ReViT: Enhancing vision transformers with residual attention (Journal of Pattern Recognition)

Abstract

Vision Transformer (ViT) self-attention mechanism is characterized by feature collapse in deeper layers, resulting in the vanishing of low-level visual features. However, such features can be helpful to accurately represent and identify elements within an image and increase the accuracy and robustness of vision-based recognition systems. Following this rationale, we propose a novel residual attention learning method for improving ViT-based architectures, increasing their visual feature diversity and model robustness. In this way, the proposed network can capture and preserve significant low-level features, providing more details about the elements within the scene being analyzed. The effectiveness and robustness of the presented method are evaluated on five image classification benchmarks, including ImageNet1k, CIFAR10, CIFAR100, Oxford Flowers-102, and Oxford-IIIT Pet, achieving improved performances. Additionally, experiments on the COCO2017 dataset show that the devised approach discovers and incorporates semantic and spatial relationships for object detection and instance segmentation when implemented into spatial-aware transformer models.

Anxhelo Diko
Anxhelo Diko
PhD Student In Computer Science

A highly motivated and results-oriented Computer Vision Ph.D. student with a deep passion for advancing the field of artificial intelligence. My research focuses on building multimodal representations and understanding human activities from ego/exocentric perspectives, addressing key challenges for autonomous agents and AI in general. I have extensive experience with multimodal large language models for video captioning and question answering and a keen interest in view-invariant video representation learning. I’m particularly committed to exploring how to effectively bridge the gap between representations of different modalities while preserving their unique characteristics. In addition to my research expertise, I possess a strong engineering foundation honed through academic and industry experiences. Proficient in Python, C++, and CUDA, I excel at rapidly prototyping and implementing innovative ideas. I’m eager to leverage my skills and knowledge to contribute to cutting-edge research and development in this dynamic field.