Encouraging Disentangled and Convex Representation with Controllable Interpolation Regularization

Yunhao Ge, Zhi Xu, Yao Xiao, Gan Xin, Yunkui Pang, Laurent Itti

Abstract:

We focus on controllable disentangled representation learning (C-Dis-RL), where users can control the partition of the disentangled latent space to factorize dataset attributes (concepts) for downstream tasks. Two general problems remain underexplored in current methods: (1) They lack comprehensive disentanglement constraints, especially missing the minimization of mutual information between different attributes across latent and observation domains. (2) They lack convexity constraints in disentangled latent space, which is important for meaningfully manipulating specific attributes for downstream tasks. To encourage both comprehensive C-Dis-RL and convexity simultaneously, we propose a simple yet efficient method: Controllable Interpolation Regularization (CIR), which creates a positive loop
where the disentanglement and convexity can help each other. Specifically, we conduct controlled interpolation in latent space during training and ’reuse’ the encoder to help form a ’perfect disentanglement’ regularization. In that case, (a) disentanglement loss implicitly enlarges the potential ’understandable’ distribution to encourage convexity; (b) convexity can in turn improve robust and precise disentanglement. CIR is a general module and we merge CIR with three different algorithms: ELEGANT, I2I-Dis, and GZS-Net to show the compatibility and effectiveness. Qualitative and quantitative experiments show improvement in C-Dis-RL and latent convexity by CIR. This further improves downstream tasks: controllable image synthesis, cross-modality image translation and zero-shot synthesis. More
experiments demonstrate CIR can also improve other downstream tasks, such as new attribute value mining, data augmentation, and eliminating bias for fairness.

One-sentence Summary: We propose a simple yet efficient method: Controllable Interpolation Regularization (CIR), which creates a positive loop where the disentanglement and convexity can help each other.