Related papers: Visual Accommodation: Rethinking Image Scale as a …

Deep Metric Learning (DML) plays a critical role in various machine learning tasks. However, most existing deep metric learning methods with binary similarity are sensitive to noisy labels, which are widely present in real-world data. Since…

The flexibility of Simultaneous Localization and Mapping (SLAM) algorithms in various environments has consistently been a significant challenge. To address the issue of LiDAR odometry drift in high-noise settings, integrating clustering…

Image classification is an essential part of computer vision which assigns a given input image to a specific category based on the similarity evaluation within given criteria. While promising classifiers can be obtained through deep…

We investigate latent-space scalability for multi-task collaborative intelligence, where one of the tasks is object detection and the other is input reconstruction. In our proposed approach, part of the latent space can be selectively…

DEtection TRansformer (DETR) for object detection reaches competitive performance compared with Faster R-CNN via a transformer encoder-decoder architecture. However, trained with scratch transformers, DETR needs large-scale training data…

Robust 3D object detection is a core challenge for autonomous mobile systems in field robotics. To tackle this issue, many researchers have demonstrated improvements in 3D object detection performance in datasets. However, real-world urban…

Parameter-efficient transfer learning (PETL) is a promising task, aiming to adapt the large-scale pre-trained model to downstream tasks with a relatively modest cost. However, current PETL methods struggle in compressing computational…

Detecting abnormalities in medical images poses unique challenges due to differences in feature representations and the intricate relationship between anatomical structures and abnormalities. This is especially evident in mammography, where…

Robust self-training (RST) can augment the adversarial robustness of image classification models without significantly sacrificing models' generalizability. However, RST and other state-of-the-art defense approaches failed to preserve the…

In modern electronic manufacturing, defect detection on Printed Circuit Boards (PCBs) plays a critical role in ensuring product yield and maintaining the reliability of downstream assembly processes. However, existing methods often suffer…

Object detection typically assumes that training and test data are drawn from an identical distribution, which, however, does not always hold in practice. Such a distribution mismatch will lead to a significant performance drop. In this…

Massive-scale pretraining has made vision-language models increasingly popular for image-to-image and text-to-image retrieval across a broad collection of domains. However, these models do not perform well when used for challenging…

Model efficiency has become increasingly important in computer vision. In this paper, we systematically study neural network architecture design choices for object detection and propose several key optimizations to improve efficiency.…

3D object detectors are fundamental components of perception systems in autonomous vehicles. While these detectors achieve remarkable performance on standard autonomous driving benchmarks, they often struggle to generalize across different…

Addressing the challenge of domain shift between datasets is vital in maintaining model performance. In the context of cross-domain object detection, the teacher-student framework, a widely-used semi-supervised model, has shown significant…

The use of local detectors and descriptors in typical computer vision pipelines work well until variations in viewpoint and appearance change become extreme. Past research in this area has typically focused on one of two approaches to this…

Recent deep reinforcement learning (DRL) successes rely on end-to-end learning from fixed-size observational inputs (e.g. image, state-variables). However, many challenging and interesting problems in decision making involve observations or…

Event-based cameras (EBCs) have emerged as a bio-inspired alternative to traditional cameras, offering advantages in power efficiency, temporal resolution, and high dynamic range. However, the development of image analysis methods for EBCs…

Metric-based meta-learning has attracted a lot of attention due to its effectiveness and efficiency in few-shot learning. Recent studies show that metric scaling plays a crucial role in the performance of metric-based meta-learning…

Multiple Object Tracking (MOT) has long been a fundamental task in computer vision, with broad applications in various real-world scenarios. However, due to distribution shifts in appearance, motion pattern, and catagory between the…