相关论文: SCP: Soft Conditional Prompt Learning for Aerial V…

Prompt engineering is a powerful tool used to enhance the performance of pre-trained models on downstream tasks. For example, providing the prompt "Let's think step by step" improved GPT-3's reasoning accuracy to 63% on MutiArith while…

Continual learning aims to refine model parameters for new tasks while retaining knowledge from previous tasks. Recently, prompt-based learning has emerged to leverage pre-trained models to be prompted to learn subsequent tasks without the…

Textual-based prompt learning methods primarily employ multiple learnable soft prompts and hard class tokens in a cascading manner as text inputs, aiming to align image and text (category) spaces for downstream tasks. However, current…

Prompting has emerged as a practical way to adapt frozen vision-language models (VLMs) for video anomaly detection (VAD). Yet, existing prompts are often overly abstract, overlooking the fine-grained human-object interactions or action…

In order to autonomously learn wide repertoires of complex skills, robots must be able to learn from their own autonomously collected data, without human supervision. One learning signal that is always available for autonomously collected…

Vision-language models (VLMs), such as CLIP, have shown strong generalization under zero-shot settings, yet adapting them to downstream tasks with limited supervision remains a significant challenge. Existing multi-modal prompt learning…

A core challenge for an autonomous agent acting in the real world is to adapt its repertoire of skills to cope with its noisy perception and dynamics. To scale learning of skills to long-horizon tasks, robots should be able to learn and…

Learning neural implicit fields of 3D shapes is a rapidly emerging field that enables shape representation at arbitrary resolutions. Due to the flexibility, neural implicit fields have succeeded in many research areas, including shape…

Understanding the vulnerability of large-scale pre-trained vision-language models like CLIP against adversarial attacks is key to ensuring zero-shot generalization capacity on various downstream tasks. State-of-the-art defense mechanisms…

We propose CaSPR, a method to learn object-centric Canonical Spatiotemporal Point Cloud Representations of dynamically moving or evolving objects. Our goal is to enable information aggregation over time and the interrogation of object state…

This paper presents a simple and effective visual prompting method for adapting pre-trained models to downstream recognition tasks. Our method includes two key designs. First, rather than directly adding together the prompt and the image,…

Prompt tuning, a recently emerging paradigm, enables the powerful vision-language pre-training models to adapt to downstream tasks in a parameter -- and data -- efficient way, by learning the ``soft prompts'' to condition frozen…

This paper contributes a novel and modularized learning-based method for aerial robots navigating cluttered environments containing hard-to-perceive thin obstacles without assuming access to a map or the full pose estimation of the robot.…

Aerial robots can enhance construction site productivity by autonomously handling inspection and mapping tasks. However, ensuring safe navigation near human workers remains challenging. While navigation in static environments has been well…

Machines are a long way from robustly solving open-world perception-control tasks, such as first-person view (FPV) aerial navigation. While recent advances in end-to-end Machine Learning, especially Imitation and Reinforcement Learning…

In visuomotor policy learning, diffusion-based imitation learning has become widely adopted for its ability to capture diverse behaviors. However, approaches built on ordinary and stochastic denoising processes struggle to jointly achieve…

In traditional audio captioning methods, a model is usually trained in a fully supervised manner using a human-annotated dataset containing audio-text pairs and then evaluated on the test sets from the same dataset. Such methods have two…

Human detection in videos plays an important role in various real-life applications. Most traditional approaches depend on utilizing handcrafted features, which are problem-dependent and optimal for specific tasks. Moreover, they are highly…

Few-Shot Class-Incremental Learning (FSCIL) models aim to incrementally learn new classes with scarce samples while preserving knowledge of old ones. Existing FSCIL methods usually fine-tune the entire backbone, leading to overfitting and…

Spatio-temporal forecasting is of great importance in a wide range of dynamical systems applications from atmospheric science, to recent COVID-19 spread modeling. These applications rely on accurate predictions of spatio-temporal structured…