In recent years, semantic segmentation has taken benefit from various works in computer vision. Inspired by the very versatile CycleGAN architecture, we combine semantic segmentation with the concept of cycle consistency to enable a multitask training protocol. However, learning is largely prevented by the so-called steganography effect, which expresses itself as watermarks in the latent segmentation domain, making image reconstruction a too easy task. To combat this, we propose a noise injection, based either on quantization noise or on Gaussian noise addition to avoid this disadvantageous information flow in the cycle architecture. We find that noise injection significantly reduces the generation of watermarks and thus allows the recognition of highly relevant classes such as "traffic signs", which are hardly detected by the ERFNet baseline. We report mIoU and PSNR results on the Cityscapes dataset for semantic segmentation and image reconstruction, respectively. The proposed methodology allows to achieve an mIoU improvement on the Cityscapes validation set of 5.7% absolute over the same CycleGAN without noise injection, and still an absolute 4.9% over the ERFNet non-cyclic baseline.
Learning Latent Representations for Image Translation using Frequency Distributed CycleGAN
Department of Information Technology, Indian Institute of Information Technology, Allahabad, U.P.（信息科技系，印度信息技术研究所，阿勒普尔，乌塔兰邦）；KTH Royal Institute of Technology（皇家理工学院）；Department of Computer Science and Engineering, Vignan University, Guntur, Andhra Pradesh（计算机科学与工程系，维加恩大学，古特尔，安得拉邦）
Bayesian Cycle-Consistent Generative Adversarial Networks via Marginalizing Latent Sampling
School of Electrical Information and Communication Engineering, Huazhong University of Science & Technology（华中科技大学电子信息与通信学院）；Microsoft AI & Research（微软人工智能与研究）；Machine Learning Department, Carnegie Mellon University（卡内基梅隆大学机器学习系）
Data-Efficient Meningioma Segmentation via Implicit Spatiotemporal Mixing and Sim2Real Semantic Injection
Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences（深圳先进技术研究所，中国科学院）；The First Affiliated Hospital of Shenzhen University（深圳大学第一附属医院）；Health Science Center（健康科学中心）；Shenzhen Second People’s Hospital（深圳第二人民医院）；Shenzhen University（深圳大学）；Department of Radiology（放射科）
Localized Latent Editing for Dose-Response Modeling in Botulinum Toxin Injection Planning
Univ. Lille, CNRS, Centrale Lille, Institut Mines-Télécom, UMR 9189 CRIStAL（里尔大学、国家科学研究中心、Centrale Lille、Institut Mines-Télécom、UMR 9189 CRIStAL）；IMT Nord Europe, Institut Mines-Télécom, Univ. Lille, Centre for Digital Systems（IMT Nord Europe、Institut Mines-Télécom、里尔大学、数字系统中心）；Lille University Hospital (CHU), Department of Plastic Surgery（里尔大学医院（CHU）、整形外科部门）；SATT Nord
ATI-VLA: Action-Centric Predictive Vision-Language-Action Models via Actionable Alignment Then Adaptive Injection
Harbin Institute of Technology, Shenzhen（哈尔滨工业大学（深圳））；Institute for Artificial Intelligence, Great Bay University（大湾区大学人工智能研究院）；Shenzhen Loop Area Institute（深圳河套学院）；Macao Polytechnic University（澳门理工大学）；Shenzhen Technology University（深圳技术大学）；Dongguan Key Laboratory for Intelligence and Information Technology（东莞市智能与信息技术重点实验室）
Few-Shot Generative Model Adaption via Identity Injection and Preservation
School of Cyberspace Security, Hangzhou Dianzi University（杭州电子科技大学网络安全学院）；Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；School of Software Engineering, Xi’an Jiaotong University（西安交通大学软件工程学院）；Lishui University and Lishui Institute of Hangzhou Dianzi University（丽水大学和杭州电子科技大学丽水研究所）；School of Faculty of Applied Science, Macao Polytechnic University（澳门理工学院应用科学学院）；School of Communication Engineering, Hangzhou Dianzi University（杭州电子科技大学通信工程学院）
One Model to Edit Them All: Free-Form Text-Driven Image Manipulation with Semantic Modulations
Tsinghua Shenzhen International Graduate School（清华大学深圳国际研究生院）；Hong Kong University of Science and Technology（香港科技大学）；Tencent AI Lab（腾讯人工智能实验室）；Huya Inc（虎牙公司）
ContextDrag: Precise Drag-Based Image Editing via Context-Preserving Token Injection and Position-Aligned Attention
School of Electronic and Information Engineering, South China University of Technology（华南理工大学电子与信息学院）；KlingAI Research, Kuaishou Technology（快手科技KlingAI研究）；The University of Hong Kong（香港大学）；Shenzhen Loop Area Institute（深圳河套学院）
A Unified Framework for Biphasic Facial Age Translation with Noisy-Semantic Guided Generative Adversarial Networks
Center for Research on Intelligent Perception And Computing, National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所模式识别国家重点实验室智能感知与计算研究中心）
