相关论文: Controlling Style and Semantics in Weakly-Supervis…

The performance of computer vision models in certain real-world applications (e.g., rare wildlife observation) is limited by the small number of available images. Expanding datasets using pre-trained generative models is an effective way to…

Conditional image generation models have achieved remarkable results by leveraging text-based control to generate customized images. However, the high resource demands of these models and the scarcity of well-annotated data have hindered…

3D-consistent image generation from a single 2D semantic label is an important and challenging research topic in computer graphics and computer vision. Although some related works have made great progress in this field, most of the existing…

Recent advances in image generation have achieved remarkable visual quality, while a fundamental challenge remains: Can image generation be controlled at the element level, enabling intuitive modifications such as adjusting shapes, altering…

Recent approaches for weakly supervised instance segmentations depend on two components: (i) a pseudo label generation model that provides instances which are consistent with a given annotation; and (ii) an instance segmentation model,…

Many promising applications of supervised machine learning face hurdles in the acquisition of labeled data in sufficient quantity and quality, creating an expensive bottleneck. To overcome such limitations, techniques that do not depend on…

Learning to build 3D scene graphs is essential for real-world perception in a structured and rich fashion. However, previous 3D scene graph generation methods utilize a fully supervised learning manner and require a large amount of…

Training convolutional networks for semantic segmentation with strong (per-pixel) and weak (per-bounding-box) supervision requires a large amount of weakly labeled data. We propose two methods for selecting the most relevant data with weak…

Recent improvements to Generative Adversarial Networks (GANs) have made it possible to generate realistic images in high resolution based on natural language descriptions such as image captions. Furthermore, conditional GANs allow us to…

Recent text-to-image generation favors various forms of spatial conditions, e.g., masks, bounding boxes, and key points. However, the majority of the prior art requires form-specific annotations to fine-tune the original model, leading to…

This paper proposes a novel weakly-supervised semantic segmentation method using image-level label only. The class-specific activation maps from the well-trained classifiers are used as cues to train a segmentation network. The well-known…

We introduce a data-driven approach for interactively synthesizing in-the-wild images from semantic label maps. Our approach is dramatically different from recent work in this space, in that we make use of no learning. Instead, our approach…

Image-level weakly-supervised semantic segmentation (WSSS) reduces the usually vast data annotation cost by surrogate segmentation masks during training. The typical approach involves training an image classification network using global…

Most state-of-the-art semantic segmentation approaches only achieve high accuracy in good conditions. In practically-common but less-discussed adverse environmental conditions, their performance can decrease enormously. Existing studies…

Text-to-image diffusion generative models can generate high quality images at the cost of tedious prompt engineering. Controllability can be improved by introducing layout conditioning, however existing methods lack layout editing ability…

In fine-grained road scene understanding, semantic segmentation plays a crucial role in enabling vehicles to perceive and comprehend their surroundings. By assigning a specific class label to each pixel in an image, it allows for precise…

Learned dynamic weighting of the conditioning signal (attention) has been shown to improve neural language generation in a variety of settings. The weights applied when generating a particular output sequence have also been viewed as…

Existing methods for large-scale point cloud semantic segmentation require expensive, tedious and error-prone manual point-wise annotations. Intuitively, weakly supervised training is a direct solution to reduce the cost of labeling.…

Diffusion models excel in image generation but lack detailed semantic control using text prompts. Additional techniques have been developed to address this limitation. However, conditioning diffusion models solely on text-based descriptions…

There is a growing interest in developing computer vision methods that can learn from limited supervision. In this paper, we consider the problem of learning to predict camera viewpoints, where obtaining ground-truth annotations are…