相关论文: Learning to Measure Change: Fully Convolutional Si…

In this paper, we propose a new measure to gauge the complexity of image classification problems. Given an annotated image dataset, our method computes a complexity measure called the cumulative spectral gradient (CSG) which strongly…

Change detection, which aims to distinguish surface changes based on bi-temporal images, plays a vital role in ecological protection and urban planning. Since high resolution (HR) images cannot be typically acquired continuously over time,…

Self-supervised learning holds promise in leveraging large numbers of unlabeled data. However, its success heavily relies on the highly-curated dataset, e.g., ImageNet, which still needs human cleaning. Directly learning representations…

We propose a novel clustering approach for point-cloud segmentation based on supervised contrastive metric learning (CML). Rather than predicting cluster assignments or object-centric variables, the method learns a latent representation in…

We present a model that automatically divides broadcast videos into coherent scenes by learning a distance measure between shots. Experiments are performed to demonstrate the effectiveness of our approach by comparing our algorithm against…

Graph Contrastive Learning (GCL) leverages data augmentation techniques to produce contrasting views, enhancing the accuracy of recommendation systems through learning the consistency between contrastive views. However, existing…

The scalability and complexity of deep learning models remains a key issue in many of visual recognition applications like, e.g., video surveillance, where fine tuning with labeled image data from each new camera is required to reduce the…

Inspired by the remarkable zero-shot generalization capacity of vision-language pre-trained model, we seek to leverage the supervision from CLIP model to alleviate the burden of data labeling. However, such supervision inevitably contains…

Deep learning has made many remarkable achievements in many fields but suffers from noisy labels in datasets. The state-of-the-art learning with noisy label method Co-teaching and Co-teaching+ confronts the noisy label by mutual-information…

This paper introduces a novel synthetic dataset that captures urban scenes under a variety of weather conditions, providing pixel-perfect, ground-truth-aligned images to facilitate effective feature alignment across domains. Additionally,…

The accurate diagnosis of pathological subtypes of lung cancer is of paramount importance for follow-up treatments and prognosis managements. Assessment methods utilizing deep learning technologies have introduced novel approaches for…

Recently, convolutional neural network (CNN) has attracted much attention in different areas of computer vision, due to its powerful abstract feature representation. Visual object tracking is one of the interesting and important areas in…

Weakly supervised person search aims to perform joint pedestrian detection and re-identification (re-id) with only person bounding-box annotations. Recently, the idea of contrastive learning is initially applied to weakly supervised person…

Scene change detection is an image processing problem related to partitioning pixels of a digital image into foreground and background regions. Mostly, visual knowledge-based computer intelligent systems, like traffic monitoring, video…

Numerous researches have proved that deep neural networks (DNNs) can fit everything in the end even given data with noisy labels, and result in poor generalization performance. However, recent studies suggest that DNNs tend to gradually…

Detecting lane markings in road scenes poses a challenge due to their intricate nature, which is susceptible to unfavorable conditions. While lane markings have strong shape priors, their visibility is easily compromised by lighting…

In the remote sensing field, Change Detection (CD) aims to identify and localize the changed regions from dual-phase images over the same places. Recently, it has achieved great progress with the advances of deep learning. However, current…

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 many machine learning problems, large-scale datasets have become the de-facto standard to train state-of-the-art deep networks at the price of heavy computation load. In this paper, we focus on condensing large training sets into…

Learnable keypoint detectors and descriptors are beginning to outperform classical hand-crafted feature extraction methods. Recent studies on self-supervised learning of visual representations have driven the increasing performance of…