Salesforce.com

About: Salesforce.com is a based out in . It is known for research contribution in the topics: User interface & Object (computer science). The organization has 2418 authors who have published 2775 publications receiving 63956 citations.

CASTing Your Model: Learning to Localize Improves Self-Supervised Representations

Abstract: Recent advances in self-supervised learning (SSL) have largely closed the gap with supervised ImageNet pretraining. Despite their success these methods have been primarily applied to unlabeled ImageNet images, and show marginal gains when trained on larger sets of uncurated images. We hypothesize that current SSL methods perform best on iconic images, and struggle on complex scene images with many objects. Analyzing contrastive SSL methods shows that they have poor visual grounding and receive poor supervisory signal when trained on scene images. We propose Contrastive Attention-Supervised Tuning(CAST) to overcome these limitations. CAST uses unsupervised saliency maps to intelligently sample crops, and to provide grounding supervision via a Grad-CAM attention loss. Experiments on COCO show that CAST significantly improves the features learned by SSL methods on scene images, and further experiments show that CAST-trained models are more robust to changes in backgrounds.

System, method and computer program product for displaying data utilizing a selected source and visualization

Abstract: In accordance with embodiments, there are provided mechanisms and methods for displaying data utilizing a selected source and visualization. These mechanisms and methods for displaying data utilizing a selected source and visualization can enable enhanced data display, improved data display development, increased time savings, etc.

Explain Yourself! Leveraging Language Models for Commonsense Reasoning

Abstract: Deep learning models perform poorly on tasks that require commonsense reasoning, which often necessitates some form of world-knowledge or reasoning over information not immediately present in the input. We collect human explanations for commonsense reasoning in the form of natural language sequences and highlighted annotations in a new dataset called Common Sense Explanations (CoS-E). We use CoS-E to train language models to automatically generate explanations that can be used during training and inference in a novel Commonsense Auto-Generated Explanation (CAGE) framework. CAGE improves the state-of-the-art by 10% on the challenging CommonsenseQA task. We further study commonsense reasoning in DNNs using both human and auto-generated explanations including transfer to out-of-domain tasks. Empirical results indicate that we can effectively leverage language models for commonsense reasoning.

Automating sharing data between users of a multi-tenant database service

Abstract: Systems, methods, and apparatus for automating sharing data between subscribers of a multi-tenant database service. Users or customers associated with one organization that is a tenant of the multi-tenant database system are enabled to share data objects such as leads, opportunities, accounts, contacts, cases, tasks and custom objects, (or other data objects) and other information with their business partners (e.g., users or customers associated with a different organization that is a tenant) and get real-time updates on the shared data.

Keeping Your Distance: Solving Sparse Reward Tasks Using Self-Balancing Shaped Rewards

Abstract: While using shaped rewards can be beneficial when solving sparse reward tasks, their successful application often requires careful engineering and is problem specific. For instance, in tasks where the agent must achieve some goal state, simple distance-to-goal reward shaping often fails, as it renders learning vulnerable to local optima. We introduce a simple and effective model-free method to learn from shaped distance-to-goal rewards on tasks where success depends on reaching a goal state. Our method introduces an auxiliary distance-based reward based on pairs of rollouts to encourage diverse exploration. This approach effectively prevents learning dynamics from stabilizing around local optima induced by the naive distance-to-goal reward shaping and enables policies to efficiently solve sparse reward tasks. Our augmented objective does not require any additional reward engineering or domain expertise to implement and converges to the original sparse objective as the agent learns to solve the task. We demonstrate that our method successfully solves a variety of hard-exploration tasks (including maze navigation and 3D construction in a Minecraft environment), where naive distance-based reward shaping otherwise fails, and intrinsic curiosity and reward relabeling strategies exhibit poor performance.