Improving Image Clustering with Artifacts Attenuation via Inference-Time Attention Engineering

• URL: http://arxiv.org/abs/2410.04801v1
• Date: Mon, 7 Oct 2024 07:26:10 GMT
• Title: Improving Image Clustering with Artifacts Attenuation via Inference-Time Attention Engineering
• Authors: Kazumoto Nakamura, Yuji Nozawa, Yu-Chieh Lin, Kengo Nakata, Youyang Ng,
• Abstract summary: As model size increases, high-norm artifacts anomaly appears in the patches of multi-head attention. We propose Inference-Time Attention Engineering (ITAE) which manipulates attention function during inference. ITAE shows improved clustering accuracy on multiple datasets by exhibiting more expressive features in latent space.
• Score: 1.8786950286587742
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The goal of this paper is to improve the performance of pretrained Vision Transformer (ViT) models, particularly DINOv2, in image clustering task without requiring re-training or fine-tuning. As model size increases, high-norm artifacts anomaly appears in the patches of multi-head attention. We observe that this anomaly leads to reduced accuracy in zero-shot image clustering. These artifacts are characterized by disproportionately large values in the attention map compared to other patch tokens. To address these artifacts, we propose an approach called Inference-Time Attention Engineering (ITAE), which manipulates attention function during inference. Specifically, we identify the artifacts by investigating one of the Query-Key-Value (QKV) patches in the multi-head attention and attenuate their corresponding attention values inside the pretrained models. ITAE shows improved clustering accuracy on multiple datasets by exhibiting more expressive features in latent space. Our findings highlight the potential of ITAE as a practical solution for reducing artifacts in pretrained ViT models and improving model performance in clustering tasks without the need for re-training or fine-tuning.

Related papers

• Stanceformer: Target-Aware Transformer for Stance Detection [59.69858080492586]
  Stance Detection involves discerning the stance expressed in a text towards a specific subject or target. Prior works have relied on existing transformer models that lack the capability to prioritize targets effectively. We introduce Stanceformer, a target-aware transformer model that incorporates enhanced attention towards the targets during both training and inference.
  arXiv  Detail & Related papers  (2024-10-09T17:24:28Z)
• Adaptive Masking Enhances Visual Grounding [12.793586888511978]
  We propose IMAGE, Interpretative MAsking with Gaussian radiation modEling, to enhance vocabulary grounding in low-shot learning scenarios. We evaluate the efficacy of our approach on benchmark datasets, including COCO and ODinW, demonstrating its superior performance in zero-shot and few-shot tasks.
  arXiv  Detail & Related papers  (2024-10-04T05:48:02Z)
• Localized Gaussians as Self-Attention Weights for Point Clouds Correspondence [92.07601770031236]
  We investigate semantically meaningful patterns in the attention heads of an encoder-only Transformer architecture. We find that fixing the attention weights not only accelerates the training process but also enhances the stability of the optimization.
  arXiv  Detail & Related papers  (2024-09-20T07:41:47Z)
• SINDER: Repairing the Singular Defects of DINOv2 [61.98878352956125]
  Vision Transformer models trained on large-scale datasets often exhibit artifacts in the patch token they extract. We propose a novel fine-tuning smooth regularization that rectifies structural deficiencies using only a small dataset.
  arXiv  Detail & Related papers  (2024-07-23T20:34:23Z)
• Attention-Guided Masked Autoencoders For Learning Image Representations [16.257915216763692]
  Masked autoencoders (MAEs) have established themselves as a powerful method for unsupervised pre-training for computer vision tasks. We propose to inform the reconstruction process through an attention-guided loss function. Our evaluations show that our pre-trained models learn better latent representations than the vanilla MAE.
  arXiv  Detail & Related papers  (2024-02-23T08:11:25Z)
• Attention as Robust Representation for Time Series Forecasting [23.292260325891032]
  Time series forecasting is essential for many practical applications. Transformers' key feature, the attention mechanism, dynamically fusing embeddings to enhance data representation, often relegating attention weights to a byproduct role. Our approach elevates attention weights as the primary representation for time series, capitalizing on the temporal relationships among data points to improve forecasting accuracy.
  arXiv  Detail & Related papers  (2024-02-08T03:00:50Z)
• Data-efficient Large Vision Models through Sequential Autoregression [58.26179273091461]
  We develop an efficient, autoregression-based vision model on a limited dataset. We demonstrate how this model achieves proficiency in a spectrum of visual tasks spanning both high-level and low-level semantic understanding. Our empirical evaluations underscore the model's agility in adapting to various tasks, heralding a significant reduction in the parameter footprint.
  arXiv  Detail & Related papers  (2024-02-07T13:41:53Z)
• Optimizing Relevance Maps of Vision Transformers Improves Robustness [91.61353418331244]
  It has been observed that visual classification models often rely mostly on the image background, neglecting the foreground, which hurts their robustness to distribution changes. We propose to monitor the model's relevancy signal and manipulate it such that the model is focused on the foreground object. This is done as a finetuning step, involving relatively few samples consisting of pairs of images and their associated foreground masks.
  arXiv  Detail & Related papers  (2022-06-02T17:24:48Z)
• Mean Embeddings with Test-Time Data Augmentation for Ensembling of Representations [8.336315962271396]
  We look at the ensembling of representations and propose mean embeddings with test-time augmentation (MeTTA) MeTTA significantly boosts the quality of linear evaluation on ImageNet for both supervised and self-supervised models. We believe that spreading the success of ensembles to inference higher-quality representations is the important step that will open many new applications of ensembling.
  arXiv  Detail & Related papers  (2021-06-15T10:49:46Z)
• CutPaste: Self-Supervised Learning for Anomaly Detection and Localization [59.719925639875036]
  We propose a framework for building anomaly detectors using normal training data only. We first learn self-supervised deep representations and then build a generative one-class classifier on learned representations. Our empirical study on MVTec anomaly detection dataset demonstrates the proposed algorithm is general to be able to detect various types of real-world defects.
  arXiv  Detail & Related papers  (2021-04-08T19:04:55Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.