Search

Weakly-supervised learning approaches have gained significant attention due to their ability to reduce the effort required for human annotations in training neural networks. This paper investigates a framework for weakly-supervised object localization, which aims to train a neural network capable of predicting both the object class and its location using only images and their image-level class labels. The proposed framework consists of a shared feature extractor, a classifier, and a localizer. The localizer predicts pixel-level class probabilities, while the classifier predicts the object class at the image level. Since image-level class labels are insufficient for training the localizer, weakly-supervised object localization methods often encounter challenges in accurately localizing the entire object region. To address this issue, the proposed method incorporates adversarial erasing and pseudo labels to improve localization accuracy. Specifically, novel losses are designed to utilize adversarially erased foreground features and adversarially erased feature maps, reducing dependence on the most discriminative region. Additionally, the proposed method employs pseudo labels to suppress activation values in the background while increasing them in the foreground. The proposed method is applied to two backbone networks (MobileNetV1 and InceptionV3) and is evaluated on three publicly available datasets (ILSVRC-2012, CUB-200-2011, and PASCAL VOC 2012). The experimental results demonstrate that the proposed method outperforms previous state-of-the-art methods across all evaluated metrics. [ABSTRACT FROM AUTHOR]

While image segmentation is crucial in various computer vision applications, such as autonomous driving, grasping, and robot navigation, annotating all objects at the pixel-level for training is nearly impossible. Therefore, the study of unsupervised image segmentation methods is essential. In this paper, we present a pixel-level clustering framework for segmenting images into regions without using ground truth annotations. The proposed framework includes feature embedding modules with an attention mechanism, a feature statistics computing module, image reconstruction, and superpixel segmentation to achieve accurate unsupervised segmentation. Additionally, we propose a training strategy that utilizes intra-consistency within each superpixel, inter-similarity/dissimilarity between neighboring superpixels, and structural similarity between images. To avoid potential over-segmentation caused by superpixel-based losses, we also propose a post-processing method. Furthermore, we present an extension of the proposed method for unsupervised semantic segmentation. We conducted experiments on three publicly available datasets (Berkeley segmentation dataset, PASCAL VOC 2012 dataset, and COCO-Stuff dataset) to demonstrate the effectiveness of the proposed framework. The experimental results show that the proposed framework outperforms previous state-of-the-art methods. [Display omitted] [ABSTRACT FROM AUTHOR]

Motion in videos refers to the pattern of the apparent movement of objects, surfaces, and edges over image sequences caused by the relative movement between a camera and a scene. Motion, as well as scene appearance, are essential features to estimate a driver's visual attention allocation in computer vision. However, the fact that motion can be a crucial factor in a driver's attention estimation has not been thoroughly studied in the literature, although driver's attention prediction models focusing on scene appearance have been well studied. Therefore, in this work, we investigate the usefulness of motion information in estimating a driver's visual attention. To analyze the effectiveness of motion information, we develop a deep neural network framework that provides attention locations and attention levels using optical flow maps, which represent the movements of contents in videos. We validate the performance of the proposed motion-based prediction model by comparing it to the performance of the current state-of-art prediction models using RGB frames. The experimental results for a real-world dataset confirm our hypothesis that motion plays a role in prediction accuracy improvement, and there is a margin for accuracy improvement by using motion features. [ABSTRACT FROM AUTHOR]

This work addresses the task of long-term person re-identification. Typically, person re-identification assumes that people do not change their clothes, which limits its applications to short-term scenarios. To overcome this limitation, we investigate long-term person re-identification, which considers both clothes-changing and clothes-consistent scenarios. In this paper, we propose a novel framework that effectively learns and utilizes both global and local information. The proposed framework consists of three streams: global, local body part, and head streams. The global and head streams encode identity-relevant information from an entire image and a cropped image of the head region, respectively. Both streams encode the most distinct, less distinct, and average features using the combinations of adversarial erasing, max pooling, and average pooling. The local body part stream extracts identity-related information for each body part, allowing it to be compared with the same body part from another image. Since body part annotations are not available in re-identification datasets, pseudo-labels are generated using clustering. These labels are then utilized to train a body part segmentation head in the local body part stream. The proposed framework is trained by backpropagating the weighted summation of the identity classification loss, the pair-based loss, and the pseudo body part segmentation loss. To demonstrate the effectiveness of the proposed method, we conducted experiments on three publicly available datasets (Celeb-reID, PRCC, and VC-Clothes). The experimental results demonstrate that the proposed method outperforms the previous state-of-the-art method. [ABSTRACT FROM AUTHOR]

Driving is a task that puts heavy demands on visual information, thereby the human visual system plays a critical role in making proper decisions for safe driving. Understanding a driver's visual attention and relevant behavior information is a challenging but essential task in advanced driver-assistance systems (ADAS) and efficient autonomous vehicles (AV). Specifically, robust prediction of a driver's attention from images could be a crucial key to assist intelligent vehicle systems where a self-driving car is required to move safely interacting with the surrounding environment. Thus, in this paper, we investigate a human driver's visual behavior in terms of computer vision to estimate the driver's attention locations in images. First, we show that feature representations at high resolution improves visual attention prediction accuracy and localization performance when being fused with features at low-resolution. To demonstrate this, we employ a deep convolutional neural network framework that learns and extracts feature representations at multiple resolutions. In particular, the network maintains the feature representation with the highest resolution at the original image resolution. Second, attention prediction tends to be biased toward centers of images when neural networks are trained using typical visual attention datasets. To avoid overfitting to the center-biased solution, the network is trained using diverse regions of images. Finally, the experimental results verify that our proposed framework improves the prediction accuracy of a driver's attention locations. [ABSTRACT FROM AUTHOR]