Related papers: Learning to Interpret Satellite Images in Global S…
Can we leverage high-resolution information without the unsustainable quadratic complexity to input scale? We propose Traversal Network (TNet), a novel multi-scale hard-attention architecture, which traverses image scale-space in a top-down…
Developing algorithms that are able to generalize to a novel task given only a few labeled examples represents a fundamental challenge in closing the gap between machine- and human-level performance. The core of human cognition lies in the…
Semantic 2D maps are commonly used by humans and machines for navigation purposes, whether it's walking or driving. However, these maps have limitations: they lack detail, often contain inaccuracies, and are difficult to create and…
Deep learning has become one of remote sensing scientists' most efficient computer vision tools in recent years. However, the lack of training labels for the remote sensing datasets means that scientists need to solve the domain adaptation…
Determining the precise geographic location of an image at a global scale remains an unsolved challenge. Standard image retrieval techniques are inefficient due to the sheer volume of images (>100M) and fail when coverage is insufficient.…
Geologic interpretation of large seismic stacked or migrated seismic images can be a time-consuming task for seismic interpreters. Neural network based semantic segmentation provides fast and automatic interpretations, provided a sufficient…
Typical end-to-end formulations for learning robotic navigation involve predicting a small set of steering command actions (e.g., step forward, turn left, turn right, etc.) from images of the current state (e.g., a bird's-eye view of a SLAM…
The inability to interpret the model prediction in semantically and visually meaningful ways is a well-known shortcoming of most existing computer-aided diagnosis methods. In this paper, we propose MDNet to establish a direct multimodal…
Image descriptions can help visually impaired people to quickly understand the image content. While we made significant progress in automatically describing images and optical character recognition, current approaches are unable to include…
Deep learning models extract, before a final classification layer, features or patterns which are key for their unprecedented advantageous performance. However, the process of complex nonlinear feature extraction is not well understood, a…
Aerial or satellite imagery is a great source for land surface analysis, which might yield land use maps or elevation models. In this investigation, we present a neural network framework for learning semantics and local height together. We…
We introduce the Multi30K dataset to stimulate multilingual multimodal research. Recent advances in image description have been demonstrated on English-language datasets almost exclusively, but image description should not be limited to…
Recent results suggest that state-of-the-art saliency models perform far from optimal in predicting fixations. This lack in performance has been attributed to an inability to model the influence of high-level image features such as objects.…
Fully supervised change detection methods require difficult to procure pixel-level labels, while weakly supervised approaches can be trained with image-level labels. However, most of these approaches require a combination of changed and…
Publicly available satellite imagery can be an ubiquitous, cheap, and powerful tool for vehicle localisation when a prior sensor map is unavailable. However, satellite images are not directly comparable to data from ground range sensors…
Few-shot learning that trains image classifiers over few labeled examples per category is a challenging task. In this paper, we propose to exploit an additional big dataset with different categories to improve the accuracy of few-shot…
Recently many research efforts have been devoted to image annotation by leveraging on the associated tags/keywords of web images as training labels. A key issue to resolve is the relatively low accuracy of the tags. In this paper, we…
Weakly supervised semantic segmentation (WSSS) approaches typically rely on class activation maps (CAMs) for initial seed generation, which often fail to capture global context due to limited supervision from image-level labels. To address…
The explosive growth of digital images and the widespread availability of image editing tools have made image manipulation detection an increasingly critical challenge. Current deep learning-based manipulation detection methods excel in…
This paper considers the task of matching images and sentences by learning a visual-textual embedding space for cross-modal retrieval. Finding such a space is a challenging task since the features and representations of text and image are…