arXiv Computer Vision

Can We Use Saliency Maps for the Evaluation of Generative Image Models?

The paper proposes a new evaluation framework for generative image models that uses a generator‑specific classifier trained to distinguish real images from those produced by a particular model. By analyzing the classifier’s decisions with saliency maps, the authors show that the maps reveal model‑specific artifacts rather than a universal notion of fakeness, and that combining classification accuracy with saliency information yields a composite score that aligns with human judgments. This approach avoids reliance on large pretrained backbones and works solely with real and generated samples from the evaluated model.

arXiv Computer Vision

Sep 28

Amplify What You Gaze At: Target Saliency Boosting in Text-to-Image Generation

The paper introduces Target Saliency Boosting, a new task that enhances the visual prominence of a specific object in text-to-image generation without visual priors. It proposes GazeME, a lightweight framework that inserts learnable marker tokens around object descriptions to indicate which objects to emphasize or suppress. By building a saliency-semantics dataset and using Saliency Prior Marker Activation, GazeME learns to adjust markers during training and automatically applies them at inference, effectively boosting target saliency while maintaining semantic alignment and image quality.

By Shengqi Dang, Zhengxi Yu, Feilin Han, Xingyu Lan, Nan Cao

diffusion safety

arXiv AI

Jul 7

Post-Generation Curation of Synthetic Images via Homogeneous-Heterogeneous Splitting

arXiv:2607. 02637v1 Announce Type: cross Abstract: Recent generative models can produce high-quality synthetic images, offering scalable training training data for data-hungry models.

By Disheng Liu, Tuo Liang, Chaoda Song, Yu Yin

llms computer-vision fine-tuning benchmarks safety

arXiv AI

Jun 26

Semantic Generative Tuning for Unified Multimodal Models

arXiv:2605. 18714v2 Announce Type: replace-cross Abstract: Unified multimodal models (UMMs) strive to consolidate visual understanding and visual generation within a single architecture.

By Songsong Yu, Yuxin Chen, Ying Shan, Yanwei Li

computer-vision multimodal benchmarks

arXiv AI

Oct 21

Assessing Representation Semantics Under Language Pretraining in Fine-Grained Classification

arXiv:2610.28051v1 Announce Type: cross Abstract: Understanding how supervision signals shape semantic visual representations remains challenging, particularly in fine-grained, low-data settings. Sta...

By Md Raisul Kibria, S\'ebastien Lafond

benchmarks

arXiv Computer Vision

Oct 9

Relative Patch Response Learning for Generalizable AI-Generated Image Detection

The paper introduces Relative Patch Response Learning (PRL) to detect AI‑generated images by comparing patch responses across two mixed views of aligned real‑generated image pairs. PRL uses a relative response objective, a reference coherence objective, and an area ranking objective to address contextual shifts caused by self‑attention, providing precise supervision for patch‑level detection. Experiments show PRL outperforms prior methods by 4.3% and 5.9% in average balanced accuracy on standard and in‑the‑wild benchmarks.

By Tianyu Wang, Ouxiang Li, Yanbin Hao, Zhenhua Tang, Shuo Wang

benchmarks safety

arXiv AI

Jul 17

When Pretty Isn't Useful: Investigating Why Modern Text-to-Image Models Fail as Reliable Training Data Generators

arXiv:2602. 19946v5 Announce Type: replace-cross Abstract: Recent text-to-image (T2I) diffusion models produce visually stunning images and demonstrate excellent prompt following.

By Krzysztof Adamkiewicz, Brian Bernhard Moser, Stanislav Frolov, Tobias Christian Nauen, Federico Raue, Andreas Dengel

diffusion benchmarks

arXiv Computer Vision

Sep 15

Learning Continuous Source Responses For Generalizable AI-Generated Image Detection

arXiv:2609.14316v1 Announce Type: new Abstract: Advances in image generation have made synthetic images increasingly difficult to distinguish from real photographs, raising concerns about the trustwo...

By Manni Cui, Ruiqi Liu, Zijian Yu, Hao Tan, Zibo Wei, Zian Wang, Ziheng Qin, Huijia Zhu, Weiqiang Wang, Jun Lan, Shu Wu

diffusion benchmarks

Hugging Face Trending Papers

Aug 26

VGA-BenchV2: An Expanded Unified Benchmark and Multi-Model Framework for Evaluating Video Aesthetics and Generation Quality

We introduce VGA-BenchV2, an extended human-aligned benchmark and optimization framework for jointly evaluating and improving video generation quality and aesthetic value. Built upon VGA-Bench, VGA-Be...

llms diffusion reinforcement-learning fine-tuning multimodal benchmarks safety

arXiv Computer Vision

Oct 27

ScenePercept: Scenario-Conditioned Perceptual Assessment of Real-World User-Generated Content Images

arXiv:2610.17661v2 Announce Type: replace Abstract: The rapid development of mobile imaging and social platforms has led to explosive growth in user-generated content images, making their systematic...

By Shuhan Xia, Yu Chen, Xiang Wang, Shuai Li, Peipie Li, Zekun Li

benchmarks safety

arXiv Computer Vision

Aug 27

VGA-BenchV2: An Expanded Unified Benchmark and Multi-Model Framework for Evaluating Video Aesthetics and Generation Quality

VGA‑BenchV2 is an expanded, human‑aligned benchmark and optimization framework that jointly evaluates video generation quality and aesthetic value. It builds on the original VGA‑Bench taxonomy, adding 52 sub‑dimensions and 1,016 curated prompts to generate over 60,000 videos from 12 mainstream models. The benchmark significantly enlarges human supervision with 36,000 task‑level annotations and introduces a hybrid evaluator (VAQA‑Net, VTag‑Net, VGQA‑Net) that aligns well with human judgments and can be used as a reward model for reinforcement‑learning fine‑tuning.

By Longteng Jiang, DanDan Zheng, Qianqian Qiao, Heng Huang, Huaye Wang, Yihang Bo, Bao Peng, Jingdong Chen, Jun Zhou, Xin Jin

llms diffusion reinforcement-learning fine-tuning multimodal benchmarks safety

arXiv Computer Vision

3d ago

RA-ClipScore: Making Generative Model Evaluation More Interpretable

arXiv:2608.12088v2 Announce Type: replace Abstract: Generative models can produce images nearly indistinguishable from real data, yet rigorous and interpretable evaluation remains challenging. Conven...

By Yifan Lu, Taras Kucherenko, Hedvig Kjellstr\"om, Judith B\"utepage

safety

Hugging Face Trending Papers

Oct 20

Assessing Representation Semantics Under Language Pretraining in Fine-Grained Classification

Understanding how supervision signals shape semantic visual representations remains challenging, particularly in fine-grained, low-data settings. Standard evaluations of vision models rely on downstre...

benchmarks

Related stories