Related papers: Randomize to Generalize: Domain Randomization for …

Unsupervised Anomaly detection (AD) requires building a notion of normalcy, distinguishing in-distribution (ID) and out-of-distribution (OOD) data, using only available ID samples. Recently, large gains were made on this task for the domain…

Few-shot object detection (FSOD) aims to detect novel instances with only a limited number of labeled training samples, presenting a challenge that is particularly prominent in numerous remote sensing applications such as endangered species…

The rapid advancement of generative artificial intelligence is producing fake remote sensing imagery (RSI) that is increasingly difficult to detect, potentially leading to erroneous intelligence, fake news, and even conspiracy theories.…

Diffusion models in image Super-Resolution (SR) treat all image regions uniformly, which risks compromising the overall image quality by potentially introducing artifacts during denoising of less-complex regions. To address this, we propose…

Weakly-supervised object detection (WSOD) models attempt to leverage image-level annotations in lieu of accurate but costly-to-obtain object localization labels. This oftentimes leads to substandard object detection and localization at…

We introduce Boundless, a photo-realistic synthetic data generation system for enabling highly accurate object detection in dense urban streetscapes. Boundless can replace massive real-world data collection and manual ground-truth object…

Domain generalization (DG) aims to adapt a model using one or multiple source domains to ensure robust performance in unseen target domains. Recently, Parameter-Efficient Fine-Tuning (PEFT) of foundation models has shown promising results…

As the misuse of AI-generated images grows, generalizable image detection techniques are urgently needed. Recent state-of-the-art (SOTA) methods adopt aligned training datasets to reduce content, size, and format biases, empowering models…

Object detection is one of the key target tasks of interest in the context of civil and military applications. In particular, the real-world deployment of target detection methods is pivotal in the decision-making process during military…

The emergence of diverse generative vision models has recently enabled the synthesis of visually realistic images, underscoring the critical need for effectively detecting these generated images from real photos. Despite advances in this…

Leveraging synthetically rendered data offers great potential to improve monocular depth estimation and other geometric estimation tasks, but closing the synthetic-real domain gap is a non-trivial and important task. While much recent work…

Single-domain generalization (S-DG) aims to generalize a model to unseen environments with a single-source domain. However, most S-DG approaches have been conducted in the field of classification. When these approaches are applied to object…

The rapid advancement of generative models in creating highly realistic images poses substantial risks for misinformation dissemination. For instance, a synthetic image, when shared on social media, can mislead extensive audiences and erode…

Object detection has achieved substantial progress in the last decade. However, detecting novel classes with only few samples remains challenging, since deep learning under low data regime usually leads to a degraded feature space. Existing…

Small object detection in aerial imagery presents significant challenges in computer vision due to the minimal data inherent in small-sized objects and their propensity to be obscured by larger objects and background noise. Traditional…

In this paper, we present a simple and parameter-efficient drop-in module for one-stage object detectors like SSD when learning from scratch (i.e., without pre-trained models). We call our module GFR (Gated Feature Reuse), which exhibits…

With the development of deep neural networks, the performance of crowd counting and pixel-wise density estimation are continually being refreshed. Despite this, there are still two challenging problems in this field: 1) current supervised…

Object detection in aerial images is an important task in environmental, economic, and infrastructure-related tasks. One of the most prominent applications is the detection of vehicles, for which deep learning approaches are increasingly…

In the past utilities relied on in-field inspections to identify asset defects. Recently, utilities have started using drone-based inspections to enhance the field-inspection process. We consider a vast repository of drone images, providing…

Tiny object detection is one of the key challenges in the field of object detection. The performance of most generic detectors dramatically decreases in tiny object detection tasks. The main challenge lies in extracting effective features…