Related papers: Bi-level Alignment for Cross-Domain Crowd Counting

We describe a method for selecting relevant new training data for the LSTM-based domain selection component of our personal assistant system. Adding more annotated training data for any ML system typically improves accuracy, but only if it…

The crowd counting task aims at estimating the number of people located in an image or a frame from videos. Existing methods widely adopt density maps as the training targets to optimize the point-to-point loss. While in testing phase, we…

Annotation through crowdsourcing draws incremental attention, which relies on an effective selection scheme given a pool of workers. Existing methods propose to select workers based on their performance on tasks with ground truth, while two…

In this work, we address the problem of unsupervised domain adaptation for person re-ID where annotations are available for the source domain but not for target. Previous methods typically follow a two-stage optimization pipeline, where the…

Multi-Task Learning (MTL) aims to enhance the model generalization by sharing representations between related tasks for better performance. Typical MTL methods are jointly trained with the complete multitude of ground-truths for all tasks…

The composition of training data mixtures is critical for effectively training large language models (LLMs), as it directly impacts their performance on downstream tasks. Our goal is to identify an optimal data mixture to specialize an LLM…

As the size of the datasets getting larger, accurately annotating such datasets is becoming more impractical due to the expensiveness on both time and economy. Therefore, crowd-sourcing has been widely adopted to alleviate the cost of…

Recently the crowd counting has received more and more attention. Especially the technology of high-density environment has become an important research content, and the relevant methods for the existence of extremely dense crowd are not…

Large-scale Multi-Agent Reinforcement Learning (MARL) often suffers from the curse of dimensionality, as the exponential growth in agent interactions significantly increases computational complexity and impedes learning efficiency. To…

Domain adaptation is pivotal for enabling deep learning models to generalize across diverse domains, a task complicated by variations in presentation and cognitive nuances. In this paper, we introduce AD-Aligning, a novel approach that…

We introduce an unsupervised domain adaption (UDA) strategy that combines multiple image translations, ensemble learning and self-supervised learning in one coherent approach. We focus on one of the standard tasks of UDA in which a semantic…

Human-annotated data plays a critical role in the fairness of AI systems, including those that deal with life-altering decisions or moderating human-created web/social media content. Conventionally, annotator disagreements are resolved…

Domain adaptation aims to exploit the knowledge in source domain to promote the learning tasks in target domain, which plays a critical role in real-world applications. Recently, lots of deep learning approaches based on autoencoders have…

In this work, we tackle the problem of online adaptation for stereo depth estimation, that consists in continuously adapting a deep network to a target video recordedin an environment different from that of the source training set. To…

Deep learning-based multi-source unsupervised domain adaptation (MUDA) has been actively studied in recent years. Compared with single-source unsupervised domain adaptation (SUDA), domain shift in MUDA exists not only between the source and…

Semantic segmentation requires extensive pixel-level annotation, motivating unsupervised domain adaptation (UDA) to transfer knowledge from labelled source domains to unlabelled or weakly labelled target domains. One of the most efficient…

Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG) systems are increasingly deployed in industry applications, yet their reliability remains hampered by challenges in detecting hallucinations. While supervised…

Bilevel optimization has been developed for many machine learning tasks with large-scale and high-dimensional data. This paper considers a constrained bilevel optimization problem, where the lower-level optimization problem is convex with…

In the field of image classification, existing methods often struggle with biased or ambiguous data, a prevalent issue in real-world scenarios. Current strategies, including semi-supervised learning and class blending, offer partial…

While current benchmark reinforcement learning (RL) tasks have been useful to drive progress in the field, they are in many ways poor substitutes for learning with real-world data. By testing increasingly complex RL algorithms on…