Related papers: Domain-Adaptive Pretraining Improves Primate Behav…

LiDAR place recognition approaches based on deep learning suffer from significant performance degradation when there is a shift between the distribution of training and test datasets, often requiring re-training the networks to achieve peak…

Deep learning has become the standard methodology to approach computer vision tasks when large amounts of labeled data are available. One area where traditional deep learning approaches fail to perform is one-shot learning tasks where a…

Reinforcement learning provides a general framework for flexible decision making and control, but requires extensive data collection for each new task that an agent needs to learn. In other machine learning fields, such as natural language…

We propose a scheme for supervised image classification that uses privileged information, in the form of keypoint annotations for the training data, to learn strong models from small and/or biased training sets. Our main motivation is the…

In this work, we tackle the problem of unsupervised domain adaptation (UDA) for video action recognition. Our approach, which we call UNITE, uses an image teacher model to adapt a video student model to the target domain. UNITE first…

We introduce ADEPT: Adaptive Data ExPloiTation, a simple yet powerful framework to enhance the **data efficiency** and **generalization** in deep reinforcement learning (RL). Specifically, ADEPT adaptively manages the use of sampled data…

State-of-the-art computer vision models are mostly trained with supervised learning using human-labeled images, which limits their scalability due to the expensive annotation cost. While self-supervised representation learning has achieved…

Unsupervised Domain Adaptive Object Detection (UDA-OD) uses unlabelled data to improve the reliability of robotic vision systems in open-world environments. Previous approaches to UDA-OD based on self-training have been effective in…

Most deep-learning frameworks for understanding biological swarms are designed to fit perceptive models of group behavior to individual-level data (e.g., spatial coordinates of identified features of individuals) that have been separately…

One of the key limitations of Molecular Dynamics simulations is the computational intractability of sampling protein conformational landscapes associated with either large system size or long timescales. To overcome this bottleneck, we…

Recently, large vision and language models have shown their success when adapting them to many downstream tasks. In this paper, we present a unified framework named CLIP-ADA for Anomaly Detection by Adapting a pre-trained CLIP model. To…

The goal of this paper is to self-train a 3D convolutional neural network on an unlabeled video collection for deployment on small-scale video collections. As smaller video datasets benefit more from motion than appearance, we strive to…

Language models pretrained on text from a wide variety of sources form the foundation of today's NLP. In light of the success of these broad-coverage models, we investigate whether it is still helpful to tailor a pretrained model to the…

While self-supervised pretraining has proven beneficial for many computer vision tasks, it requires expensive and lengthy computation, large amounts of data, and is sensitive to data augmentation. Prior work demonstrates that models…

Visual object recognition -- the behavioral ability to rapidly and accurately categorize many visually encountered objects -- is core to primate cognition. This behavioral capability is algorithmically impressive because of the myriad…

Data-driven techniques for machine vision heavily depend on the training data to sufficiently resemble the data occurring during test and application. However, in practice unknown distortion can lead to a domain gap between training and…

This paper presents Dual Action Policy (DAP), a novel approach to address the dynamics mismatch inherent in the sim-to-real gap of reinforcement learning. DAP uses a single policy to predict two sets of actions: one for maximizing task…

In the context of supervised statistical learning, it is typically assumed that the training set comes from the same distribution that draws the test samples. When this is not the case, the behavior of the learned model is unpredictable and…

While pose estimation is an important computer vision task, it requires expensive annotation and suffers from domain shift. In this paper, we investigate the problem of domain adaptive 2D pose estimation that transfers knowledge learned on…

We propose the use of self-supervised learning for human activity recognition with smartphone accelerometer data. Our proposed solution consists of two steps. First, the representations of unlabeled input signals are learned by training a…