Papers Weakly-Supervised Object Localization
“Weakly-Supervised Object Localization” 태그가 달린 논문 140편 · 필터 해제
Weakly Supervised Foreground Learning for Weakly Supervised Localization and Detection
Modern deep learning models require large amounts of accurately annotated data, which is often difficult to satisfy. Hence, weakly supervised tasks, including weakly supervised object localization~(WSOL) and detection~(W…
Object LocalizationWeakly-Supervised Object LocalizationShallow Feature Matters for Weakly Supervised Object Localization
Weakly supervised object localization (WSOL) aims to localize objects by only utilizing image-level labels. Class activation maps (CAMs) are the commonly used features to achieve WSOL. However, previous CAM-based methods…
ObjectObject LocalizationPseudo LabelWeakly-Supervised Object LocalizationNormalization Matters in Weakly Supervised Object Localization
Weakly-supervised object localization (WSOL) enables finding an object using a dataset without any localization information. By simply training a classification model using only image-level annotations, the feature map o…
ObjectObject LocalizationWeakly-Supervised Object LocalizationLayerCAM: Exploring Hierarchical Class Activation Maps for Localization
The class activation maps are generated from the final convolutional layer of CNN. They can highlight discriminative object regions for the class of interest. These discovered object regions have been widely used for wea…
ObjectObject LocalizationSemantic SegmentationWeakly-Supervised Object LocalizationStrengthen Learning Tolerance for Weakly Supervised Object Localization
Weakly supervised object localization (WSOL) aims at learning to localize objects of interest by only using the image-level labels as the supervision. While numerous efforts have been made in this field, recent appro…
ObjectObject LocalizationWeakly-Supervised Object LocalizationKeep CALM and Improve Visual Feature Attribution
The class activation mapping, or CAM, has been the cornerstone of feature attribution methods for multiple vision tasks. Its simplicity and effectiveness have led to wide applications in the explanation of visual predict…
Object LocalizationWeakly-Supervised Object LocalizationImproving Few-shot Learning with Weakly-supervised Object Localization
Few-shot learning often involves metric learning-based classifiers, which predict the image label by comparing the distance between the extracted feature vector and class representations. However, applying global pooling…
Few-Shot LearningMetric LearningObject LocalizationWeakly-Supervised Object LocalizationMinMaxCAM: Improving object coverage for CAM-basedWeakly Supervised Object Localization
One of the most common problems of weakly supervised object localization is that of inaccurate object coverage. In the context of state-of-the-art methods based on Class Activation Mapping, this is caused either by local…
ObjectObject LocalizationWeakly-Supervised Object LocalizationImproving Weakly-supervised Object Localization via Causal Intervention
The recent emerged weakly supervised object localization (WSOL) methods can learn to localize an object in the image only using image-level labels. Previous works endeavor to perceive the interval objects from the small …
ObjectObject LocalizationWeakly-Supervised Object LocalizationWeakly Supervised Object Localization and Detection: A Survey
As an emerging and challenging problem in the computer vision community, weakly supervised object localization and detection plays an important role for developing new generation computer vision systems and has received …
ObjectObject LocalizationSurveyWeakly-Supervised Object LocalizationFine-Grained Attention for Weakly Supervised Object Localization
Although recent advances in deep learning accelerated an improvement in a weakly supervised object localization (WSOL) task, there are still challenges to identify the entire body of an object, rather than only discrimin…
ObjectObject LocalizationWeakly-Supervised Object LocalizationDAP: Detection-Aware Pre-training with Weak Supervision
This paper presents a detection-aware pre-training (DAP) approach, which leverages only weakly-labeled classification-style datasets (e.g., ImageNet) for pre-training, but is specifically tailored to benefit object detec…
ClassificationGeneral Classificationimage-classificationImage Classification+4TS-CAM: Token Semantic Coupled Attention Map for Weakly Supervised Object Localization
Weakly supervised object localization (WSOL) is a challenging problem when given image category labels but requires to learn object localization models. Optimizing a convolutional neural network (CNN) for classification …
ObjectObject LocalizationWeakly-Supervised Object LocalizationUnveiling the Potential of Structure Preserving for Weakly Supervised Object Localization
Weakly supervised object localization(WSOL) remains an open problem given the deficiency of finding object extent information using a classification network. Although prior works struggled to localize objects through var…
ClassificationGeneral ClassificationObjectObject Localization+2Learning from Counting: Leveraging Temporal Classification for Weakly Supervised Object Localization and Detection
This paper reports a new solution of leveraging temporal classification to support weakly supervised object detection (WSOD). Specifically, we introduce raster scan-order techniques to serialize 2D images into 1D sequenc…
General ClassificationObjectobject-detectionObject Detection+3Foreground Activation Maps for Weakly Supervised Object Localization
Weakly supervised object localization (WSOL) aims to localize objects with only image-level labels, which has better scalability and practicability than fully supervised methods in the actual deployment. However, wit…
ClassificationObjectObject LocalizationWeakly-Supervised Object LocalizationGridMix: Strong regularization through local context mapping
Recently developed regularization techniques improve the networks generalization by only considering the global context. Therefore, the network tends to focus on a few most discriminative subregions of an image for predi…
Adversarial RobustnessData AugmentationObject LocalizationWeakly-Supervised Object LocalizationHierarchical Complementary Learning for Weakly Supervised Object Localization
Weakly supervised object localization (WSOL) is a challenging problem which aims to localize objects with only image-level labels. Due to the lack of ground truth bounding boxes, class labels are mainly employed to train…
ObjectObject LocalizationWeakly-Supervised Object LocalizationLID 2020: The Learning from Imperfect Data Challenge Results
Learning from imperfect data becomes an issue in many industrial applications after the research community has made profound progress in supervised learning from perfectly annotated datasets. The purpose of the Learning …
object-detectionObject DetectionObject LocalizationScene Parsing+5Zoom-CAM: Generating Fine-grained Pixel Annotations from Image Labels
Current weakly supervised object localization and segmentation rely on class-discriminative visualization techniques to generate pseudo-labels for pixel-level training. Such visualization methods, including class activat…
Object LocalizationSegmentationSemantic SegmentationWeakly-Supervised Object Localization+2