Papers Weakly-Supervised Object Localization
“Weakly-Supervised Object Localization” 태그가 달린 논문 140편 · 필터 해제
Counterfactual Co-occurring Learning for Bias Mitigation in Weakly-supervised Object Localization
Contemporary weakly-supervised object localization (WSOL) methods have primarily focused on addressing the challenge of localizing the most discriminative region while largely overlooking the relatively less explored iss…
AttributecounterfactualObject LocalizationWeakly-Supervised Object LocalizationOpen-World Weakly-Supervised Object Localization
While remarkable success has been achieved in weakly-supervised object localization (WSOL), current frameworks are not capable of locating objects of novel categories in open-world settings. To address this issue, we are…
ObjectObject LocalizationRepresentation LearningWeakly-Supervised Object LocalizationSpatial-Aware Token for Weakly Supervised Object Localization
Weakly supervised object localization (WSOL) is a challenging task aiming to localize objects with only image-level supervision. Recent works apply visual transformer to WSOL and achieve significant success by exploiting…
ObjectObject LocalizationWeakly-Supervised Object LocalizationKnowledge-guided Causal Intervention for Weakly-supervised Object Localization
Previous weakly-supervised object localization (WSOL) methods aim to expand activation map discriminative areas to cover the whole objects, yet neglect two inherent challenges when relying solely on image-level labels. F…
Knowledge DistillationObjectObject LocalizationWeakly-Supervised Object LocalizationAdversarial Normalization: I Can Visualize Everything (ICE)
Vision transformers use [CLS] tokens to predict image classes. Their explainability visualization has been studied using relevant information from [CLS] tokens or focusing on attention scores during self-attention. S…
Object DiscoveryObject LocalizationWeakly-Supervised Object LocalizationCategory-aware Allocation Transformer for Weakly Supervised Object Localization
Weakly supervised object localization (WSOL) aims to localize objects based on only image-level labels as supervision. Recently, transformers have been introduced into WSOL, yielding impressive results. The self-atte…
ObjectObject LocalizationWeakly-Supervised Object LocalizationExpeditious Saliency-guided Mix-up through Random Gradient Thresholding
Mix-up training approaches have proven to be effective in improving the generalization ability of Deep Neural Networks. Over the years, the research community expands mix-up methods into two directions, with extensive ef…
Classifier calibrationImage ClassificationObject LocalizationWeakly-Supervised Object LocalizationMax Pooling with Vision Transformers reconciles class and shape in weakly supervised semantic segmentation
Weakly Supervised Semantic Segmentation (WSSS) research has explored many directions to improve the typical pipeline CNN plus class activation maps (CAM) plus refinements, given the image-class label as the only supervis…
Self-Supervised LearningSemantic SegmentationSentencevalid+6Dual Progressive Transformations for Weakly Supervised Semantic Segmentation
Weakly supervised semantic segmentation (WSSS), which aims to mine the object regions by merely using class-level labels, is a challenging task in computer vision. The current state-of-the-art CNN-based methods usually a…
Inductive BiasObjectObject LocalizationSemantic Segmentation+3Constrained Sampling for Class-Agnostic Weakly Supervised Object Localization
Self-supervised vision transformers can generate accurate localization maps of the objects in an image. However, since they decompose the scene into multiple maps containing various objects, and they do not rely on any e…
ObjectObject LocalizationWeakly-Supervised Object LocalizationDiscriminative Sampling of Proposals in Self-Supervised Transformers for Weakly Supervised Object Localization
Drones are employed in a growing number of visual recognition applications. A recent development in cell tower inspection is drone-based asset surveillance, where the autonomous flight of a drone is guided by localizing …
ObjectObject LocalizationWeakly-Supervised Object LocalizationRe-Attention Transformer for Weakly Supervised Object Localization
Weakly supervised object localization is a challenging task which aims to localize objects with coarse annotations such as image categories. Existing deep network approaches are mainly based on class activation map, whic…
ObjectObject LocalizationWeakly-Supervised Object LocalizationWeakly Supervised Object Localization via Transformer with Implicit Spatial Calibration
Weakly Supervised Object Localization (WSOL), which aims to localize objects by only using image-level labels, has attracted much attention because of its low annotation cost in real applications. Recent studies leverage…
Long-range modelingObjectObject LocalizationWeakly-Supervised Object LocalizationOn Label Granularity and Object Localization
Weakly supervised object localization (WSOL) aims to learn representations that encode object location using only image-level category labels. However, many objects can be labeled at different levels of granularity. Is i…
ObjectObject LocalizationWeakly-Supervised Object LocalizationBagging Regional Classification Activation Maps for Weakly Supervised Object Localization
Classification activation map (CAM), utilizing the classification structure to generate pixel-wise localization maps, is a crucial mechanism for weakly supervised object localization (WSOL). However, CAM directly uses th…
ObjectObject LocalizationWeakly-Supervised Object LocalizationCREAM: Weakly Supervised Object Localization via Class RE-Activation Mapping
Weakly Supervised Object Localization (WSOL) aims to localize objects with image-level supervision. Existing works mainly rely on Class Activation Mapping (CAM) derived from a classification model. However, CAM-based met…
ClusteringObjectObject Localizationparameter estimation+1Location-free Human Pose Estimation
Human pose estimation (HPE) usually requires large-scale training data to reach high performance. However, it is rather time-consuming to collect high-quality and fine-grained annotations for human body. To alleviate thi…
Object LocalizationPose EstimationWeakly-Supervised Object LocalizationDiverse Instance Discovery: Vision-Transformer for Instance-Aware Multi-Label Image Recognition
Previous works on multi-label image recognition (MLIR) usually use CNNs as a starting point for research. In this paper, we take pure Vision Transformer (ViT) as the research base and make full use of the advantages of T…
Multi-Label Image RecognitionObject LocalizationWeakly-Supervised Object LocalizationViTOL: Vision Transformer for Weakly Supervised Object Localization
Weakly supervised object localization (WSOL) aims at predicting object locations in an image using only image-level category labels. Common challenges that image classification models encounter when localizing objects ar…
image-classificationImage ClassificationObjectObject Localization+1Anti-Adversarially Manipulated Attributions for Weakly Supervised Semantic Segmentation and Object Localization
Obtaining accurate pixel-level localization from class labels is a crucial process in weakly supervised semantic segmentation and object localization. Attribution maps from a trained classifier are widely used to provide…
Adversarial AttackObjectObject LocalizationSemantic Segmentation+4