Search Results for author:
Found 7 papers, 3 papers with code
Stylist: Style-Driven Feature Ranking for Robust Novelty Detection
Similar to works in out-of-distribution generalization, we propose to use the formalization of separating into semantic or content changes, that are relevant to our task, and style changes, that are irrelevant.
Environment-biased Feature Ranking for Novelty Detection Robustness
Thus, we propose a method that starts with a pretrained embedding and a multi-env setup and manages to rank the features based on their environment-focus.
Learning Diverse Features in Vision Transformers for Improved Generalization
We observe improved out-of-distribution performance on diagnostic benchmarks (MNIST-CIFAR, Waterbirds) as a consequence of the enhanced diversity of features and the pruning of undesirable heads.
Spuriosity Didn't Kill the Classifier: Using Invariant Predictions to Harness Spurious Features
To avoid failures on out-of-distribution data, recent works have sought to extract features that have an invariant or stable relationship with the label across domains, discarding "spurious" or unstable features whose relationship with the label changes across domains.
Env-Aware Anomaly Detection: Ignore Style Changes, Stay True to Content!
We introduce a formalization and benchmark for the unsupervised anomaly detection task in the distribution-shift scenario.
DCI-ES: An Extended Disentanglement Framework with Connections to Identifiability
In representation learning, a common approach is to seek representations which disentangle the underlying factors of variation.
Mining for meaning: from vision to language through multiple networks consensus
Here we propose an approach to describe videos in natural language by reaching a consensus among multiple encoder-decoder networks.
