相关论文: Images Speak in Images: A Generalist Painter for I…

Going beyond mere fine-tuning of vision-language models (VLMs), learnable prompt tuning has emerged as a promising, resource-efficient alternative. Despite their potential, effectively learning prompts faces the following challenges: (i)…

Domain generalization studies the problem of training a model with samples from several domains (or distributions) and then testing the model with samples from a new, unseen domain. In this paper, we propose a novel approach for domain…

We propose a novel memory-modular learner for image classification that separates knowledge memorization from reasoning. Our model enables effective generalization to new classes by simply replacing the memory contents, without the need for…

Providing a human-understandable explanation of classifiers' decisions has become imperative to generate trust in their use for day-to-day tasks. Although many works have addressed this problem by generating visual explanation maps, they…

During the past decade, deep neural networks have led to fast-paced progress and significant achievements in computer vision problems, for both academia and industry. Yet despite their success, state-of-the-art image classification…

Physics-based manipulation in clutter involves complex interaction between multiple objects. In this paper, we consider the problem of learning, from interaction in a physics simulator, manipulation skills to solve this multi-step…

Neuroimage processing tasks like segmentation, reconstruction, and registration are central to the study of neuroscience. Robust deep learning strategies and architectures used to solve these tasks are often similar. Yet, when presented…

Transferring knowledge from task-agnostic pre-trained deep models for downstream tasks is an important topic in computer vision research. Along with the growth of computational capacity, we now have open-source vision-language pre-trained…

The vision-language pre-training has enabled deep models to make a huge step forward in generalizing across unseen domains. The recent learning method based on the vision-language pre-training model is a great tool for domain generalization…

With the advent of vision-language models (VLMs) that can perform in-context and prompt-based learning, how can we design prompting approaches that robustly generalize to distribution shift and can be used on novel classes outside the…

One of the challenges of full autonomy is to have a robot capable of manipulating its current environment to achieve another environment configuration. This paper is a step towards this challenge, focusing on the visual understanding of the…

Despite large-scale pretraining endowing models with language and vision reasoning capabilities, improving their spatial reasoning capability remains challenging due to the lack of data grounded in the 3D world. While it is possible for…

We present a vision-language model whose parameters are jointly trained on all tasks and fully shared among multiple heterogeneous tasks which may interfere with each other, resulting in a single model which we named Musketeer. The…

We study theoretical guarantees for solving linear systems in-context using a linear transformer architecture. For in-domain generalization, we provide neural scaling laws that bound the generalization error in terms of the number of tasks…

That shared features between train and test data are required for generalisation in artificial neural networks has been a common assumption of both proponents and critics of these models. Here, we show that convolutional architectures avoid…

With the advent of large labelled datasets and high-capacity models, the performance of machine vision systems has been improving rapidly. However, the technology has still major limitations, starting from the fact that different vision…

Existing vision-language models (VLMs) such as CLIP have showcased an impressive capability to generalize well across various downstream tasks. These models leverage the synergy between visual and textual information, enabling them to…

Although an object may appear in numerous contexts, we often describe it in a limited number of ways. Language allows us to abstract away visual variation to represent and communicate concepts. Building on this intuition, we propose an…

Effective human-robot collaboration requires the ability to learn personalized concepts from a limited number of demonstrations, while exhibiting inductive generalization, hierarchical composition, and adaptability to novel constraints.…

The painting process of artists is inherently stepwise and varies significantly among different painters and styles. Generating detailed, step-by-step painting processes is essential for art education and research, yet remains largely…