English
Related papers

Related papers: ViM: Vision Middleware for Unified Downstream Tran…

200 papers

How much does having visual priors about the world (e.g. the fact that the world is 3D) assist in learning to perform downstream motor tasks (e.g. navigating a complex environment)? What are the consequences of not utilizing such visual…

Computer Vision and Pattern Recognition · Computer Science 2019-12-25 Alexander Sax , Jeffrey O. Zhang , Bradley Emi , Amir Zamir , Silvio Savarese , Leonidas Guibas , Jitendra Malik

The past year has witnessed a rapid development of masked image modeling (MIM). MIM is mostly built upon the vision transformers, which suggests that self-supervised visual representations can be done by masking input image parts while…

Computer Vision and Pattern Recognition · Computer Science 2022-03-29 Yunjie Tian , Lingxi Xie , Jiemin Fang , Mengnan Shi , Junran Peng , Xiaopeng Zhang , Jianbin Jiao , Qi Tian , Qixiang Ye

When performing 3D manipulation tasks, robots have to execute action planning based on perceptions from multiple fixed cameras. The multi-camera setup introduces substantial redundancy and irrelevant information, which increases…

Robotics · Computer Science 2025-12-19 Yixiang Chen , Yan Huang , Keji He , Peiyan Li , Liang Wang

We introduce UViM, a unified approach capable of modeling a wide range of computer vision tasks. In contrast to previous models, UViM has the same functional form for all tasks; it requires no task-specific modifications which require…

Computer Vision and Pattern Recognition · Computer Science 2022-10-17 Alexander Kolesnikov , André Susano Pinto , Lucas Beyer , Xiaohua Zhai , Jeremiah Harmsen , Neil Houlsby

A handful of visual foundation models (VFMs) have recently emerged as the backbones for numerous downstream tasks. VFMs like CLIP, DINOv2, SAM are trained with distinct objectives, exhibiting unique characteristics for various downstream…

Computer Vision and Pattern Recognition · Computer Science 2024-08-01 Mike Ranzinger , Greg Heinrich , Jan Kautz , Pavlo Molchanov

The agility of animals, particularly in complex activities such as running, turning, jumping, and backflipping, stands as an exemplar for robotic system design. Transferring this suite of behaviors to legged robotic systems introduces…

Robotics · Computer Science 2025-05-06 Ruihan Yang , Zhuoqun Chen , Jianhan Ma , Chongyi Zheng , Yiyu Chen , Quan Nguyen , Xiaolong Wang

The recent advances in virtualization technology have enabled the sharing of computing and networking resources of cloud data centers among multiple users. Virtual Network Embedding (VNE) is highly important and is an integral part of the…

Distributed, Parallel, and Cluster Computing · Computer Science 2021-11-05 Hiren Kumar Thakkar , Chinmaya Kumar Dehury , Prasan Kumar Sahoo

Vision foundation models (VFMs) are predominantly developed using data-centric methods. These methods require training on vast amounts of data usually with high-quality labels, which poses a bottleneck for most institutions that lack both…

Computer Vision and Pattern Recognition · Computer Science 2025-09-16 Jiabo Huang , Chen Chen , Lingjuan Lyu

Recent years have seen a paradigm shift towards multi-task learning. This calls for memory and energy-efficient solutions for inference in a multi-task scenario. We propose an algorithm-hardware co-design approach called MIME. MIME reuses…

Machine Learning · Computer Science 2022-06-22 Abhiroop Bhattacharjee , Yeshwanth Venkatesha , Abhishek Moitra , Priyadarshini Panda

Vision Foundation Models (VFMs) have become a de facto choice for many downstream vision tasks, like image classification, image segmentation, and object localization. However, they can also provide significant utility for downstream 3D…

Computer Vision and Pattern Recognition · Computer Science 2025-04-22 Johannes Spoecklberger , Wei Lin , Pedro Hermosilla , Sivan Doveh , Horst Possegger , M. Jehanzeb Mirza

Foundation models pre-trained on web-scale vision-language data, such as CLIP, are widely used as cornerstones of powerful machine learning systems. While pre-training offers clear advantages for downstream learning, it also endows…

Computer Vision and Pattern Recognition · Computer Science 2024-03-20 Anjun Hu , Jindong Gu , Francesco Pinto , Konstantinos Kamnitsas , Philip Torr

In reinforcement learning for visual navigation, it is common to develop a model for each new task, and train that model from scratch with task-specific interactions in 3D environments. However, this process is expensive; massive amounts of…

Computer Vision and Pattern Recognition · Computer Science 2022-05-02 Ziad Al-Halah , Santhosh K. Ramakrishnan , Kristen Grauman

Like masked language modeling (MLM) in natural language processing, masked image modeling (MIM) aims to extract valuable insights from image patches to enhance the feature extraction capabilities of the underlying deep neural network (DNN).…

Computer Vision and Pattern Recognition · Computer Science 2023-11-30 Yixuan Luo , Mengye Ren , Sai Qian Zhang

We present a model that can perform multiple vision tasks and can be adapted to other downstream tasks efficiently. Despite considerable progress in multi-task learning, most efforts focus on learning from multi-label data: a single image…

Computer Vision and Pattern Recognition · Computer Science 2023-06-30 Zitian Chen , Mingyu Ding , Yikang Shen , Wei Zhan , Masayoshi Tomizuka , Erik Learned-Miller , Chuang Gan

Transfer learning has recently become the dominant paradigm of machine learning. Pre-trained models fine-tuned for downstream tasks achieve better performance with fewer labelled examples. Nonetheless, it remains unclear how to develop…

Machine Learning · Computer Science 2024-01-30 Jonas Pfeiffer , Sebastian Ruder , Ivan Vulić , Edoardo Maria Ponti

Vision-transformers (ViTs) and large-scale convolution-neural-networks (CNNs) have reshaped computer vision through pretrained feature representations that enable strong transfer learning for diverse tasks. However, their efficiency as…

Computer Vision and Pattern Recognition · Computer Science 2025-10-07 Alon Kaya , Igal Bilik , Inna Stainvas

Modern visual agents require representations that are general, causal, and physically structured to operate in real-time streaming environments. However, current vision foundation models remain fragmented, specializing narrowly in image…

Computer Vision and Pattern Recognition · Computer Science 2026-03-13 Yibin Yan , Jilan Xu , Shangzhe Di , Haoning Wu , Weidi Xie

Large-scale pretrained foundation models have been an emerging paradigm for building artificial intelligence (AI) systems, which can be quickly adapted to a wide range of downstream tasks. This paper presents mPLUG, a new vision-language…

Computation and Language · Computer Science 2023-07-06 Chenliang Li , Haiyang Xu , Junfeng Tian , Wei Wang , Ming Yan , Bin Bi , Jiabo Ye , Hehong Chen , Guohai Xu , Zheng Cao , Ji Zhang , Songfang Huang , Fei Huang , Jingren Zhou , Luo Si

Pre-training has achieved remarkable success when transferred to downstream tasks. In machine learning, we care about not only the good performance of a model but also its behavior under reasonable shifts of condition. The same philosophy…

Computer Vision and Pattern Recognition · Computer Science 2023-11-27 Jianghui Wang , Yang Chen , Xingyu Xie , Cong Fang , Zhouchen Lin

We present VINO, a unified visual generator that performs image and video generation and editing within a single framework. Instead of relying on task-specific models or independent modules for each modality, VINO uses a shared diffusion…

Computer Vision and Pattern Recognition · Computer Science 2026-01-19 Junyi Chen , Tong He , Zhoujie Fu , Pengfei Wan , Kun Gai , Weicai Ye