Related papers: Local Scale Equivariance with Latent Deep Equilibr…

Unsupervised contrastive learning achieves great success in learning image representations with CNN. Unlike most recent methods that focused on improving accuracy of image classification, we present a novel contrastive learning approach,…

Predictive maintenance is an important sector in modern industries which improves fault detection and cost reduction processes. By using machine learning algorithms in the whole process, the defects detection process can be implemented…

Scale variation across object instances remains a key challenge in object detection task. Despite the remarkable progress made by modern detection models, this challenge is particularly evident in the semi-supervised case. While existing…

Image denoising is a classical problem in low level computer vision. Model-based optimization methods and deep learning approaches have been the two main strategies for solving the problem. Model-based optimization methods are flexible for…

Recent progress of deep image classification models has provided great potential to improve state-of-the-art performance in related computer vision tasks. However, the transition to semantic segmentation is hampered by strict memory…

Semantic labeling (or pixel-level land-cover classification) in ultra-high resolution imagery (< 10cm) requires statistical models able to learn high level concepts from spatial data, with large appearance variations. Convolutional Neural…

Scale variation is one of the key challenges in object detection. In this work, we first present a controlled experiment to investigate the effect of receptive fields for scale variation in object detection. Based on the findings from the…

Visual saliency is a fundamental problem in both cognitive and computational sciences, including computer vision. In this paper, we discover that a high-quality visual saliency model can be learned from multiscale features extracted using…

Understanding how cities visually differ from each others is interesting for planners, residents, and historians. We investigate the interpretation of deep features learned by convolutional neural networks (CNNs) for city recognition. Given…

Despite the successes of deep learning in computer vision, difficulties persist in recognizing objects that have undergone group-symmetric transformations rarely seen during training$\unicode{x2013}$for example objects seen in unusual…

Salient object detection increasingly receives attention as an important component or step in several pattern recognition and image processing tasks. Although a variety of powerful saliency models have been intensively proposed, they…

Vision Transformers (ViTs) can learn strong image-level representations while their patch representations become less effective for dense prediction during prolonged training. We revisit this dense degradation phenomenon and argue that it…

Class-agnostic counting (CAC) aims to count objects of interest from a query image given few exemplars. This task is typically addressed by extracting the features of query image and exemplars respectively and then matching their feature…

Real-world face detection and alignment demand an advanced discriminative model to address challenges by pose, lighting and expression. Illuminated by the deep learning algorithm, some convolutional neural networks based face detection and…

Canonical Correlation Analysis (CCA) is a method for feature extraction of two views by finding maximally correlated linear projections of them. Several variants of CCA have been introduced in the literature, in particular, variants based…

Image-level weakly supervised semantic segmentation is a challenging problem that has been deeply studied in recent years. Most of advanced solutions exploit class activation map (CAM). However, CAMs can hardly serve as the object mask due…

To date, most existing self-supervised learning methods are designed and optimized for image classification. These pre-trained models can be sub-optimal for dense prediction tasks due to the discrepancy between image-level prediction and…

When it comes to image compression in digital cameras, denoising is traditionally performed prior to compression. However, there are applications where image noise may be necessary to demonstrate the trustworthiness of the image, such as…

We consider a variant of online convex optimization in which both the instances (input vectors) and the comparator (weight vector) are unconstrained. We exploit a natural scale invariance symmetry in our unconstrained setting: the…

Dense correspondence across semantically related images has been extensively studied, but still faces two challenges: 1) large variations in appearance, scale and pose exist even for objects from the same category, and 2) labeling…