Efficient Object Localization Research Articles

Adaptive Zone Learning for Weakly Supervised Object Localization.

Weakly supervised object localization (WSOL) stands as a pivotal endeavor within the realm of computer vision, entailing the location of objects utilizing merely image-level labels. Contemporary approaches in WSOL have leveraged FPMs, yielding commendable outcomes. However, these existing FPM-based techniques are predominantly confined to rudimentary strategies of either augmenting the foreground or diminishing the background presence. We argue for the exploration and exploitation of the intricate interplay between the object's foreground and its background to achieve efficient object localization. In this manuscript, we introduce an innovative framework, termed adaptive zone learning (AZL), which operates on a coarse-to-fine basis to refine FPMs through a triad of adaptive zone mechanisms. First, an adversarial learning mechanism (ALM) is employed, orchestrating an interplay between the foreground and background regions. This mechanism accentuates coarse-grained object regions in a mutually adversarial manner. Subsequently, an oriented learning mechanism (OLM) is unveiled, which harnesses local insights from both foreground and background in a fine-grained manner. This mechanism is instrumental in delineating object regions with greater granularity, thereby generating better FPMs. Furthermore, we propose a reinforced learning mechanism (RLM) as the compensatory mechanism for adversarial design, by which the undesirable foreground maps are refined again. Extensive experiments on CUB-200-2011 and ILSVRC datasets demonstrate that AZL achieves significant and consistent performance improvements over other state-of-the-art WSOL methods.

Efficient Object Localization Scheme Based on Vanishing Line in Road Image for Autonomous Vehicles

This paper proposes an efficient object localization method based on a vanishing line. The proposed method can be much improved in time efficiency since it requires scanning only vanishing line area. It requires the time complexity of O(n) while the existing sliding window method requires the time complexity O(n2) for detecting all objects in the entire image. In addition, the range of detection area can be also remarkably reduced when compared with the sliding window method. As a result, the total range and times for searching in the proposed method can be significantly reduced by considering together the distance and position of the object. The experiment on the proposed method is performed with the virtual road data set known as SYNTHIA, and the competitive results are obtained.

NucleiSegNet: Robust deep learning architecture for the nuclei segmentation of liver cancer histopathology images

The nuclei segmentation of hematoxylin and eosin (H&E) stained histopathology images is an important prerequisite in designing a computer-aided diagnostics (CAD) system for cancer diagnosis and prognosis. Automated nuclei segmentation methods enable the qualitative and quantitative analysis of tens of thousands of nuclei within H&E stained histopathology images. However, a major challenge during nuclei segmentation is the segmentation of variable sized, touching nuclei. To address this challenge, we present NucleiSegNet - a robust deep learning network architecture for the nuclei segmentation of H&E stained liver cancer histopathology images. Our proposed architecture includes three blocks: a robust residual block, a bottleneck block, and an attention decoder block. The robust residual block is a newly proposed block for the efficient extraction of high-level semantic maps. The attention decoder block uses a new attention mechanism for efficient object localization, and it improves the proposed architecture's performance by reducing false positives. When applied to nuclei segmentation tasks, the proposed deep-learning architecture yielded superior results compared to state-of-the-art nuclei segmentation methods. We applied our proposed deep learning architecture for nuclei segmentation to a set of H&E stained histopathology images from two datasets, and our comprehensive results show that our proposed architecture outperforms state-of-the-art methods. As part of this work, we also introduced a new liver dataset (KMC liver dataset) of H&E stained liver cancer histopathology image tiles, containing 80 images with annotated nuclei procured from Kasturba Medical College (KMC), Mangalore, Manipal Academy of Higher Education (MAHE), Manipal, Karnataka, India. The proposed model's source code is available at https://github.com/shyamfec/NucleiSegNet.

Efficient Target Object Localization Model Based on Biologically Motivated Visual Selective Attention

This work proposes a novel biologically motivated visual selective attention model for efficient visual searching, which is implemented by integrating three attention mechanisms: bottom-up attention, top-down attention, and spatial attention. Bottom-up attention generates salient locations by reflecting top-down biases as well as three primitive visual features: intensity, edge and color. Prototype-based object perception is proposed for top-down attention, in which a 3-D color histogram is applied to generate a prototype of the target object. And experience based spatial attention can determine acceleration to localize a target object, which is modeled by using memorized spatial location information updated by object-localization experience. In order to verify the performance of the proposed visual selective attention model, we apply the proposed model to a real application in pedestrian traffic signal detection, to be utilized as part of a blind guide system. The proposed selective attention model shows plausible performance in terms of accuracy and computation time while efficiently localizing pedestrian traffic signals.

Randomized spatial context for object search.

Searching visual objects in large image or video data sets is a challenging problem, because it requires efficient matching and accurate localization of query objects that often occupy a small part of an image. Although spatial context has been shown to help produce more reliable detection than methods that match local features individually, how to extract appropriate spatial context remains an open problem. Instead of using fixed-scale spatial context, we propose a randomized approach to deriving spatial context, in the form of spatial random partition. The effect of spatial context is achieved by averaging the matching scores over multiple random patches. Our approach offers three benefits: 1) the aggregation of the matching scores over multiple random patches provides robust local matching; 2) the matched objects can be directly identified on the pixelwise confidence map, which results in efficient object localization; and 3) our algorithm lends itself to easy parallelization and also allows a flexible tradeoff between accuracy and speed through adjusting the number of partition times. Both theoretical studies and experimental comparisons with the state-of-the-art methods validate the advantages of our approach.