InstructMixup: Instruction-Guided Salient Patch Editing for Robust Data Augmentation

• URL: http://arxiv.org/abs/2607.19324v1
• Date: Tue, 21 Jul 2026 17:44:55 GMT
• Title: InstructMixup: Instruction-Guided Salient Patch Editing for Robust Data Augmentation
• Abstract summary: We propose our, a data augmentation method that constructs challenging yet label-consistent training samples entirely within a single visual sample.<n>our first extracts multi-scale salient patches from the sample using a lightweight saliency detector, refines each patch with an instruction-guided generative model, and blends the edited patch back into the non-salient regions of the same sample.<n>To further diversify the learned representation, our injects self-similar fractal structure into the same salient regions at an adaptive ratio, so each training sample carries both fractal and non-fractal structure
• Score: 41.90458736034228
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In image and video technologies, data augmentation is widely used to improve the generalization of deep visual models, and mixup-based strategies that interpolate between samples have become the dominant approach. However, computing informative mixing regions adds substantial overhead, and blending content across different images frequently disrupts the semantic integrity of the resulting sample. We propose \our{}, a data augmentation method that constructs challenging yet label-consistent training samples entirely within a single visual sample. \our{} first extracts multi-scale salient patches from the sample using a lightweight saliency detector, refines each patch with an instruction-guided generative model, and blends the edited patch back into the non-salient regions of the same sample; because the generative edits are computed once and cached offline, this step adds negligible training cost. To further diversify the learned representation, \our{} injects self-similar fractal structure into the same salient regions at an adaptive ratio, so each training sample carries both fractal and non-fractal structure. We derive a second-order approximation of the resulting vicinal risk, showing that the method simultaneously enforces invariance to the generative edit and suppresses curvature along the perturbed salient directions, and we verify both predictions empirically. We evaluate on small to large backbones for instance Convolutional Neural Networks (CNNs), Vision Transformers (ViTs) and Vision-Language Foundational Models (VLMs) across seven benchmarks covering coarse- and fine-grained classification, robustness to corruption and occlusion, calibration, and transfer and self-supervised learning, InstructMixup outperforms nine competing augmentation methods, surpassing the strongest baseline across all benchmarks.

Related papers

• $S^{2}$-FracMix: Label-Preserving Self-Saliency Mixup Augmentation [41.90458736034228]
  Self-Saliency ($S2$) Mixup and FracMix ($S2$-FracMix) are presented.<n>Self-Saliency constructs challenging yet label-consistent samples by extracting multi-scale salient patches.<n>FracMix injects self-similarity patterns into salient regions using adaptive ratios.
  arXiv  Detail & Related papers  (2026-06-24T13:00:39Z)
• Towards Generalized Image Manipulation Localization via Score-based Model [38.03898206912958]
  We propose DiffIML, a novel framework that introduces score-based generative modeling to IML.<n>Under this formulation, diffusion models serve as an effective numerical solver for the learned score function.<n>Experiments on eight non-generative and three generative benchmarks demonstrate that DiffIML consistently outperforms state-of-the-art methods.
  arXiv  Detail & Related papers  (2026-05-16T08:39:54Z)
• Calibrating Biased Distribution in VFM-derived Latent Space via Cross-Domain Geometric Consistency [52.52950138164424]
  We show that when leveraging the off-the-shelf (vision) foundation models for feature extraction, the geometric shapes of the resulting feature distributions exhibit remarkable transferability across domains and datasets.<n>We embody our geometric knowledge-guided distribution calibration framework in two popular and challenging settings: federated learning and long-tailed recognition.<n>In long-tailed learning, it utilizes the geometric knowledge transferred from sample-rich categories to recover the true distribution for sample-scarce tail classes.
  arXiv  Detail & Related papers  (2025-08-19T05:22:59Z)
• Cross-Subject Mind Decoding from Inaccurate Representations [42.19569985029642]
  We propose a Bi Autoencoder Intertwining framework for accurate decoded representation prediction.<n>Our method outperforms state-of-the-art approaches on benchmark datasets in both qualitative and quantitative evaluations.
  arXiv  Detail & Related papers  (2025-07-25T08:45:02Z)
• A Simplified Framework for Contrastive Learning for Node Representations [2.277447144331876]
  We investigate the potential of deploying contrastive learning in combination with Graph Neural Networks for embedding nodes in a graph. We show that the quality of the resulting embeddings and training time can be significantly improved by a simple column-wise postprocessing of the embedding matrix. This modification yields improvements in downstream classification tasks of up to 1.5% and even beats existing state-of-the-art approaches on 6 out of 8 different benchmarks.
  arXiv  Detail & Related papers  (2023-05-01T02:04:36Z)
• Reflected Diffusion Models [93.26107023470979]
  We present Reflected Diffusion Models, which reverse a reflected differential equation evolving on the support of the data. Our approach learns the score function through a generalized score matching loss and extends key components of standard diffusion models.
  arXiv  Detail & Related papers  (2023-04-10T17:54:38Z)
• Intra-class Adaptive Augmentation with Neighbor Correction for Deep Metric Learning [99.14132861655223]
  We propose a novel intra-class adaptive augmentation (IAA) framework for deep metric learning. We reasonably estimate intra-class variations for every class and generate adaptive synthetic samples to support hard samples mining. Our method significantly improves and outperforms the state-of-the-art methods on retrieval performances by 3%-6%.
  arXiv  Detail & Related papers  (2022-11-29T14:52:38Z)
• DoubleMix: Simple Interpolation-Based Data Augmentation for Text Classification [56.817386699291305]
  This paper proposes a simple yet effective data augmentation approach termed DoubleMix. DoubleMix first generates several perturbed samples for each training data. It then uses the perturbed data and original data to carry out a two-step in the hidden space of neural models.
  arXiv  Detail & Related papers  (2022-09-12T15:01:04Z)
• Saliency Grafting: Innocuous Attribution-Guided Mixup with Calibrated Label Mixing [104.630875328668]
  Mixup scheme suggests mixing a pair of samples to create an augmented training sample. We present a novel, yet simple Mixup-variant that captures the best of both worlds.
  arXiv  Detail & Related papers  (2021-12-16T11:27:48Z)
• Conditional Variational Autoencoder for Learned Image Reconstruction [5.487951901731039]
  We develop a novel framework that approximates the posterior distribution of the unknown image at each query observation. It handles implicit noise models and priors, it incorporates the data formation process (i.e., the forward operator), and the learned reconstructive properties are transferable between different datasets.
  arXiv  Detail & Related papers  (2021-10-22T10:02:48Z)

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.