Related papers: One-Stage Cascade Refinement Networks for Infrared…
Cross-domain pedestrian detection aims to generalize pedestrian detectors from one label-rich domain to another label-scarce domain, which is crucial for various real-world applications. Most recent works focus on domain alignment to train…
In order to handle the challenges of autonomous driving, deep learning has proven to be crucial in tackling increasingly complex tasks, such as 3D detection or instance segmentation. State-of-the-art approaches for image-based detection…
A common class of problems in remote sensing is scene classification, a fundamentally important task for natural hazards identification, geographic image retrieval, and environment monitoring. Recent developments in this field rely…
Object detectors trained on fully-annotated data currently yield state of the art performance but require expensive manual annotations. On the other hand, weakly-supervised detectors have much lower performance and cannot be used reliably…
Infrared small target detection is crucial for the efficacy of infrared search and tracking systems. Current tensor decomposition methods emphasize representing small targets with sparsity but struggle to separate targets from complex…
Weakly-supervised instance segmentation aims to detect and segment object instances precisely, given imagelevel labels only. Unlike previous methods which are composed of multiple offline stages, we propose Sequential Label Propagation and…
In the absence of labeled target data, unsupervised domain adaptation approaches seek to align the marginal distributions of the source and target domains in order to train a classifier for the target. Unsupervised domain alignment…
Infrared small target detection is a challenging task due to its unique characteristics (e.g., small, dim, shapeless and changeable). Recently published CNN-based methods have achieved promising performance with heavy feature extraction and…
Infrared small target detection (IRSTD) methods predominantly formulate the task as pixel-level segmentation, which requires costly dense annotations and is not well suited to tiny targets with weak texture and ambiguous boundaries. To…
Infrared target detection (IRSTD) tasks have critical applications in areas like wilderness rescue and maritime search. However, detecting infrared targets is challenging due to their low contrast and tendency to blend into complex…
An iris presentation attack detection (IPAD) is essential for securing personal identity is widely used iris recognition systems. However, the existing IPAD algorithms do not generalize well to unseen and cross-domain scenarios because of…
In this paper, we address the limitations of the DETR-based semi-supervised object detection (SSOD) framework, particularly focusing on the challenges posed by the quality of object queries. In DETR-based SSOD, the one-to-one assignment…
Nuclei instance segmentation in pathological images is crucial for downstream tasks such as tumor microenvironment analysis. However, the high cost and scarcity of annotated data limit the applicability of fully supervised methods, while…
Small object detection under complex backgrounds remains a challenging task due to severe feature degradation, weak semantic representation, and inaccurate localization caused by downsampling operations and background interference. Existing…
We present SemiOccam, an image recognition network that leverages semi-supervised learning in a highly efficient manner. Existing works often rely on complex training techniques and architectures, requiring hundreds of GPU hours for…
The recent Segment Anything Model (SAM) is a significant advancement in natural image segmentation, exhibiting potent zero-shot performance suitable for various downstream image segmentation tasks. However, directly utilizing the pretrained…
Infrared imagery enables temperature-based scene understanding using passive sensors, particularly under conditions of low visibility where traditional RGB imaging fails. Yet, developing downstream vision models for infrared applications is…
Unsupervised visible-infrared person re-identification (UVI-ReID) has recently gained great attention due to its potential for enhancing human detection in diverse environments without labeling. Previous methods utilize intra-modality…
The objective of this paper is few-shot object detection (FSOD) -- the task of expanding an object detector for a new category given only a few instances for training. We introduce a simple pseudo-labelling method to source high-quality…
Recent years have seen a rapid growth in new approaches improving the accuracy of semantic segmentation in a weakly supervised setting, i.e. with only image-level labels available for training. However, this has come at the cost of…