output
20122024
most citedCaptum: A unified and generic model interpretability library for PyTorch

649 citations

Showing 2016Show all

8 papers · 1 filter

cs.CV201611 cited

Improved Stereo Matching with Constant Highway Networks and Reflective Confidence Learning

Amit Shaked, Lior Wolf

We present an improved three-step pipeline for the stereo matching problem and introduce multiple novelties at each stage. We propose a new highway network architecture for computi…

cs.CV201646 cited

CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning

Justin Johnson, Bharath Hariharan, Laurens van der Maaten +3

When building artificial intelligence systems that can reason and answer questions about visual data, we need diagnostic tests to analyze our progress and discover shortcomings. Ex…

cs.CL201696 cited

Improving Neural Language Models with a Continuous Cache

Edouard Grave, Armand Joulin, Nicolas Usunier

We propose an extension to neural network language models to adapt their prediction to the recent history. Our model is a simplified version of memory augmented networks, which sto…

cs.CV2016489 cited

Semantic Segmentation using Adversarial Networks

Pauline Luc, Camille Couprie, Soumith Chintala +1

Adversarial training has been shown to produce state of the art results for generative image modeling. In this paper we propose an adversarial training approach to train semantic s…

cs.CV2016429 cited

Unsupervised Cross-Domain Image Generation

Yaniv Taigman, Adam Polyak, Lior Wolf

We study the problem of transferring a sample in one domain to an analog sample in another domain. Given two related domains, S and T, we would like to learn a generative function…

cs.AI201646 cited

Dialogue Learning With Human-In-The-Loop

Jiwei Li, Alexander H. Miller, Sumit Chopra +2

An important aspect of developing conversational agents is to give a bot the ability to improve through communicating with humans and to learn from the mistakes that it makes. Most…