相关论文: Learning Where to Edit Vision Transformers

Image segmentation remains a challenging task in computer vision, demanding robust mask generation and precise classification. Recent mask-based approaches yield high-quality masks by capturing global context. However, accurately…

Visual data from the Web power image classifiers, which often underpin many web services, such as recommendation and content moderation. However, the raw Web data often contain spurious correlations and social biases, and neural networks…

Changing how pre-trained models behave -- e.g., improving their performance on a downstream task or mitigating biases learned during pre-training -- is a common practice when developing machine learning systems. In this work, we propose a…

Converting deep learning models between frameworks is a common step to maximize model compatibility across devices and leverage optimization features that may be exclusively provided in one deep learning framework. However, this conversion…

Medical image segmentation is a vital healthcare endeavor requiring precise and efficient models for appropriate diagnosis and treatment. Vision transformer (ViT)-based segmentation models have shown great performance in accomplishing this…

A Vision Transformer (ViT) is a simple neural architecture amenable to serve several computer vision tasks. It has limited built-in architectural priors, in contrast to more recent architectures that incorporate priors either about the…

Vision Transformers (ViTs) have demonstrated superior performance over Convolutional Neural Networks (CNNs) in various vision-related tasks such as classification, object detection, and segmentation due to their use of self-attention…

Vision Transformers (ViTs) have achieved remarkable success over various vision tasks, yet their robustness against data distribution shifts and inherent inductive biases remain underexplored. To enhance the robustness of ViT models for…

Currently, enhancing Unified Multimodal Models (UMMs) with image understanding, generation, and editing capabilities mainly relies on mixed multi-task training. Due to inherent task conflicts, such strategy requires complex multi-stage…

Image translation with convolutional neural networks has recently been used as an approach to multimodal change detection. Existing approaches train the networks by exploiting supervised information of the change areas, which, however, is…

Structural re-parameterization is a general training scheme for Convolutional Neural Networks (CNNs), which achieves performance improvement without increasing inference cost. As Vision Transformers (ViTs) are gradually surpassing CNNs in…

While the Vision Transformer (VT) architecture is becoming trendy in computer vision, pure VT models perform poorly on tiny datasets. To address this issue, this paper proposes the locality guidance for improving the performance of VTs on…

There is an increasing number of pre-trained deep neural network models. However, it is still unclear how to effectively use these models for a new task. Transfer learning, which aims to transfer knowledge from source tasks to a target…

The Vision Transformer (ViT) leverages the Transformer's encoder to capture global information by dividing images into patches and achieves superior performance across various computer vision tasks. However, the self-attention mechanism of…

We address the problem of predicting edit completions based on a learned model that was trained on past edits. Given a code snippet that is partially edited, our goal is to predict a completion of the edit for the rest of the snippet. We…

We introduce a vision-language foundation model called VL-BEiT, which is a bidirectional multimodal Transformer learned by generative pretraining. Our minimalist solution conducts masked prediction on both monomodal and multimodal data with…

This work targets to merge various Vision Transformers (ViTs) trained on different tasks (i.e., datasets with different object categories) or domains (i.e., datasets with the same categories but different environments) into one unified…

In recent years, deep neural networks (DNNs) trained with transformed data have been applied to various applications such as privacy-preserving learning, access control, and adversarial defenses. However, the use of transformed data…

We introduce a framework to measure how biases change before and after fine-tuning a large scale visual recognition model for a downstream task. Deep learning models trained on increasing amounts of data are known to encode societal biases.…

Post-training for large language models (LLMs) is constrained by the high cost of acquiring new knowledge or correcting errors and by the unintended side effects that frequently arise from retraining. To address these issues, we introduce…