Search Results for author: Alexander C. Li

Found 8 papers, 5 papers with code

Diffusion-TTA: Test-time Adaptation of Discriminative Models via Generative Feedback

1 code implementation27 Nov 2023 Mihir Prabhudesai, Tsung-Wei Ke, Alexander C. Li, Deepak Pathak, Katerina Fragkiadaki

Our method, Diffusion-TTA, adapts pre-trained discriminative models such as image classifiers, segmenters and depth predictors, to each unlabelled example in the test set using generative feedback from a diffusion model.

Test-time Adaptation

Your Diffusion Model is Secretly a Zero-Shot Classifier

2 code implementations ICCV 2023 Alexander C. Li, Mihir Prabhudesai, Shivam Duggal, Ellis Brown, Deepak Pathak

Our generative approach to classification, which we call Diffusion Classifier, attains strong results on a variety of benchmarks and outperforms alternative methods of extracting knowledge from diffusion models.

Domain Generalization Fine-Grained Image Classification +5

Internet Explorer: Targeted Representation Learning on the Open Web

1 code implementation27 Feb 2023 Alexander C. Li, Ellis Brown, Alexei A. Efros, Deepak Pathak

Modern vision models typically rely on fine-tuning general-purpose models pre-trained on large, static datasets.

Classification Representation Learning +1

Understanding Collapse in Non-Contrastive Siamese Representation Learning

1 code implementation29 Sep 2022 Alexander C. Li, Alexei A. Efros, Deepak Pathak

We empirically analyze these non-contrastive methods and find that SimSiam is extraordinarily sensitive to dataset and model size.

Continual Learning Contrastive Learning +1

Functional Regularization for Reinforcement Learning via Learned Fourier Features

1 code implementation NeurIPS 2021 Alexander C. Li, Deepak Pathak

We propose a simple architecture for deep reinforcement learning by embedding inputs into a learned Fourier basis and show that it improves the sample efficiency of both state-based and image-based RL.

reinforcement-learning Reinforcement Learning (RL)

Generalized Hindsight for Reinforcement Learning

no code implementations NeurIPS 2020 Alexander C. Li, Lerrel Pinto, Pieter Abbeel

Compared to standard relabeling techniques, Generalized Hindsight provides a substantially more efficient reuse of samples, which we empirically demonstrate on a suite of multi-task navigation and manipulation tasks.

reinforcement-learning Reinforcement Learning (RL)

Autoregressive Models: What Are They Good For?

no code implementations17 Oct 2019 Murtaza Dalal, Alexander C. Li, Rohan Taori

Autoregressive (AR) models have become a popular tool for unsupervised learning, achieving state-of-the-art log likelihood estimates.

Translation

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