Related papers: Parameter-Inverted Image Pyramid Networks

Although scaling laws and many empirical results suggest that increasing the size of Vision Transformers often improves performance, model accuracy and training behavior are not always monotonically increasing with scale. Focusing on…

Feature representations, both hand-designed and learned ones, are often hard to analyze and interpret, even when they are extracted from visual data. We propose a new approach to study image representations by inverting them with an…

Visual inspection is predominantly used to evaluate the state of civil structures, but recent developments in unmanned aerial vehicles (UAVs) and artificial intelligence have increased the speed, safety, and reliability of the inspection…

Multi-task scene understanding aims to design models that can simultaneously predict several scene understanding tasks with one versatile model. Previous studies typically process multi-task features in a more local way, and thus cannot…

Reconstructing the shape and spatially varying surface appearances of a physical-world object as well as its surrounding illumination based on 2D images (e.g., photographs) of the object has been a long-standing problem in computer vision…

Topological features such as persistence diagrams and their functional approximations like persistence images (PIs) have been showing substantial promise for machine learning and computer vision applications. This is greatly attributed to…

Humans are capable of building holistic representations for images at various levels, from local objects, to pairwise relations, to global structures. The interpretation of structures involves reasoning over repetition and symmetry of the…

Feature interactions across space and scales underpin modern visual recognition systems because they introduce beneficial visual contexts. Conventionally, spatial contexts are passively hidden in the CNN's increasing receptive fields or…

Graph neural networks have emerged as a promising paradigm for image processing, yet their performance in image classification tasks is hindered by a limited consideration of the underlying structure and relationships among visual entities.…

Natural image quality is often degraded by adverse weather conditions, significantly impairing the performance of downstream tasks. Image restoration has emerged as a core solution to this challenge and has been widely discussed in the…

Feature pyramid networks (FPN) are widely exploited for multi-scale feature fusion in existing advanced object detection frameworks. Numerous previous works have developed various structures for bidirectional feature fusion, all of which…

This paper introduces an effective processing framework nominated ICP (Image Cloud Processing) to powerfully cope with the data explosion in image processing field. While most previous researches focus on optimizing the image processing…

Deep metric learning for vision is trained by optimizing a representation network to map (non-)matching image pairs to (non-)similar representations. During testing, which typically corresponds to image retrieval, both database and query…

Existing image-to-image translation (I2IT) methods are either constrained to low-resolution images or long inference time due to their heavy computational burden on the convolution of high-resolution feature maps. In this paper, we focus on…

Image processing is a fundamental task in computer vision, which aims at enhancing image quality and extracting essential features for subsequent vision applications. Traditionally, task-specific models are developed for individual tasks…

Feature pyramid network (FPN) is a critical component in modern object detection frameworks. The performance gain in most of the existing FPN variants is mainly attributed to the increase of computational burden. An attempt to enhance the…

Object detection is a challenging task in remote sensing because objects only occupy a few pixels in the images, and the models are required to simultaneously learn object locations and detection. Even though the established approaches well…

Convolutional networks are at the core of most state-of-the-art computer vision solutions for a wide variety of tasks. Since 2014 very deep convolutional networks started to become mainstream, yielding substantial gains in various…

Although image restoration has advanced significantly, most existing methods target only a single type of degradation. In real-world scenarios, images often contain multiple degradations simultaneously, such as rain, noise, and haze,…

High-resolution depth map can be inferred from a low-resolution one with the guidance of an additional high-resolution texture map of the same scene. Recently, deep neural networks with large receptive fields are shown to benefit…