A conditional surrogate loss that always picks the gradient estimate aligned with the reconstruction loss improves flow autoencoder training and reaches state-of-the-art generative performance on molecules, tabular data, and images.
HindSight: A Graph-Based Vision Model Architecture For Representing Part-Whole Hierarchies
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
This paper presents a model architecture for encoding the representations of part-whole hierarchies in images in form of a graph. The idea is to divide the image into patches of different levels and then treat all of these patches as nodes for a fully connected graph. A dynamic feature extraction module is used to extract feature representations from these patches in each graph iteration. This enables us to learn a rich graph representation of the image that encompasses the inherent part-whole hierarchical information. Utilizing proper self-supervised training techniques, such a model can be trained as a general purpose vision encoder model which can then be used for various vision related downstream tasks (e.g., Image Classification, Object Detection, Image Captioning, etc.).
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
NAE: Normalizing AutoEncoder
A conditional surrogate loss that always picks the gradient estimate aligned with the reconstruction loss improves flow autoencoder training and reaches state-of-the-art generative performance on molecules, tabular data, and images.