Related papers: Masked AutoDecoder is Effective Multi-Task Vision …

At the core of both successful generative and self-supervised representation learning models there is a reconstruction objective that incorporates some form of image corruption. Diffusion models implement this approach through a scheduled…

While originally designed for unidirectional generative modeling, decoder-only large language models (LLMs) are increasingly being adapted for bidirectional modeling. However, unidirectional and bidirectional models are typically trained…

Multiview systems have become a key technology in modern computer vision, offering advanced capabilities in scene understanding and analysis. However, these systems face critical challenges in bandwidth limitations and computational…

Generative transformers have experienced rapid popularity growth in the computer vision community in synthesizing high-fidelity and high-resolution images. The best generative transformer models so far, however, still treat an image naively…

Masked face recognition is important for social good but challenged by diverse occlusions that cause insufficient or inaccurate representations. In this work, we propose a unified deep network to learn generative-to-discriminative…

In this paper, we propose a new progressive pre-training method for image understanding tasks which leverages RGB-D datasets. The method utilizes Multi-Modal Contrastive Masked Autoencoder and Denoising techniques. Our proposed approach…

Current machine learning models for vision are often highly specialized and limited to a single modality and task. In contrast, recent large language models exhibit a wide range of capabilities, hinting at a possibility for similarly…

There is a recent trend in the LiDAR perception field towards unifying multiple tasks in a single strong network with improved performance, as opposed to using separate networks for each task. In this paper, we introduce a new LiDAR…

Autoregressive (AR) models, common in sequence generation, are limited in many biological tasks such as de novo peptide sequencing and protein modeling by their unidirectional nature, failing to capture crucial global bidirectional token…

Recent advancements in deep learning have actively addressed complex challenges within the Computer-Aided Design (CAD) domain.However, most existing approaches rely on task-specifi c models requiring structural modifi cations for new tasks,…

We introduce a novel self-supervised learning framework that automatically learns representations from input computer-aided design (CAD) models for downstream tasks, including part classification, modeling segmentation, and machining…

This work proposes a new method to sequentially train deep neural networks on multiple tasks without suffering catastrophic forgetting, while endowing it with the capability to quickly adapt to unseen tasks. Starting from existing work on…

Post-training pretrained autoregressive models (ARMs) into masked diffusion models (MDMs) has emerged as a cost-effective way to overcome the limitations of sequential generation. Yet it remains unclear whether post-trained MDMs acquire…

Trajectory prediction has been a crucial task in building a reliable autonomous driving system by anticipating possible dangers. One key issue is to generate consistent trajectory predictions without colliding. To overcome the challenge, we…

Training general-purpose vision models on purely sequential visual data, eschewing linguistic inputs, has heralded a new frontier in visual understanding. These models are intended to not only comprehend but also seamlessly transit to…

Generalizable person re-identification (Re-ID) is a very hot research topic in machine learning and computer vision, which plays a significant role in realistic scenarios due to its various applications in public security and video…

Autonomous driving systems require a comprehensive understanding of the environment, achieved by extracting visual features essential for perception, planning, and control. However, models trained solely on single-task objectives or generic…

Autoregressive modeling has been a huge success in the field of natural language processing (NLP). Recently, autoregressive models have emerged as a significant area of focus in computer vision, where they excel in producing high-quality…

We present a mask-piloted Transformer which improves masked-attention in Mask2Former for image segmentation. The improvement is based on our observation that Mask2Former suffers from inconsistent mask predictions between consecutive decoder…

We present a conceptually simple, flexible, and universal visual perception head for variant visual tasks, e.g., classification, object detection, instance segmentation and pose estimation, and different frameworks, such as one-stage or…