We propose C-SFDA, a curriculum learning aided self-training framework for SFDA that adapts efficiently and reliably to changes across domains based on selective pseudo-labeling. Specifically, we employ a curriculum learning scheme to promote learning from a restricted amount of pseudo labels selected based on their reliabilities.
Machine learning publications
Night-Time GPS-Denied Navigation and Situational Understanding Using Vision-Enhanced Low-Light Imager
In this presentation, we describe and demonstrate a novel vision-enhanced low-light imager system to provide GPS-denied navigation and ML-based visual scene understanding capabilities for both day and night operations.
Cross-View Visual Geo-Localization for Outdoor Augmented Reality
We address the problem of geo-pose estimation by cross-view matching of query ground images to a geo-referenced aerial satellite image database. Recently, neural network-based methods have shown state-of-the-art performance in cross-view matching.
Sensor Control for Information Gain in Dynamic, Sparse and Partially Observed Environments
We present an approach for autonomous sensor control for information gathering under partially observable, dynamic and sparsely sampled environments.
Unpacking Large Language Models with Conceptual Consistency
We propose conceptual consistency to measure a LLM’s understanding of relevant concepts. This novel metric measures how well a model can be characterized by finding out how consistent its responses to queries about conceptually relevant background knowledge are.
Incremental Learning with Differentiable Architecture and Forgetting Search
In this paper, we show that leveraging NAS for incremental learning results in strong performance gains for classification tasks.
Dual-Key Multimodal Backdoors for Visual Question Answering
In this work, we show that multimodal networks are vulnerable to a novel type of attack that we refer to as Dual-Key Multimodal Backdoors.
Saccade Mechanisms for Image Classification, Object Detection and Tracking
We examine how the saccade mechanism from biological vision can be used to make deep neural networks more efficient for classification and object detection problems.
Conformal Prediction Intervals for Markov Decision Process Trajectories
This paper extends previous work on conformal prediction for functional data and conformalized quantile regression to provide conformal prediction intervals over the future behavior of an autonomous system executing a fixed control policy on a Markov Decision Process.