Search Results for author: Tongzhou Wang

Found 20 papers, 15 papers with code

The Platonic Representation Hypothesis

1 code implementation13 May 2024 Minyoung Huh, Brian Cheung, Tongzhou Wang, Phillip Isola

We argue that representations in AI models, particularly deep networks, are converging.

Optimal Goal-Reaching Reinforcement Learning via Quasimetric Learning

1 code implementation3 Apr 2023 Tongzhou Wang, Antonio Torralba, Phillip Isola, Amy Zhang

In goal-reaching reinforcement learning (RL), the optimal value function has a particular geometry, called quasimetric structure.

reinforcement-learning Reinforcement Learning (RL)

Deep Augmentation: Self-Supervised Learning with Transformations in Activation Space

no code implementations25 Mar 2023 Rickard Brüel-Gabrielsson, Tongzhou Wang, Manel Baradad, Justin Solomon

We use this observation to formulate a method for selecting which layer to target; in particular, our experimentation reveals that targeting deeper layers with Deep Augmentation outperforms augmenting the input data.

Contrastive Learning Data Augmentation +2

Steerable Equivariant Representation Learning

no code implementations22 Feb 2023 Sangnie Bhardwaj, Willie McClinton, Tongzhou Wang, Guillaume Lajoie, Chen Sun, Phillip Isola, Dilip Krishnan

In this paper, we propose a method of learning representations that are instead equivariant to data augmentations.

Image Retrieval object-detection +5

Procedural Image Programs for Representation Learning

1 code implementation29 Nov 2022 Manel Baradad, Chun-Fu Chen, Jonas Wulff, Tongzhou Wang, Rogerio Feris, Antonio Torralba, Phillip Isola

Learning image representations using synthetic data allows training neural networks without some of the concerns associated with real images, such as privacy and bias.

Representation Learning

Improved Representation of Asymmetrical Distances with Interval Quasimetric Embeddings

1 code implementation28 Nov 2022 Tongzhou Wang, Phillip Isola

Asymmetrical distance structures (quasimetrics) are ubiquitous in our lives and are gaining more attention in machine learning applications.

reinforcement-learning Reinforcement Learning (RL)

Totems: Physical Objects for Verifying Visual Integrity

no code implementations26 Sep 2022 Jingwei Ma, Lucy Chai, Minyoung Huh, Tongzhou Wang, Ser-Nam Lim, Phillip Isola, Antonio Torralba

We introduce a new approach to image forensics: placing physical refractive objects, which we call totems, into a scene so as to protect any photograph taken of that scene.

Image Forensics

On the Learning and Learnability of Quasimetrics

2 code implementations30 Jun 2022 Tongzhou Wang, Phillip Isola

In contrast, our proposed Poisson Quasimetric Embedding (PQE) is the first quasimetric learning formulation that both is learnable with gradient-based optimization and enjoys strong performance guarantees.

Q-Learning Reinforcement Learning (RL)

Dataset Distillation by Matching Training Trajectories

5 code implementations CVPR 2022 George Cazenavette, Tongzhou Wang, Antonio Torralba, Alexei A. Efros, Jun-Yan Zhu

To efficiently obtain the initial and target network parameters for large-scale datasets, we pre-compute and store training trajectories of expert networks trained on the real dataset.

Dataset Distillation - 1IPC

Learning to See by Looking at Noise

1 code implementation NeurIPS 2021 Manel Baradad, Jonas Wulff, Tongzhou Wang, Phillip Isola, Antonio Torralba

We investigate a suite of image generation models that produce images from simple random processes.

Image Generation

Rewriting a Deep Generative Model

3 code implementations ECCV 2020 David Bau, Steven Liu, Tongzhou Wang, Jun-Yan Zhu, Antonio Torralba

To address the problem, we propose a formulation in which the desired rule is changed by manipulating a layer of a deep network as a linear associative memory.

Dataset Distillation

5 code implementations27 Nov 2018 Tongzhou Wang, Jun-Yan Zhu, Antonio Torralba, Alexei A. Efros

Model distillation aims to distill the knowledge of a complex model into a simpler one.

Meta-Learning MCMC Proposals

no code implementations NeurIPS 2018 Tongzhou Wang, Yi Wu, David A. Moore, Stuart J. Russell

The learned neural proposals generalize to occurrences of common structural motifs across different models, allowing for the construction of a library of learned inference primitives that can accelerate inference on unseen models with no model-specific training required.

Meta-Learning named-entity-recognition +2

Learning to Synthesize a 4D RGBD Light Field from a Single Image

1 code implementation ICCV 2017 Pratul P. Srinivasan, Tongzhou Wang, Ashwin Sreelal, Ravi Ramamoorthi, Ren Ng

We present a machine learning algorithm that takes as input a 2D RGB image and synthesizes a 4D RGBD light field (color and depth of the scene in each ray direction).

Depth Estimation

Cannot find the paper you are looking for? You can Submit a new open access paper.