Related papers: Pattern Integration and Enhancement Vision Transfo…
Image retrieval systems help users to browse and search among extensive images in real-time. With the rise of cloud computing, retrieval tasks are usually outsourced to cloud servers. However, the cloud scenario brings a daunting challenge…
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…
Vision Transformers can achieve high accuracy and strong generalization across various contexts, but their practical applicability on real-world robotic systems is limited due to their quadratic attention complexity. Recent works have…
Learning visual representations through self-supervision is an extremely challenging task as the network needs to sieve relevant patterns from spurious distractors without the active guidance provided by supervision. This is achieved…
Semi-supervised video object segmentation is a task of segmenting the target object in a video sequence given only a mask annotation in the first frame. The limited information available makes it an extremely challenging task. Most previous…
We investigate the generalization of semi-supervised learning (SSL) to diverse pixel-wise tasks. Although SSL methods have achieved impressive results in image classification, the performances of applying them to pixel-wise tasks are…
This study aims to learn a translation from visible to infrared imagery, bridging the domain gap between the two modalities so as to improve accuracy on downstream tasks including object detection. Previous approaches attempt to perform…
Existing visual change detectors usually adopt CNNs or Transformers for feature representation learning and focus on learning effective representation for the changed regions between images. Although good performance can be obtained by…
Automatic pavement distress classification facilitates improving the efficiency of pavement maintenance and reducing the cost of labor and resources. A recently influential branch of this task divides the pavement image into patches and…
Multispectral imaging is an important task of image processing and computer vision, which is especially relevant to applications such as dehazing or object detection. With the development of the RGBT (RGB & Thermal) sensor, the problem of…
Visible-Infrared Person Re-Identification (VI-ReID) is a challenging retrieval task under complex modality changes. Existing methods usually focus on extracting discriminative visual features while ignoring the reliability and commonality…
Satellites continuously generate massive volumes of data, particularly for Earth observation, including satellite image time series (SITS). However, most deep learning models are designed to process either entire images or complete time…
Self-supervised learning (SSL) has recently achieved tremendous empirical advancements in learning image representation. However, our understanding of the principle behind learning such a representation is still limited. This work shows…
Current self-supervised learning (SSL) methods (e.g., SimCLR, DINO, VICReg,MOCOv3) target primarily on representations at instance level and do not generalize well to dense prediction tasks, such as object detection and segmentation.Towards…
Recent self-supervised models have demonstrated equal or better performance than supervised methods, opening for AI systems to learn visual representations from practically unlimited data. However, these methods are typically…
Videos are a rich source for self-supervised learning (SSL) of visual representations due to the presence of natural temporal transformations of objects. However, current methods typically randomly sample video clips for learning, which…
Self-supervised learning (SSL) has produced a diverse landscape of vision transformers (ViTs) whose pretrained representations support a wide range of downstream tasks. Towards a better understanding of these models, a body of work has…
We study semi-supervised learning (SSL) for vision transformers (ViT), an under-explored topic despite the wide adoption of the ViT architectures to different tasks. To tackle this problem, we propose a new SSL pipeline, consisting of first…
Remote sensing scene classification has been extensively studied for its critical roles in geological survey, oil exploration, traffic management, earthquake prediction, wildfire monitoring, and intelligence monitoring. In the past, the…
For 3D object detection, both camera and lidar have been demonstrated to be useful sensory devices for providing complementary information about the same scenery with data representations in different modalities, e.g., 2D RGB image vs 3D…