Related papers: MARMOT: Masked Autoencoder for Modeling Transient …

Vision sensors are becoming more important in Intelligent Transportation Systems (ITS) for traffic monitoring, management, and optimization as the number of network cameras continues to rise. However, manual object tracking and matching…

We show how bidirectional transformers trained for masked token prediction can be applied to neural image compression to achieve state-of-the-art results. Such models were previously used for image generation by progressivly sampling groups…

Lane detection is crucial for vehicle localization which makes it the foundation for automated driving and many intelligent and advanced driving assistant systems. Available vision-based lane detection methods do not make full use of the…

LiDAR and camera are two important sensors for 3D object detection in autonomous driving. Despite the increasing popularity of sensor fusion in this field, the robustness against inferior image conditions, e.g., bad illumination and sensor…

Salient Object Detection (SOD) with deep learning often requires substantial computational resources and large annotated datasets, making it impractical for resource-constrained applications. Lightweight models address computational demands…

Transfer learning has gained attention in medical image analysis due to limited annotated 3D medical datasets for training data-driven deep learning models in the real world. Existing 3D-based methods have transferred the pre-trained models…

This work proposes a unified self-supervised pre-training framework for transferable multi-modal perception representation learning via masked multi-modal reconstruction in Neural Radiance Field (NeRF), namely NeRF-Supervised Masked…

As a class of fruitful approaches, diffusion probabilistic models (DPMs) have shown excellent advantages in high-resolution image reconstruction. On the other hand, masked autoencoders (MAEs), as popular self-supervised vision learners,…

Text images contain both visual and linguistic information. However, existing pre-training techniques for text recognition mainly focus on either visual representation learning or linguistic knowledge learning. In this paper, we propose a…

Unsupervised object-centric learning aims to decompose scenes into interpretable object entities, termed slots. Slot-based auto-encoders stand out as a prominent method for this task. Within them, crucial aspects include guiding the encoder…

Pre-trained Language Models (PLMs) have been widely used in various natural language processing (NLP) tasks, owing to their powerful text representations trained on large-scale corpora. In this paper, we propose a new PLM called PERT for…

Multi-object tracking (MOT) methods often rely on Intersection-over-Union (IoU) for association. However, this becomes unreliable when objects are similar or occluded. Also, computing IoU for segmentation masks is computationally expensive.…

The need for a large amount of labeled data in the supervised setting has led recent studies to utilize self-supervised learning to pre-train deep neural networks using unlabeled data. Many self-supervised training strategies have been…

Much of natural language processing is focused on leveraging large capacity language models, typically trained over single messages with a task of predicting one or more tokens. However, modeling human language at higher-levels of context…

This paper investigates the critical problem of representation similarity evolution during cross-domain transfer learning, with particular focus on understanding why pre-trained models maintain effectiveness when adapted to medical imaging…

Open-world object detection (OWOD), as a more general and challenging goal, requires the model trained from data on known objects to detect both known and unknown objects and incrementally learn to identify these unknown objects. The…

Fluorescence Molecular Tomography (FMT) is a promising technique for non-invasive 3D visualization of fluorescent probes, but its reconstruction remains challenging due to the inherent ill-posedness and reliance on inaccurate or…

A critical object detection task is finetuning an existing model to detect novel objects, but the standard workflow requires bounding box annotations which are time-consuming and expensive to collect. Weakly supervised object detection…

Object recognition has seen significant progress in the image domain, with focus primarily on 2D perception. We propose to leverage existing large-scale datasets of 3D models to understand the underlying 3D structure of objects seen in an…

In this paper, we propose a transformer-based image matting model called MatteFormer, which takes full advantage of trimap information in the transformer block. Our method first introduces a prior-token which is a global representation of…