Related papers: Active Multimodal Distillation for Few-shot Action…

Modern neural networks are powerful predictive models. However, when it comes to recognizing that they may be wrong about their predictions, they perform poorly. For example, for one of the most common activation functions, the ReLU and its…

In recent years, few-shot action recognition has attracted increasing attention. It generally adopts the paradigm of meta-learning. In this field, overcoming the overlapping distribution of classes and outliers is still a challenging…

Distillation addresses the slow sampling problem in diffusion models by creating models with smaller size or fewer steps that approximate the behavior of high-step teachers. In this work, we propose a reinforcement learning based…

Learning based on multimodal data has attracted increasing interest recently. While a variety of sensory modalities can be collected for training, not all of them are always available in development scenarios, which raises the challenge to…

Active learning (AL) aims to optimize model training and reduce annotation costs by selecting the most informative samples for labeling. Typically, AL methods rely on the empirical distribution of labeled data to define the decision…

Multispectral pedestrian detection has been shown to be effective in improving performance within complex illumination scenarios. However, prevalent double-stream networks in multispectral detection employ two separate feature extraction…

Few-shot classification has made great strides due to foundation models that, through priming and prompting, are highly effective few-shot learners. However, this approach has high variance both across different sets of few shots (data…

Few-shot segmentation focuses on the generalization of models to segment unseen object with limited annotated samples. However, existing approaches still face two main challenges. First, huge feature distinction between support and query…

The rise of Large Language Models (LLMs) has boosted the use of Few-Shot Learning (FSL) methods in natural language processing, achieving acceptable performance even when working with limited training data. The goal of FSL is to effectively…

Multimodal sentiment analysis (MSA) aims to understand human sentiment through multimodal data. In real-world scenarios, practical factors often lead to uncertain modality missingness. Existing methods for handling modality missingness are…

Active recognition enables robots to intelligently explore novel observations, thereby acquiring more information while circumventing undesired viewing conditions. Recent approaches favor learning policies from simulated or collected data,…

We propose a technique that tackles action detection in multimodal videos under a realistic and challenging condition in which only limited training data and partially observed modalities are available. Common methods in transfer learning…

Few-shot segmentation (FSS) aims to rapidly learn novel class concepts from limited examples to segment specific targets in unseen images, and has been widely applied in areas such as medical diagnosis and industrial inspection. However,…

Inspired by the concept of active learning, we propose active inference$\unicode{x2013}$a methodology for statistical inference with machine-learning-assisted data collection. Assuming a budget on the number of labels that can be collected,…

Few-shot Intent Detection is challenging due to the scarcity of available annotated utterances. Although recent works demonstrate that multi-level matching plays an important role in transferring learned knowledge from seen training classes…

There has been a remarkable progress in learning a model which could recognise novel classes with only a few labeled examples in the last few years. Few-shot learning (FSL) for action recognition is a challenging task of recognising novel…

In this work, we address the problem of learning an ensemble of specialist networks using multimodal data, while considering the realistic and challenging scenario of possible missing modalities at test time. Our goal is to leverage the…

It is important to develop mathematically tractable models than can interpret knowledge extracted from the data and provide reasonable predictions. In this paper, we present a Linear Distillation Learning, a simple remedy to improve the…

In the surveillance and defense domain, multi-target detection and classification (MTD) is considered essential yet challenging due to heterogeneous inputs from diverse data sources and the computational complexity of algorithms designed…

Active statistical inference is a new method for inference with AI-assisted data collection. Given a budget on the number of labeled data points that can be collected and assuming access to an AI predictive model, the basic idea is to…