Related papers: Aligning Pretraining for Detection via Object-Leve…

To improve performance in visual feature representation from photos or videos for practical applications, we generally require large-scale human-annotated labeled data while training deep neural networks. However, the cost of gathering and…

This paper explores a better prediction target for BERT pre-training of vision transformers. We observe that current prediction targets disagree with human perception judgment.This contradiction motivates us to learn a perceptual prediction…

We present Pix2Seq, a simple and generic framework for object detection. Unlike existing approaches that explicitly integrate prior knowledge about the task, we cast object detection as a language modeling task conditioned on the observed…

Contrastive learning models have demonstrated impressive abilities to capture semantic similarities by aligning representations in the embedding space. However, their performance can be limited by the quality of the training data and its…

Although graph neural networks (GNNs) have achieved impressive achievements in graph classification, they often need abundant task-specific labels, which could be extensively costly to acquire. A credible solution is to explore additional…

Contrastive learning has emerged as a promising paradigm for 3D open-world understanding, i.e., aligning point cloud representation to image and text embedding space individually. In this paper, we introduce MixCon3D, a simple yet effective…

Foundation models have recently gained attention within the field of machine learning thanks to its efficiency in broad data processing. While researchers had attempted to extend this success to time series models, the main challenge is…

Different from general object detection, moving infrared small target detection faces huge challenges due to tiny target size and weak background contrast.Currently, most existing methods are fully-supervised, heavily relying on a large…

Object counting has progressed from class-specific models, which count only known categories, to class-agnostic models that generalize to unseen categories. The next challenge is Referring Expression Counting (REC), where the goal is to…

Due to object detection's close relationship with video analysis and image understanding, it has attracted much research attention in recent years. Traditional object detection methods are built on handcrafted features and shallow trainable…

Object detection models perform well at localizing and classifying objects that they are shown during training. However, due to the difficulty and cost associated with creating and annotating detection datasets, trained models detect a…

Recently, a noticeable trend has emerged in developing pre-trained foundation models in the domains of CV and NLP. However, for molecular pre-training, there lacks a universal model capable of effectively applying to various categories of…

Meta-learning enables learning systems to adapt quickly to new tasks, similar to humans. Different meta-learning approaches all work under/with the mini-batch episodic training framework. Such framework naturally gives the information about…

Multimodal learning from document data has achieved great success lately as it allows to pre-train semantically meaningful features as a prior into a learnable downstream task. In this paper, we approach the document classification problem…

We consider how image super resolution (SR) can contribute to an object detection task in low-resolution images. Intuitively, SR gives a positive impact on the object detection task. While several previous works demonstrated that this…

Pre-training plays a vital role in various vision tasks, such as object recognition and detection. Commonly used pre-training methods, which typically rely on randomized approaches like uniform or Gaussian distributions to initialize model…

We aim to localize objects in images using image-level supervision only. Previous approaches to this problem mainly focus on discriminative object regions and often fail to locate precise object boundaries. We address this problem by…

Self-supervised learning (SSL) approaches have achieved great success when the amount of labeled data is limited. Within SSL, models learn robust feature representations by solving pretext tasks. One such pretext task is contrastive…

The application of deep neural networks to remote sensing imagery is often constrained by the lack of ground-truth annotations. Adressing this issue requires models that generalize efficiently from limited amounts of labeled data, allowing…

We investigate a strategy for improving the efficiency of contrastive learning of visual representations by leveraging a small amount of supervised information during pre-training. We propose a semi-supervised loss, SuNCEt, based on…