2 papers
cs.CV2026
Region-Aware CLS Token Augmentation for Fine-Grained Image Retrieval
Ian de Holanda Cavalcanti Bezerra, Vivek Trivedy, Lucas Pascotti Valem +1
Image retrieval methods often rely on a single global semantic descriptor extracted from an image, e.g., the [CLS] token in vision transformers. However, trying to squeeze all the…
cs.CV2025
Learning Object Focused Attention
Vivek Trivedy, Amani Almalki, Longin Jan Latecki
We propose an adaptation to the training of Vision Transformers (ViTs) that allows for an explicit modeling of objects during the attention computation. This is achieved by adding…