REVIEW 5 cited by
Spatial Broadcast Decoder: A Simple Architecture for Learning Disentangled Representations in VAEs
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Spatial Broadcast Decoder: A Simple Architecture for Learning Disentangled Representations in VAEs
read the original abstract
We present a simple neural rendering architecture that helps variational autoencoders (VAEs) learn disentangled representations. Instead of the deconvolutional network typically used in the decoder of VAEs, we tile (broadcast) the latent vector across space, concatenate fixed X- and Y-"coordinate" channels, and apply a fully convolutional network with 1x1 stride. This provides an architectural prior for dissociating positional from non-positional features in the latent distribution of VAEs, yet without providing any explicit supervision to this effect. We show that this architecture, which we term the Spatial Broadcast decoder, improves disentangling, reconstruction accuracy, and generalization to held-out regions in data space. It provides a particularly dramatic benefit when applied to datasets with small objects. We also emphasize a method for visualizing learned latent spaces that helped us diagnose our models and may prove useful for others aiming to assess data representations. Finally, we show the Spatial Broadcast Decoder is complementary to state-of-the-art (SOTA) disentangling techniques and when incorporated improves their performance.
Forward citations
Cited by 5 Pith papers
-
Loki: Representation over Architecture for Diffusion-Based Portrait Animation
Loki replaces RGB conditioning stacks with identity-orthogonal parametric face encodings rasterized for diffusion, achieving efficient cross-ID portrait animation without cross-ID training data.
-
Learning Visually Interpretable Oscillator Networks for Soft Continuum Robots from Video
ABCD and VONs enable visually and mechanically interpretable latent dynamics learning for soft robots from video, with reported multi-step prediction gains of 5.8x and 3.5x on two-segment cases.
-
Rethinking Object-Centric Representations for Video Dynamics Modeling
STAITUS disentangles appearance from pose in video slots, enforces spatial separation and appearance-only temporal alignment, and adds adaptive gating to improve segmentation and identity persistence.
-
Slot-MPC: Goal-Conditioned Model Predictive Control with Object-Centric Representations
Slot-MPC learns slot representations to build a differentiable object-centric dynamics model that supports efficient gradient-based MPC for robotic manipulation in novel situations.
-
Information theoretic underpinning of self-supervised learning by clustering
SSL clustering is derived as KL-divergence optimization where a teacher-distribution constraint normalizes via inverse cluster priors and simplifies to batch centering by Jensen's inequality.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.