Active

Video Representation Learning for Global and Local Features

This ongoing project attempts to use self-supervised learning to learn video representation that are both useful for coarser tasks involving global informationand finer-grained tasks involving local information.

Researchers Franklin Wang, UC Berkeley Avideh Zakhor, UC Berkeley Yale Song, Microsoft Du Tran, Facebook Aravind Kalaiah, Facebook Overview

Self-supervised video representation learning provides new opportunities to computer vision: It can take full advantage of the wealth of unlabeled video data available, and when successful, it can improve...

Personalized federated learning: new algorithms and statistical rates,

Background: Federated Learning (FL) has emerged as a powerful paradigm for distributed, privacy-preserving machine learning over a large network of devices [1]. Most existing works on FL focus on learning a single model that is deployed to all devices. Given the diverse characteristics of the users and application scenarios, personalization is highly desirable and inevitable in the near future. Personalized Federated Learning (PFL) aims to improve the experience of individual users by training personalized on-device models that overcome the limitations of a common...

Reinforcement Learning in High Dimensional Systems

The goal of this collaboration is to explore the limits and possibilities of sequential decision making in complex, high-dimensional environments. Compared with more classical settings such as supervised learning, relatively little is known regarding the minimal assumptions, representational conditions, and algorithmic principles needed to enable sample-efficient learning in complex control systems with rich sets of actions and observations. Given recent empirical breakthroughs in robotics and game playing (...

Learning Selective Invariance Upon Parametric Density Functions of Transformations

Researchers Utkarsh Singhal (s.utkarsh@berkeley.edu) Stella Yu (stellayu@berkeley.edu) Ameesh Makadia (makadia@google.com) Carlos Esteves (machc@google.com) Overview

Symmetry is a powerful tool in the deep learning repertoire. Natural data displays structured variations due to naturally occurring symmetries, so modeling these symmetries greatly...

Robust Image Classification via Parts and Disentangled Attributes

Robustness is steadily becoming a real concern for machine learning models, especially when deployed in security or safety-critical settings. Significant research has demonstrated the fragility of neural networks when the i.i.d. assumption does not hold, e.g., natural corruptions and adversarial perturbation. Many application domains...

Realistic Large-Scale Benchmark for Adversarial Patch

Problem

The goal of our study is to make machine learning models robust against patch attacks. In particular, we will develop the first standardized benchmark for security against patch attacks, under realistic threat models. Our benchmark will cover two important aspects often ignored in past work: (1) realistic patches that must work under...

Self Supervised Semantic Segmentation in the Wild

Overview

Self-supervised learning (SSL) enables the learning of effective task-agnostic representations that generalize to a wide range of downstream applications. Recent advances in SSL have adopted strong augmentation pipelines combined with pretext tasks to achieve results competitive with supervised learning while using a fraction of the labels. The goal of this project is to transfer the success of SSL to real-world applications. SSL in the wild specifically aims to tackle semantic segmentation where pixel-level annotation can be hard and time-consuming for humans....

Learning Safety-Assured Collaborative Quadrupedal Manipulation

Collaboration is very common in animals, ranging from flocks of wolves to packs of bees. For instance, a team of ants can cooperatively carry heavy loads to their nest. Drawing inspiration from collaborative teamwork in nature, robots can also work together to achieve tasks that are beyond the ability of individual robots. However, this is challenging in several...

Pre-trained Representations for Language-Guided Web Navigation

Overview

Personal assistants that interact with open-domain websites can assist humans with arbitrary tasks, such as booking flights or searching for information. Language-guided assistants can be a natural interface for users, enabling assistive technologies, browser automation tools, and web navigation in situations where people cannot use standard interfaces (e.g., while cooking or while browsing a website in an unfamiliar language).

Most existing web navigation assistants rely on text-only pretrained representations, which do not take advantage of structural information in web...

Learning-Driven Exploration For Search

Kevin Yang, Tianjun Zhang, Yuandong Tian, Dan Klein

Summary

Search/path planning is an important topic with applications to a variety of other domains, e.g., RL, robotics, chemistry, compiler optimization. However, random search is too inefficient for many applications. Classic global approaches such as Bayesian Optimization may struggle with high-dimensional spaces and smaller numbers of samples. Local approaches such as CEM and CMA-ES may struggle to escape local optima. We propose to explore and partition the search...