Enhancing Transformer-Based Vision Models: Addressing Feature Map Anomalies Through Novel Optimization Strategies

Abstract

Vision Transformers (ViTs) have demonstrated superior performance across a wide range of computer vision tasks. However, structured noise artifacts in their feature maps hinder downstream applications such as segmentation and depth estimation. We propose two novel and lightweight optimisation techniques- Structured Token Augmentation (STA) and Adaptive Noise Filtering (ANF)- to improve interpretability and mitigate these artefacts. STA enhances token diversity through spatial perturbations during tokenisation, while ANF applies learnable inline denoising between transformer layers. These methods are architecture-agnostic and evaluated across standard benchmarks, including ImageNet, Ade20k, and NYUv2. Experimental results show consistent improvements in visual quality and task performance, highlighting the practical effectiveness of our approach.