相关论文: Bootstrapping SparseFormers from Vision Foundation…

Developing deep learning models on tiny devices (e.g. Microcontroller units, MCUs) has attracted much attention in various embedded IoT applications. However, it is challenging to efficiently design and deploy recent advanced models (e.g.…

Cross-modal 3D medical image analysis requires voxelwise representations that remain anatomically consistent across imaging contrasts, scanners, and acquisition protocols. Recent work has shown that frozen 2D Vision Transformer (ViT)…

Recently, vision transformer (ViT) based multimodal learning methods have been proposed to improve the robustness of face anti-spoofing (FAS) systems. However, there are still no works to explore the fundamental natures (\textit{e.g.},…

Code summarization aims to generate natural language descriptions of source code, facilitating programmers to understand and maintain it rapidly. While previous code summarization efforts have predominantly focused on method-level, this…

In the wake of Masked Image Modeling (MIM), a diverse range of plain, non-hierarchical Vision Transformer (ViT) models have been pre-trained with extensive datasets, offering new paradigms and significant potential for semantic…

Transformers are remarkably versatile, suggesting the existence of generic inductive biases beneficial across modalities. In this work, we explore a new way to instil such biases in vision transformers (ViTs) through pretraining on…

Contrastive language-image pre-training aligns the features of text-image pairs in a common latent space via distinct encoders for each modality. While this approach achieves impressive performance in several zero-shot tasks, it cannot…

Training visual embeddings with labeled data supervision has been the de facto setup for representation learning in computer vision. Inspired by recent success of adopting masked image modeling (MIM) in self-supervised representation…

We present a novel approach for recovering 3D shape and view dependent appearance from a few colored images, enabling efficient 3D reconstruction and novel view synthesis. Our method learns an implicit neural representation in the form of a…

Self-supervised vision-language models trained with contrastive objectives form the basis of current state-of-the-art methods in AI vision tasks. The success of these models is a direct consequence of the huge web-scale datasets used to…

Open-vocabulary semantic segmentation (OVSS) underpins many vision and robotics tasks that require generalizable semantic understanding. Existing approaches either rely on limited segmentation training data, which hinders generalization, or…

Autonomy in robot-assisted minimally invasive surgery has the potential to reduce surgeon cognitive and task load, thereby increasing procedural efficiency. However, implementing accurate autonomous control can be difficult due to poor…

Sparse mixture of expert architectures (MoEs) scale model capacity without significant increases in training or inference costs. Despite their success, MoEs suffer from a number of issues: training instability, token dropping, inability to…

Open-Vocabulary Video Instance Segmentation (VIS) is attracting increasing attention due to its ability to segment and track arbitrary objects. However, the recent Open-Vocabulary VIS attempts obtained unsatisfactory results, especially in…

Recently, vision transformer (ViT) and its variants have achieved promising performances in various computer vision tasks. Yet the high computational costs and training data requirements of ViTs limit their application in…

One-Shot Federated Learning, where a central server learns a global model in a single communication round, has emerged as a promising paradigm. However, under extremely non-IID settings, existing data-free methods often generate low-quality…

Segment Anything Model (SAM) has emerged as a powerful tool for numerous vision applications. A key component that drives the impressive performance for zero-shot transfer and high versatility is a super large Transformer model trained on…

In this paper, we show the surprisingly good properties of plain vision transformers for body pose estimation from various aspects, namely simplicity in model structure, scalability in model size, flexibility in training paradigm, and…

Assessing human skill levels in complex activities is a challenging problem with applications in sports, rehabilitation, and training. In this work, we present SkillFormer, a parameter-efficient architecture for unified multi-view…

We introduce a method to train vision-language models for remote-sensing images without using any textual annotations. Our key insight is to use co-located internet imagery taken on the ground as an intermediary for connecting…