CapsGAN: Using Dynamic Routing for Generative Adversarial Networks
In this paper, we propose a novel technique for generating images in the 3D domain from images with high degree of geometrical transformations. By coalescing two popular concurrent methods that have seen rapid ascension to the machine learning zeitgeist in recent years: GANs (Goodfellow et. al.) and Capsule networks (Sabour, Hinton et. al.) - we present: \textbf{CapsGAN}. We show that CapsGAN performs better than or equal to traditional CNN based GANs in generating images with high geometric transformations using rotated MNIST. In the process, we also show the efficacy of using capsules architecture in the GANs domain. Furthermore, we tackle the Gordian Knot in training GANs - the performance control and training stability by experimenting with using Wasserstein distance (gradient clipping, penalty) and Spectral Normalization. The experimental findings of this paper should propel the application of capsules and GANs in the still exciting and nascent domain of 3D image generation, and plausibly video (frame) generation.
Code (1)
Tasks
Image GenerationRotated MNISTMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
OD-DEAL: Dynamic Expert-Guided Adversarial Learning with Online Decomposition for Scalable Capacitated Vehicle Routing
Solving large-scale capacitated vehicle routing problems (CVRP) is hindered by the high complexity of heuristics and the limited generalization of neural solvers on massive graphs. We propose OD-DEAL, an adversarial lear…
Knowledge DistillationPainting on Placement: Forecasting Routing Congestion using Conditional Generative Adversarial Nets
Physical design process commonly consumes hours to days for large designs, and routing is known as the most critical step. Demands for accurate routing quality prediction raise to a new level to accelerate hardware innov…
ColorizationTranslationRoute to Rome Attack: Directing LLM Routers to Expensive Models via Adversarial Suffix Optimization
Cost-aware routing dynamically dispatches user queries to models of varying capability to balance performance and inference cost. However, the routing strategy introduces a new security concern that adversaries may manip…
Training capsules as a routing-weighted product of expert neurons
Capsules are the multidimensional analogue to scalar neurons in neural networks, and because they are multidimensional, much more complex routing schemes can be used to pass information forward through the network than w…
C-DIRA: Computationally Efficient Dynamic ROI Routing and Domain-Invariant Adversarial Learning for Lightweight Driver Behavior Recognition
Driver distraction behavior recognition using in-vehicle cameras demands real-time inference on edge devices. However, lightweight models often fail to capture fine-grained behavioral cues, resulting in reduced performan…