Papers for

image recognition system developers

Papers whose findings have a practical use for this group, as judged from the abstract. Open a paper to read what it means in practice.

Diffusion models lose some features faster when trained on synthetic data

Feature Selective Model Collapse in Diffusion Models: Total Replacement versus Fixed-Budget Training

Abstract: Model collapse arises when generative models are trained on synthetic data produced by earlier models. The phenomenon has attracted considerable attention because of its societal and technical implications. However, previous studies have reached seemingly contradictory conclusions: replacing real data with synthetic data causes collapse (Shumailov et al.), yet accumulating real data alongside synthetic data can prevent it. For diffusion models, we study an intermediate regime typical of finite-budget pipelines: all past datasets and the real data are kept, but each new model is trained on a fixed-size sample from this growing pool, so the real fraction vanishes without any data being removed. Experiments on a 2D spiral dataset as well as the image benchmarks (MNIST, Fashion-MNIST, and CIFAR-10) show that replacement protocol degrades dataset rapidly as in the literature, whereas the fixed budget degrades only partially, sparing some features. A linear-response model of the multi-generational parameter dynamics, analyzed by stochastic recursion, confirms that the two protocols differ: some features will be fragile and lost within a few generations for both protocols, while some will be robust and preserved over practically unbounded horizons under the fixed budget protocol.

Thu 1 OctMachine LearningArtificial Intelligence
The gist
When AI systems called diffusion models learn from data generated by earlier versions of themselves, they can lose important details, a problem called model collapse. The paper compares two training methods: one where real data is completely replaced by synthetic data, and another where training uses a fixed amount of mixed real and synthetic data, even as more data accumulates. The authors find that completely replacing data leads to rapid loss of features, while the fixed-budget approach retains some features for many generations. They also provide a mathematical model to explain why some features disappear quickly and others last longer depending on the method.
Open → 2610.01318v1

Carrier improves adversarial attacks while preserving main image objects

Let the Carrier Carry the Attack: Preserving the Subject in Adversarial Image Generation

Abstract: Strong unrestricted adversarial attacks can distort the primary object of an image, hereafter referred to as the subject. To preserve subject integrity without compromising attack magnitude, we introduce the carrier: a secondary visual element that provides an auxiliary region to facilitate the attack under global classifier guidance. We demonstrate three key findings: 1. A carrier mitigates subject distortion by absorbing a larger share of globally normalized attack updates. 2. A carrier improves cross-model transferability, governed by the strength of target-related features that balance semantic separation and transfer performance. 3. Successful targeted attacks retain the personalized subject as the primary content perceived by humans while successfully misleading the classifier. Our results demonstrate that a visually secondary carrier offers an auxiliary spatial pathway for adversarial changes, enabling strong and transferable attacks while improving subject preservation.

Wed 30 SeptComputer Vision and Pattern RecognitionArtificial Intelligence
The gist
Adversarial attacks on images try to fool AI systems but often distort the main object in the picture. The authors propose adding a ‘carrier,’ a less important part of the image that carries most of the attack changes instead. This approach keeps the main object looking normal to humans while still tricking AI across different models. The carrier helps balance strong attacks with keeping the subject recognizable.
Open → 2609.39723v1