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

Source: [Enhancing Transformer-Based Vision Models: Addressing Feature Map Anomalies Through Novel Optimization Strategies](<https://www.sota2.com/research/paper/68fa7b931e209131cea893be>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T05:43:27.824Z

Authors: Sumit Mamtani

Published: 2025-09-24T01:49:59.000Z

## 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2509.19687>)

[PDF](<https://arxiv.org/pdf/2509.19687.pdf>)