Related papers: ViM: Vision Middleware for Unified Downstream Tran…
Pretrained vision foundation models deliver strong performance across tasks with limited fine-tuning. However, their Vision Transformer (ViT) backbones impose high inference costs, limiting deployment on resource-constrained devices. In…
Vision-language foundation models such as CLIP have shown impressive zero-shot performance on many tasks and datasets, especially thanks to their free-text inputs. However, they struggle to handle some downstream tasks, such as fine-grained…
The visual pathway of human brain includes two sub-pathways, ie, the ventral pathway and the dorsal pathway, which focus on object identification and dynamic information modeling, respectively. Both pathways comprise multi-layer structures,…
In recent years, there has been a proliferation of spatiotemporal foundation models in different scientific disciplines. While promising, these models are often domain-specific and are only assessed within the particular applications for…
We present Diversity-Aware Meta Visual Prompting~(DAM-VP), an efficient and effective prompting method for transferring pre-trained models to downstream tasks with frozen backbone. A challenging issue in visual prompting is that image…
Intermediate features of a pre-trained model have been shown informative for making accurate predictions on downstream tasks, even if the model backbone is kept frozen. The key challenge is how to utilize these intermediate features given…
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…
Large Vision-Language Foundation Models (VLFM), such as CLIP, ALIGN and Florence, are trained on large-scale datasets of image-caption pairs and achieve superior transferability and robustness on downstream tasks, but they are difficult to…
Navigation is a fundamental capability in embodied AI, representing the intelligence required to perceive and interact within physical environments following language instructions. Despite significant progress in large Vision-Language…
Recent vision transformer based video models mostly follow the ``image pre-training then finetuning" paradigm and have achieved great success on multiple video benchmarks. However, full finetuning such a video model could be computationally…
Large pretrained diffusion models have demonstrated impressive generation capabilities and have been adapted to various downstream tasks. However, unlike Large Language Models (LLMs) that can learn multiple tasks in a single model based on…
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…
VILA-U is a Unified foundation model that integrates Video, Image, Language understanding and generation. Traditional visual language models (VLMs) use separate modules for understanding and generating visual content, which can lead to…
Large-scale foundation models (LFMs) have recently made impressive progress in text-to-motion generation by learning strong generative priors from massive 3D human motion datasets and paired text descriptions. However, how to effectively…
Depth information is robust to scene appearance variations and inherently carries 3D spatial details. Thus, a visual backbone based on the vision transformer is proposed to fuse RGB and depth modalities for enhancing generalization in this…
Large pretrained plain vision Transformers (ViTs) have been the workhorse for many downstream tasks. However, existing works utilizing off-the-shelf ViTs are inefficient in terms of training and deployment, because adopting ViTs with…
Foundation models (FMs) have achieved remarkable success across a wide range of applications, from image classification to natural langurage processing, but pose significant challenges for deployment at edge. This has sparked growing…
Large vision models (LVMs) have emerged as a foundational paradigm in visual intelligence, achieving state-of-the-art performance across diverse visual tasks. Recent advances in LVMs have facilitated their integration into Internet of…
Self-supervised pretrain techniques have been widely used to improve the downstream tasks' performance. However, real-world magnetic resonance (MR) studies usually consist of different sets of contrasts due to different acquisition…
Vision Foundation Models (VFMs) have advanced representation learning through self-supervised methods. However, existing training pipelines are often inflexible, domain-specific, or computationally expensive, which limits their usability…