Related papers: Localizing Semantic Patches for Accelerating Image…

Image based localization is one of the important problems in computer vision due to its wide applicability in robotics, augmented reality, and autonomous systems. There is a rich set of methods described in the literature how to…

Understanding and extracting 3D information of objects from monocular 2D images is a fundamental problem in computer vision. In the task of 3D object pose estimation, recent data driven deep neural network based approaches suffer from…

Patch-based image tokenization ignores the morphology of the visual world, limiting effective and efficient learning of image understanding. Inspired by subword tokenization, we introduce subobject-level adaptive token segmentation and…

This work presents and analyzes three convolutional neural network (CNN) models for efficient pixelwise classification of images. When using convolutional neural networks to classify single pixels in patches of a whole image, a lot of…

Semantic localization, i.e., robot self-localization with semantic image modality, is critical in recently emerging embodied AI applications (e.g., point-goal navigation, object-goal navigation, vision language navigation) and topological…

The ability to quickly recognize and learn new visual concepts from limited samples enables humans to swiftly adapt to new environments. This ability is enabled by semantic associations of novel concepts with those that have already been…

The main obstacle to weakly supervised semantic image segmentation is the difficulty of obtaining pixel-level information from coarse image-level annotations. Most methods based on image-level annotations use localization maps obtained from…

Understanding how a complex machine learning model makes a classification decision is essential for its acceptance in sensitive areas such as health care. Towards this end, we present PatchNet, a method that provides the features indicative…

We aim for domestic robots to perform long-term indoor service. Under the object-level scene dynamics induced by daily human activities, a robot needs to robustly localize itself in the environment subject to scene uncertainties. Previous…

Recently, semantic segmentation and general object detection frameworks have been widely adopted by scene text detecting tasks. However, both of them alone have obvious shortcomings in practice. In this paper, we propose a novel end-to-end…

This paper presents a sparse representation-based classification approach with a novel dictionary construction procedure. By using the constructed dictionary sophisticated prior knowledge about the spatial nature of the image can be…

Tiny deep learning on microcontroller units (MCUs) is challenging due to the limited memory size. We find that the memory bottleneck is due to the imbalanced memory distribution in convolutional neural network (CNN) designs: the first…

Single image-level annotations only correctly describe an often small subset of an image's content, particularly when complex real-world scenes are depicted. While this might be acceptable in many classification scenarios, it poses a…

Images captured in harsh environments often exhibit blurred details, reduced contrast, and color distortion, which hinder feature detection and matching, thereby affecting the accuracy and robustness of homography estimation. While visual…

A neural network targeting at unsupervised image anomaly localization, called the PEDENet, is proposed in this work. PEDENet contains a patch embedding (PE) network, a density estimation (DE) network, and an auxiliary network called the…

Scene text image super-resolution has significantly improved the accuracy of scene text recognition. However, many existing methods emphasize performance over efficiency and ignore the practical need for lightweight solutions in deployment…

Patch-level image representation is very important for object classification and detection, since it is robust to spatial transformation, scale variation, and cluttered background. Many existing methods usually require fine-grained…

We present SparseAttnNet, a new hierarchical attention-driven framework for efficient image classification that adaptively selects and processes only the most informative pixels from images. Traditional convolutional neural networks…

Real-time single-stage object detectors based on deep learning still remain less accurate than more complex ones. The trade-off between model performance and computational speed is a major challenge. In this paper, we propose a new way to…

Modern deep learning architectures produce highly accurate results on many challenging semantic segmentation datasets. State-of-the-art methods are, however, not directly transferable to real-time applications or embedded devices, since…