Related papers: Contrastive Learning for Automotive mmWave Radar D…

Contrastive learning is a discriminative approach that aims at grouping similar samples closer and diverse samples far from each other. It it an efficient technique to train an encoder generating distinguishable and informative…

The DEtection TRansformer (DETR) opened new possibilities for object detection by modeling it as a translation task: converting image features into object-level representations. Previous works typically add expensive modules to DETR to…

Instance segmentation of images is an important tool for automated scene understanding. Neural networks are usually trained to optimize their overall performance in terms of accuracy. Meanwhile, in applications such as automated driving, an…

Data-driven techniques for machine vision heavily depend on the training data to sufficiently resemble the data occurring during test and application. However, in practice unknown distortion can lead to a domain gap between training and…

Modality representation learning is an important problem for multimodal sentiment analysis (MSA), since the highly distinguishable representations can contribute to improving the analysis effect. Previous works of MSA have usually focused…

As a safety critical task, autonomous driving requires accurate predictions of road users' future trajectories for safe motion planning, particularly under challenging conditions. Yet, many recent deep learning methods suffer from a…

We develop techniques for refining representations for fine-grained classification and segmentation tasks in a self-supervised manner. We find that fine-tuning methods based on instance-discriminative contrastive learning are not as…

This paper focuses on two crucial issues in domain-adaptive lane detection, i.e., how to effectively learn discriminative features and transfer knowledge across domains. Existing lane detection methods usually exploit a pixel-wise…

Multimodal deep learning utilizing imaging and diagnostic reports has made impressive progress in the field of medical imaging diagnostics, demonstrating a particularly strong capability for auxiliary diagnosis in cases where sufficient…

Video object detection is a challenging task because videos often suffer from image deterioration such as motion blur, occlusion, and deformable shapes, making it significantly more difficult than detecting objects in still images. Prior…

Object detection is an important computer vision task with plenty of real-world applications; therefore, how to enhance its robustness against adversarial attacks has emerged as a crucial issue. However, most of the previous defense methods…

Most state-of-the-art instance segmentation methods have to be trained on densely annotated images. While difficult in general, this requirement is especially daunting for biomedical images, where domain expertise is often required for…

With large-scale well-labeled datasets, deep learning has shown significant success in medical image segmentation. However, it is challenging to acquire abundant annotations in clinical practice due to extensive expertise requirements and…

Anomaly detection in multivariate time series (MTS) is hindered by dynamic inter-variable dependencies and feature entanglement under spectral noise, and in practice, is further complicated by the absence of anomaly labels. Existing…

Object recognition from images means to automatically find object(s) of interest and to return their category and location information. Benefiting from research on deep learning, like convolutional neural networks~(CNNs) and generative…

Image segmentation relies on large annotated datasets, which are expensive and slow to produce. Silver-standard (AI-generated) labels are easier to obtain, but they risk introducing bias. Self-supervised learning, needing only images, has…

Graph representation learning has long been an important yet challenging task for various real-world applications. However, their downstream tasks are mainly performed in the settings of supervised or semi-supervised learning. Inspired by…

Foundational vision models, such as the Segment Anything Model (SAM), have achieved significant breakthroughs through extensive pre-training on large-scale visual datasets. Despite their general success, these models may fall short in…

Robust detection of moving vehicles is a critical task for any autonomously operating outdoor robot or self-driving vehicle. Most modern approaches for solving this task rely on training image-based detectors using large-scale vehicle…

In this paper, we propose an adaptive margin contrastive learning method for 3D point cloud semantic segmentation, namely AMContrast3D. Most existing methods use equally penalized objectives, which ignore per-point ambiguities and less…