Search Results for author:
Found 4 papers, 2 papers with code
F-CAM: Full Resolution Class Activation Maps via Guided Parametric Upscaling
Interpolation is required to restore full size CAMs, yet it does not consider the statistical properties of objects, such as color and texture, leading to activations with inconsistent boundaries, and inaccurate localizations.
Discriminative Sampling of Proposals in Self-Supervised Transformers for Weakly Supervised Object Localization
In this paper, we propose a method to train deep weakly-supervised object localization (WSOL) models based only on image-class labels to locate object with high confidence.
Constrained Sampling for Class-Agnostic Weakly Supervised Object Localization
Then, foreground and background pixels are sampled from these regions in order to train a WSOL model for generating activation maps that can accurately localize objects belonging to a specific class.
DiPS: Discriminative Pseudo-Label Sampling with Self-Supervised Transformers for Weakly Supervised Object Localization
Subsequently, these proposals are used as pseudo-labels to train our new transformer-based WSOL model designed to perform classification and localization tasks.
