Related papers: Modeling Image Composition for Complex Scene Gener…
Many image understanding tasks involve identifying what is present and where it appears. However, tasks that address where, such as object discovery, detection, and segmentation, are often considerably more complex than image…
There has been exciting progress in generating images from natural language or layout conditions. However, these methods struggle to faithfully reproduce complex scenes due to the insufficient modeling of multiple objects and their…
In image fusion, images obtained from different sensors are fused to generate a single image with enhanced information. In recent years, state-of-the-art methods have adopted Convolution Neural Networks (CNNs) to encode meaningful features…
This paper addresses the problem of novel view synthesis by means of neural rendering, where we are interested in predicting the novel view at an arbitrary camera pose based on a given set of input images from other viewpoints. Using the…
Deformable image registration establishes non-linear spatial correspondences between fixed and moving images. Deep learning-based deformable registration methods have been widely studied in recent years due to their speed advantage over…
Transformers have been extensively studied in medical image segmentation to build pairwise long-range dependence. Yet, relatively limited well-annotated medical image data makes transformers struggle to extract diverse global features,…
Denosing diffusion model, as a generative model, has received a lot of attention in the field of image generation recently, thanks to its powerful generation capability. However, diffusion models have not yet received sufficient research in…
Few-shot object detection is a challenging but realistic scenario, where only a few annotated training images are available for training detectors. A popular approach to handle this problem is transfer learning, i.e., fine-tuning a detector…
We introduce FewGAN, a generative model for generating novel, high-quality and diverse images whose patch distribution lies in the joint patch distribution of a small number of N>1 training samples. The method is, in essence, a hierarchical…
Recently, Vision Transformer and its variants have shown great promise on various computer vision tasks. The ability of capturing short- and long-range visual dependencies through self-attention is arguably the main source for the success.…
Layout-to-image synthesis is an emerging technique in conditional image generation. It aims to generate complex scenes, where users require fine control over the layout of the objects in a scene. However, it remains challenging to control…
Inferring objects and their relationships from an image in the form of a scene graph is useful in many applications at the intersection of vision and language. We consider a challenging problem of compositional generalization that emerges…
Transformer has been popular in recent crowd counting work since it breaks the limited receptive field of traditional CNNs. However, since crowd images always contain a large number of similar patches, the self-attention mechanism in…
Example-guided image synthesis has been recently attempted to synthesize an image from a semantic label map and an exemplary image. In the task, the additional exemplary image serves to provide style guidance that controls the appearance of…
A layout to image (L2I) generation model aims to generate a complicated image containing multiple objects (things) against natural background (stuff), conditioned on a given layout. Built upon the recent advances in generative adversarial…
Attention mechanism has been crucial for image diffusion models, however, their quadratic computational complexity limits the sizes of images we can process within reasonable time and memory constraints. This paper investigates the…
Weakly-supervised semantic segmentation (WSSS) with image-level labels is an important and challenging task. Due to the high training efficiency, end-to-end solutions for WSSS have received increasing attention from the community. However,…
Transformers exhibit great advantages in handling computer vision tasks. They model image classification tasks by utilizing a multi-head attention mechanism to process a series of patches consisting of split images. However, for complex…
Deep Convolutional Neural Networks (CNNs) are powerful models that have achieved excellent performance on difficult computer vision tasks. Although CNNs perform well whenever large labeled training samples are available, they work badly on…
The classification of gigapixel histopathology images with deep multiple instance learning models has become a critical task in digital pathology and precision medicine. In this work, we propose a Transformer-based multiple instance…