6 accepted papers
The _distributional simplicity bias_ (DSB) posits that neural networks learn low-order moments of the data distribution first, before moving on to higher-order correlations. In this work, we present compelling new evidence for the DSB by showing that networks automatically learn to perform well on m…
We present a method for classifying the quality of near-contact grasps using spatial metrics that are recoverable from sensor data. Current methods often rely on calculating precise contact points, which are difficult to calculate in real life, or on tactile sensors or image data, which may be unava…
We study the problem of generating counterfactual text for a classifier as a means for understanding and debugging classification. Given a textual input and a classification model, we aim to minimally alter the text to change the model’s prediction. White-box approaches have been successfully applie…
In open set recognition, a classifier must label instances of known classes while detecting instances of unknown classes not encountered during training. To detect unknown classes while still generalizing to new instances of existing classes, we introduce a dataset augmentation technique that we cal…
Convolutional neural networks (CNNs) are powerful tools for classification of visual inputs. An important property of CNN is its restriction to local connections and sharing of local weights among different locations. In this paper, we consider the definition of appropriate local neighborhoods in CN…
Multi-instance multi-label learning (MIML) is a framework for learning in the presence of label ambiguity. In MIML, experts provide labels for groups of instances (bags), instead of directly providing a label for every instance. When labeling efforts are focused on a set of target classes, instances…