Related papers: Revisiting Model Stitching In the Foundation Model…

The last decade has witnessed the success of deep learning and the surge of publicly released trained models, which necessitates the quantification of the model functional distance for various purposes. However, quantifying the model…

Medical images are often more difficult to acquire than natural images due to the specialism of the equipment and technology, which leads to less medical image datasets. So it is hard to train a strong pretrained medical vision model. How…

Training a general-purpose time series foundation models with robust generalization capabilities across diverse applications from scratch is still an open challenge. Efforts are primarily focused on fusing cross-domain time series datasets…

Vision-language models (VLMs) achieve strong benchmark results, yet can exhibit systematic perceptual weaknesses: structured, large changes to pixel values can cause confident yet nonsensical predictions, even when the underlying scene…

Low-textured image stitching remains a challenging problem. It is difficult to achieve good alignment and it is easy to break image structures due to insufficient and unreliable point correspondences. Moreover, because of the viewpoint…

Vision-Language Models (VLMs) are a new family of models that align image content with natural language. Existing approaches typically fuse either (a) early: by mixing tokens/features inside the encoders, or (b) late: by comparing pooled…

Vision-language foundation models (VLMs) have shown impressive performance in guiding image generation through text, with emerging applications in medical imaging. In this work, we are the first to investigate the question: 'Can fine-tuned…

It has been observed that representations learned by distinct neural networks conceal structural similarities when the models are trained under similar inductive biases. From a geometric perspective, identifying the classes of…

Image segmentation is a long-standing challenge in computer vision, studied continuously over several decades, as evidenced by seminal algorithms such as N-Cut, FCN, and MaskFormer. With the advent of foundation models (FMs), contemporary…

Federated Learning (FL) has become an established technique to facilitate privacy-preserving collaborative training across a multitude of clients. However, new approaches to FL often discuss their contributions involving small deep-learning…

Current image stitching methods often produce noticeable seams in challenging scenarios such as uneven hue and large parallax. To tackle this problem, we propose the Reference-Driven Inpainting Stitcher (RDIStitcher), which reformulates the…

Background: RETFound, a self-supervised, retina-specific foundation model (FM), showed potential in downstream applications. However, its comparative performance with traditional deep learning (DL) models remains incompletely understood.…

The strength of machine learning models stems from their ability to learn complex function approximations from data; however, this strength also makes training deep neural networks challenging. Notably, the complex models tend to memorize…

The pretrain-finetune paradigm usually improves downstream performance over training a model from scratch on the same task, becoming commonplace across many areas of machine learning. While pretraining is empirically observed to be…

Recently, Stitchable Neural Networks (SN-Net) is proposed to stitch some pre-trained networks for quickly building numerous networks with different complexity and performance trade-offs. In this way, the burdens of designing or training the…

Model merging offers an efficient way to combine pre-trained neural networks but often suffers from inconsistent performance, especially when merging models with different initializations. We identify the ``vanishing feature'' phenomenon,…

Vision foundation models (VFMs) such as DINOv2 and CLIP have achieved impressive results on various downstream tasks, but their limited feature resolution hampers performance in applications requiring pixel-level understanding. Feature…

This work presents a systematic investigation into the latent knowledge encoded within Network Foundation Models (NFMs) that focuses on hidden representations analysis rather than pure downstream task performance. Different from existing…

A finite element simulation of the mechanical behaviour of woven textile materials at the scale of individual fibers is proposed in this paper. The aim of the simulation is to understand and identify phenomena involved at different scales…

Recent advances at the intersection of reinforcement learning (RL) and visual intelligence have enabled agents that not only perceive complex visual scenes but also reason, generate, and act within them. This survey offers a critical and…