DualDis: Dual-Branch Disentangling with Adversarial Learning
In computer vision, disentangling techniques aim at improving latent representations of images by modeling factors of variation. In this paper, we propose DualDis, a new auto-encoder-based framework that disentangles and linearizes class and attribute information. This is achieved thanks to a two-branch architecture forcing the separation of the two kinds of information, accompanied by a decoder for image reconstruction and generation. To effectively separate the information, we propose to use a combination of regular and adversarial classifiers to guide the two branches in specializing for class and attribute information respectively. We also investigate the possibility of using semi-supervised learning for an effective disentangling even using few labels. We leverage the linearization property of the latent spaces for semantic image editing and generation of new images. We validate our approach on CelebA, Yale-B and NORB by measuring the efficiency of information separation via classification metrics, visual image manipulation and data augmentation.
Code (1)
Tasks
AttributeData AugmentationDecoderImage ManipulationImage ReconstructionSimilar Papers 제목 키워드 기반
Towards Understanding Dual BN In Hybrid Adversarial Training
There is a growing concern about applying batch normalization (BN) in adversarial training (AT), especially when the model is trained on both adversarial samples and clean samples (termed Hybrid-AT). With the assumption …
Agentic-R1: Distilled Dual-Strategy Reasoning
Current long chain-of-thought (long-CoT) models excel at mathematical reasoning but rely on slow and error-prone natural language traces. Tool-augmented agents address arithmetic via code execution, but often falter on c…
Mathematical ReasoningTowards Cross-Subject EMG Pattern Recognition via Dual-Branch Adversarial Feature Disentanglement
Cross-subject electromyography (EMG) pattern recognition faces significant challenges due to inter-subject variability in muscle anatomy, electrode placement, and signal characteristics. Traditional methods rely on subje…
AnatomyDisentanglementElectromyography (EMG)Learning Disentangling and Fusing Networks for Face Completion Under Structured Occlusions
Face completion aims to generate semantically new pixels for missing facial components. It is a challenging generative task due to large variations of face appearance. This paper studies generative face completion under …
DecoderFacial InpaintingGenerative Adversarial NetworkBodyGAN: General-Purpose Controllable Neural Human Body Generation
Recent advances in generative adversarial networks (GANs) have provided potential solutions for photorealistic human image synthesis. However, the explicit and individual control of synthesis over multiple factors, s…
DisentanglementImage GenerationSemantic Segmentation