supervisory signal from audio-visual data, using…
In this paper, we aim to tackle the one-shot person re-identification problem where only one image is labelled for each person, while other images are unlabelled. This task is challenging due to the lack of sufficient labelled training…
Longitudinal imaging forms an essential component in the management and follow-up of many medical conditions. The presence of lesion changes on serial imaging can have significant impact on clinical decision making, highlighting the…
Change detection, as an important and widely applied technique in the field of remote sensing, aims to analyze changes in surface areas over time and has broad applications in areas such as environmental monitoring, urban development, and…
The recently advanced unsupervised learning approaches use the siamese-like framework to compare two "views" from the same image for learning representations. Making the two views distinctive is a core to guarantee that unsupervised methods…
Unsupervised domain adaptation in person re-identification resorts to labeled source data to promote the model training on target domain, facing the dilemmas caused by large domain shift and large camera variations. The non-overlapping…
Artificial intelligence generative content (AIGC) has significantly impacted image generation in the field of remote sensing. However, the equally important area of remote sensing image (RSI) editing has not received sufficient attention.…
Change detection plays an important role in most video-based applications. The first stage is to build appropriate background model, which is now becoming increasingly complex as more sophisticated statistical approaches are introduced to…
Employing clustering strategy to assign unlabeled target images with pseudo labels has become a trend for person re-identification (re-ID) algorithms in domain adaptation. A potential limitation of these clustering-based methods is that…
Applying an object detector, which is neither trained nor fine-tuned on data close to the final application, often leads to a substantial performance drop. In order to overcome this problem, it is necessary to consider a shift between…
For autonomous vehicles, driving safely is highly dependent on the capability to correctly perceive the environment in 3D space, hence the task of 3D object detection represents a fundamental aspect of perception. While 3D sensors deliver…
A principal barrier to training temporal relation extraction models in new domains is the lack of varied, high quality examples and the challenge of collecting more. We present a method of automatically collecting distantly-supervised…
Change detection for remote sensing images is widely applied for urban change detection, disaster assessment and other fields. However, most of the existing CNN-based change detection methods still suffer from the problem of inadequate…
The automatic detection of changes or anomalies between multispectral and hyperspectral images collected at different time instants is an active and challenging research topic. To effectively perform change-point detection in multitemporal…
Remote sensing scene classification aims to assign a specific semantic label to a remote sensing image. Recently, convolutional neural networks have greatly improved the performance of remote sensing scene classification. However, some…
In this paper, we propose a basic RGB single-mode model based on weakly supervised training under pseudo labels, which performs high-precision authenticity identification under multi-scene typical target remote sensing images. Due to the…
Self-supervised video correspondence learning depends on the ability to accurately associate pixels between video frames that correspond to the same visual object. However, achieving reliable pixel matching without supervision remains a…
Despite the promising progress made in recent years, person re-identification (re-ID) remains a challenging task due to the complex variations in human appearances from different camera views. For this challenging problem, a large variety…
With recent advancements in aerospace technology, the volume of unlabeled remote sensing image (RSI) data has increased dramatically. Effectively leveraging this data through self-supervised learning (SSL) is vital in the field of remote…
In this paper, we propose Test-Time Training, a general approach for improving the performance of predictive models when training and test data come from different distributions. We turn a single unlabeled test sample into a self-supervised…