Related papers: SemAug: Semantically Meaningful Image Augmentation…

We present a novel approach for relocalization or place recognition, a fundamental problem to be solved in many robotics, automation, and AR applications. Rather than relying on often unstable appearance information, we consider a situation…

Semantic segmentation is a powerful method to facilitate visual scene understanding. Each pixel is assigned a label according to a pre-defined list of object classes and semantic entities. This becomes very useful as a means to summarize…

Enhancing the generalization capability of robotic learning to enable robots to operate effectively in diverse, unseen scenes is a fundamental and challenging problem. Existing approaches often depend on pretraining with large-scale data…

We propose an approach to domain adaptation for semantic segmentation that is both practical and highly accurate. In contrast to previous work, we abandon the use of computationally involved adversarial objectives, network ensembles and…

The detection and grounding of manipulated content in multimodal data has emerged as a critical challenge in media forensics. While existing benchmarks demonstrate technical progress, they suffer from misalignment artifacts that poorly…

The success of deep learning in computer vision is based on availability of large annotated datasets. To lower the need for hand labeled images, virtually rendered 3D worlds have recently gained popularity. Creating realistic 3D content is…

Building robust and generic object detection frameworks requires scaling to larger label spaces and bigger training datasets. However, it is prohibitively costly to acquire annotations for thousands of categories at a large scale. We…

With the aim of promoting and understanding the multilingual version of image search, we leverage visual object detection and propose a model with diverse multi-head attention to learn grounded multilingual multimodal representations.…

In semi-supervised semantic segmentation (SSSS), data augmentation plays a crucial role in the weak-to-strong consistency regularization framework, as it enhances diversity and improves model generalization. Recent strong augmentation…

Intelligent image editing increasingly relies on advances in computer vision, multimodal reasoning, and generative modeling. While vision-language models (VLMs) and diffusion models enable guided visual manipulation, existing work rarely…

It is challenging to train a robust object detector under the supervised learning setting when the annotated data are scarce. Thus, previous approaches tackling this problem are in two categories: semi-supervised learning models that…

In the field of autonomous driving, camera-based perception models are mostly trained on clear weather data. Models that focus on addressing specific weather challenges are unable to adapt to various weather changes and primarily prioritize…

Object detection in urban scenarios is crucial for autonomous driving in intelligent traffic systems. However, unlike conventional object detection tasks, urban-scene images vary greatly in style. For example, images taken on sunny days…

Multimodal automatic speech recognition systems integrate information from images to improve speech recognition quality, by grounding the speech in the visual context. While visual signals have been shown to be useful for recovering…

This paper describes a fast and accurate semantic image segmentation approach that encodes not only the discriminative features from deep neural networks, but also the high-order context compatibility among adjacent objects as well as low…

We address the problem of phrase grounding by lear ing a multi-level common semantic space shared by the textual and visual modalities. We exploit multiple levels of feature maps of a Deep Convolutional Neural Network, as well as…

In computer vision, it is well-known that a lack of data diversity will impair model performance. In this study, we address the challenges of enhancing the dataset diversity problem in order to benefit various downstream tasks such as…

Existing semantic segmentation approaches either aim to improve the object's inner consistency by modeling the global context, or refine objects detail along their boundaries by multi-scale feature fusion. In this paper, a new paradigm for…

Semantic segmentation using deep neural networks has been widely explored to generate high-level contextual information for autonomous vehicles. To acquire a complete $180^\circ$ semantic understanding of the forward surroundings, we…

Data augmentation is a prevalent technique for improving performance in various machine learning applications. We propose SeqAug, a modality-agnostic augmentation method that is tailored towards sequences of extracted features. The core…