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

arXiv: https://arxiv.org/abs/2509.19687 · HTML: https://mlsanity.com/paper/2509.19687/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 15 references that are in the map.
- First posted on arXiv 24 Sep 2025.

## Builds on (most cited first, 15 of 15)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [Reproducible scaling laws for contrastive language-image learning](https://mlsanity.com/paper/2212.07143/) (2022)
- [Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model](https://mlsanity.com/paper/2401.09417/) (2024)
- [Vision Transformers Need Registers](https://mlsanity.com/paper/2309.16588/) (2023)
- [DeiT III: Revenge of the ViT](https://mlsanity.com/paper/2204.07118/) (2022)
- [Localizing Objects with Self-Supervised Transformers and no Labels](https://mlsanity.com/paper/2109.14279/) (2021)
- [Memory Transformer](https://mlsanity.com/paper/2006.11527/) (2020)
- [Mamba-R: Vision Mamba ALSO Needs Registers](https://mlsanity.com/paper/2405.14858/) (2024)
- [Denoising Vision Transformers](https://mlsanity.com/paper/2401.02957/) (2024)
- [Vision Transformers: State of the Art and Research Challenges](https://mlsanity.com/paper/2207.03041/) (2022)

## Built on by (most cited first, 2 of 2)

- [Guardrailed Uplift Targeting: A Causal Optimization Playbook for Marketing Strategy](https://mlsanity.com/paper/2512.19805/) (2025)
- [Guardrailed Elasticity Pricing: A Churn-Aware Forecasting Playbook for Subscription Strategy](https://mlsanity.com/paper/2512.20932/) (2025)

## Abstract (arXiv)

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.