Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387560848> ?p ?o ?g. }
Showing items 1 to 71 of
71
with 100 items per page.
- W4387560848 abstract "Self-supervised vision transformers (SSTs) have shown great potential to yield rich localization maps that highlight different objects in an image. However, these maps remain class-agnostic since the model is unsupervised. They often tend to decompose the image into multiple maps containing different objects while being unable to distinguish the object of interest from background noise objects. In this paper, Discriminative Pseudo-label Sampling (DiPS) is introduced to leverage these class-agnostic maps for weakly-supervised object localization (WSOL), where only image-class labels are available. Given multiple attention maps, DiPS relies on a pre-trained classifier to identify the most discriminative regions of each attention map. This ensures that the selected ROIs cover the correct image object while discarding the background ones, and, as such, provides a rich pool of diverse and discriminative proposals to cover different parts of the object. Subsequently, these proposals are used as pseudo-labels to train our new transformer-based WSOL model designed to perform classification and localization tasks. Unlike standard WSOL methods, DiPS optimizes performance in both tasks by using a transformer encoder and a dedicated output head for each task, each trained using dedicated loss functions. To avoid overfitting a single proposal and promote better object coverage, a single proposal is randomly selected among the top ones for a training image at each training step. Experimental results on the challenging CUB, ILSVRC, OpenImages, and TelDrone datasets indicate that our architecture, in combination with our transformer-based proposals, can yield better localization performance than state-of-the-art methods." @default.
- W4387560848 created "2023-10-12" @default.
- W4387560848 creator A5006937759 @default.
- W4387560848 creator A5008134051 @default.
- W4387560848 creator A5017562387 @default.
- W4387560848 creator A5038624519 @default.
- W4387560848 creator A5039660800 @default.
- W4387560848 date "2023-10-09" @default.
- W4387560848 modified "2023-10-17" @default.
- W4387560848 title "DiPS: Discriminative Pseudo-Label Sampling with Self-Supervised Transformers for Weakly Supervised Object Localization" @default.
- W4387560848 doi "https://doi.org/10.1016/j.imavis.2023.104838" @default.
- W4387560848 hasPublicationYear "2023" @default.
- W4387560848 type Work @default.
- W4387560848 citedByCount "0" @default.
- W4387560848 crossrefType "posted-content" @default.
- W4387560848 hasAuthorship W4387560848A5006937759 @default.
- W4387560848 hasAuthorship W4387560848A5008134051 @default.
- W4387560848 hasAuthorship W4387560848A5017562387 @default.
- W4387560848 hasAuthorship W4387560848A5038624519 @default.
- W4387560848 hasAuthorship W4387560848A5039660800 @default.
- W4387560848 hasBestOaLocation W43875608481 @default.
- W4387560848 hasConcept C119599485 @default.
- W4387560848 hasConcept C119857082 @default.
- W4387560848 hasConcept C127413603 @default.
- W4387560848 hasConcept C138885662 @default.
- W4387560848 hasConcept C153083717 @default.
- W4387560848 hasConcept C153180895 @default.
- W4387560848 hasConcept C154945302 @default.
- W4387560848 hasConcept C165801399 @default.
- W4387560848 hasConcept C22019652 @default.
- W4387560848 hasConcept C27206212 @default.
- W4387560848 hasConcept C2778738651 @default.
- W4387560848 hasConcept C31972630 @default.
- W4387560848 hasConcept C41008148 @default.
- W4387560848 hasConcept C50644808 @default.
- W4387560848 hasConcept C66322947 @default.
- W4387560848 hasConcept C95623464 @default.
- W4387560848 hasConcept C97931131 @default.
- W4387560848 hasConceptScore W4387560848C119599485 @default.
- W4387560848 hasConceptScore W4387560848C119857082 @default.
- W4387560848 hasConceptScore W4387560848C127413603 @default.
- W4387560848 hasConceptScore W4387560848C138885662 @default.
- W4387560848 hasConceptScore W4387560848C153083717 @default.
- W4387560848 hasConceptScore W4387560848C153180895 @default.
- W4387560848 hasConceptScore W4387560848C154945302 @default.
- W4387560848 hasConceptScore W4387560848C165801399 @default.
- W4387560848 hasConceptScore W4387560848C22019652 @default.
- W4387560848 hasConceptScore W4387560848C27206212 @default.
- W4387560848 hasConceptScore W4387560848C2778738651 @default.
- W4387560848 hasConceptScore W4387560848C31972630 @default.
- W4387560848 hasConceptScore W4387560848C41008148 @default.
- W4387560848 hasConceptScore W4387560848C50644808 @default.
- W4387560848 hasConceptScore W4387560848C66322947 @default.
- W4387560848 hasConceptScore W4387560848C95623464 @default.
- W4387560848 hasConceptScore W4387560848C97931131 @default.
- W4387560848 hasLocation W43875608481 @default.
- W4387560848 hasOpenAccess W4387560848 @default.
- W4387560848 hasPrimaryLocation W43875608481 @default.
- W4387560848 hasRelatedWork W1574414179 @default.
- W4387560848 hasRelatedWork W2490526372 @default.
- W4387560848 hasRelatedWork W2922073769 @default.
- W4387560848 hasRelatedWork W3040691452 @default.
- W4387560848 hasRelatedWork W4221142204 @default.
- W4387560848 hasRelatedWork W4281702477 @default.
- W4387560848 hasRelatedWork W4297676672 @default.
- W4387560848 hasRelatedWork W4362597605 @default.
- W4387560848 hasRelatedWork W4376166922 @default.
- W4387560848 hasRelatedWork W4378510483 @default.
- W4387560848 isParatext "false" @default.
- W4387560848 isRetracted "false" @default.
- W4387560848 workType "article" @default.