Search Results for author:
Found 13 papers, 3 papers with code
Causal Scene BERT: Improving object detection by searching for challenging groups of data
Our main contribution is a pseudo-automatic method to discover such groups in foresight by performing causal interventions on simulated scenes.
Causal Scene BERT: Improving object detection by searching for challenging groups
We verify that the prioritized groups found via intervention are challenging for the object detector and show that retraining with data collected from these groups helps inordinately compared to adding more IID data.
Self-Supervised Equivariant Scene Synthesis from Video
We propose a self-supervised framework to learn scene representations from video that are automatically delineated into background, characters, and their animations.
Ridge Rider: Finding Diverse Solutions by Following Eigenvectors of the Hessian
In the era of ever decreasing loss functions, SGD and its various offspring have become the go-to optimization tool in machine learning and are a key component of the success of deep neural networks (DNNs).
Learned Equivariant Rendering without Transformation Supervision
We propose a self-supervised framework to learn scene representations from video that are automatically delineated into objects and background.
In-Distribution Interpretability for Challenging Modalities
It is widely recognized that the predictions of deep neural networks are difficult to parse relative to simpler approaches.
Compositionality and Capacity in Emergent Languages
Our hypothesis is that there should be a specific range of model capacity and channel bandwidth that induces compositional structure in the resulting language and consequently encourages systematic generalization.
Probing the State of the Art: A Critical Look at Visual Representation Evaluation
Our first contribution is to show that this test is insufficient and that models which perform poorly (strongly) on linear classification can perform strongly (weakly) on more involved tasks like temporal activity localization.
Capacity, Bandwidth, and Compositionality in Emergent Language Learning
In this paper, we investigate the learning biases that affect the efficacy and compositionality of emergent languages.
Backplay: 'Man muss immer umkehren'
Our contributions are that we analytically characterize the types of environments where Backplay can improve training speed, demonstrate the effectiveness of Backplay both in large grid worlds and a complex four player zero-sum game (Pommerman), and show that Backplay compares favorably to other competitive methods known to improve sample efficiency.
Backplay: "Man muss immer umkehren"
Our contributions are that we analytically characterize the types of environments where Backplay can improve training speed, demonstrate the effectiveness of Backplay both in large grid worlds and a complex four player zero-sum game (Pommerman), and show that Backplay compares favorably to other competitive methods known to improve sample efficiency.
Vehicle Communication Strategies for Simulated Highway Driving
Interest in emergent communication has recently surged in Machine Learning.
Neural Audio Synthesis of Musical Notes with WaveNet Autoencoders
Generative models in vision have seen rapid progress due to algorithmic improvements and the availability of high-quality image datasets.
