Search Results for author:
Found 11 papers, 7 papers with code
Binding Dynamics in Rotating Features
In human cognition, the binding problem describes the open question of how the brain flexibly integrates diverse information into cohesive object representations.
Image segmentation with traveling waves in an exactly solvable recurrent neural network
We study image segmentation using spatiotemporal dynamics in a recurrent neural network where the state of each unit is given by a complex number.
BISCUIT: Causal Representation Learning from Binary Interactions
Identifying the causal variables of an environment and how to intervene on them is of core value in applications such as robotics and embodied AI.
Causal Representation Learning for Instantaneous and Temporal Effects in Interactive Systems
To address this issue, we propose iCITRIS, a causal representation learning method that allows for instantaneous effects in intervened temporal sequences when intervention targets can be observed, e. g., as actions of an agent.
Complex-Valued Autoencoders for Object Discovery
Object-centric representations form the basis of human perception, and enable us to reason about the world and to systematically generalize to new settings.
CITRIS: Causal Identifiability from Temporal Intervened Sequences
Understanding the latent causal factors of a dynamical system from visual observations is considered a crucial step towards agents reasoning in complex environments.
Contrastive Predictive Coding for Anomaly Detection
However, while most existing contrastive anomaly detection and segmentation approaches have been applied to images, none of them can use the contrastive losses directly for both anomaly detection and segmentation.
Learning Object-Centric Video Models by Contrasting Sets
We address this problem by introducing a global, set-based contrastive loss: instead of contrasting individual slot representations against one another, we aggregate the representations and contrast the joined sets against one another.
Amortized Causal Discovery: Learning to Infer Causal Graphs from Time-Series Data
This enables us to train a single, amortized model that infers causal relations across samples with different underlying causal graphs, and thus leverages the shared dynamics information.
Putting An End to End-to-End: Gradient-Isolated Learning of Representations
We propose a novel deep learning method for local self-supervised representation learning that does not require labels nor end-to-end backpropagation but exploits the natural order in data instead.
Ranked #60 on
Image Classification
on STL-10
Representation Learning
Self-Supervised Audio Classification
+2
Improving Unsupervised Defect Segmentation by Applying Structural Similarity to Autoencoders
Convolutional autoencoders have emerged as popular methods for unsupervised defect segmentation on image data.
