Related papers: Training Spatial-Frequency Visual Prompts and Prob…

The pre-trained foundation models (PFMs) have become essential for facilitating large-scale multimodal learning. Researchers have effectively employed the ``pre-train, prompt, and predict'' paradigm through prompt learning to induce…

Capitalizing on image-level pre-trained models for various downstream tasks has recently emerged with promising performance. However, the paradigm of "image pre-training followed by video fine-tuning" for high-dimensional video data…

Large pre-trained vision-language models such as CLIP have demonstrated great potential in zero-shot transferability to downstream tasks. However, to attain optimal performance, the manual selection of prompts is necessary to improve…

Prompt learning has been designed as an alternative to fine-tuning for adapting Vision-language (V-L) models to the downstream tasks. Previous works mainly focus on text prompt while visual prompt works are limited for V-L models. The…

Large-scale video-language pretraining enables strong generalization across multimodal tasks but often incurs prohibitive computational costs. Although recent advances in masked visual modeling help mitigate this issue, they still suffer…

Pre-trained vision-language models are able to interpret visual concepts and language semantics. Prompt learning, a method of constructing prompts for text encoders or image encoders, elicits the potentials of pre-trained models and readily…

Deploying machine learning algorithms for robot tasks in real-world applications presents a core challenge: overcoming the domain gap between the training and the deployment environment. This is particularly difficult for visuomotor…

Visual localization is the task of estimating camera pose in a known scene, which is an essential problem in robotics and computer vision. However, long-term visual localization is still a challenge due to the environmental appearance…

Vision-Language Models (VLMs), such as CLIP, have demonstrated impressive zero-shot transfer capabilities in image-level visual perception. However, these models have shown limited performance in instance-level tasks that demand precise…

Instance segmentation is a fundamental task in computer vision with broad applications across various industries. In recent years, with the proliferation of deep learning and artificial intelligence applications, how to train effective…

Efficient learning from demonstration for long-horizon tasks remains an open challenge in robotics. While significant effort has been directed toward learning trajectories, a recent resurgence of object-centric approaches has demonstrated…

Pre-trained vision-language models provide a robust foundation for efficient transfer learning across various downstream tasks. In the field of video action recognition, mainstream approaches often introduce additional modules to capture…

Neural network-based clustering has recently gained popularity, and in particular a constrained clustering formulation has been proposed to perform transfer learning and image category discovery using deep learning. The core idea is to…

The large-scale pre-trained vision language models (VLM) have shown remarkable domain transfer capability on natural images. However, it remains unknown whether this capability can also apply to the medical image domain. This paper…

For more efficient generalization to unseen domains (classes), most Few-shot Segmentation (FSS) would directly exploit pre-trained encoders and only fine-tune the decoder, especially in the current era of large models. However, such fixed…

Open-world object counting leverages the robust text-image alignment of pre-trained vision-language models (VLMs) to enable counting of arbitrary categories in images specified by textual queries. However, widely adopted naive fine-tuning…

Large Vision-Language Models (LVLMs) excel in visual understanding and reasoning, but the excessive visual tokens lead to high inference costs. Although recent token reduction methods mitigate this issue, they mainly target single-turn…

We present a meta-algorithm for learning a posterior-inference algorithm for restricted probabilistic programs. Our meta-algorithm takes a training set of probabilistic programs that describe models with observations, and attempts to learn…

Adapting pre-trained models to new tasks can exhibit varying effectiveness across datasets. Visual prompting, a state-of-the-art parameter-efficient transfer learning method, can significantly improve the performance of out-of-distribution…

Recently, test-time adaptation has garnered attention as a method for tuning models without labeled data. The conventional modus operandi for adapting pre-trained vision-language models (VLMs) during test-time primarily focuses on tuning…