Related papers: MTTrans: Cross-Domain Object Detection with Mean-T…
Supervised 3D Object Detection models have been displaying increasingly better performance in single-domain cases where the training data comes from the same environment and sensor as the testing data. However, in real-world scenarios data…
This paper focuses on source-free domain adaptation for object detection in computer vision. This task is challenging and of great practical interest, due to the cost of obtaining annotated data sets for every new domain. Recent research…
In recent years, rapid technological advancements and expanded Internet access have led to a significant rise in anomalies within network traffic and time-series data. Prompt detection of these irregularities is crucial for ensuring service…
In automatic target recognition (ATR) systems, sensors may fail to capture discriminative, fine-grained detail features due to environmental conditions, noise created by CMOS chips, occlusion, parallaxes, and sensor misalignment. Therefore,…
One of the major obstacles in designing an automatic target recognition (ATR) algorithm, is that there are often labeled images in one domain (i.e., infrared source domain) but no annotated images in the other target domains (i.e., visible,…
We focus on the source-free domain adaptive object detection (SF-DAOD) problem when source data is unavailable during adaptation and the model must adapt to an unlabeled target domain. The majority of approaches for the problem employ a…
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…
This paper presents a study on semi-supervised learning to solve the visual attribute prediction problem. In many applications of vision algorithms, the precise recognition of visual attributes of objects is important but still challenging.…
The introduction of DETR represents a new paradigm for object detection. However, its decoder conducts classification and box localization using shared queries and cross-attention layers, leading to suboptimal results. We observe that…
While representation learning aims to derive interpretable features for describing visual data, representation disentanglement further results in such features so that particular image attributes can be identified and manipulated. However,…
Domain adaptation of visual detectors is a critical challenge, yet existing methods have overlooked pixel appearance transformations, focusing instead on bootstrapping and/or domain confusion losses. We propose a Semantic Pixel-Level…
DETR-style detectors stand out amongst in-domain scenarios, but their properties in domain shift settings are under-explored. This paper aims to build a simple but effective baseline with a DETR-style detector on domain shift settings based…
Anomaly detection is represented as an unsupervised learning to identify deviated images from normal images. In general, there are two main challenges of anomaly detection tasks, i.e., the class imbalance and the unexpectedness of…
Recently,the detection transformer has gained substantial attention for its inherent minimal post-processing requirement.However,this paradigm relies on abundant training data,yet in the context of the cross-domain adaptation,insufficient…
Prior works in cross-lingual named entity recognition (NER) with no/little labeled data fall into two primary categories: model transfer based and data transfer based methods. In this paper we find that both method types can complement each…
Recent DEtection TRansformer-based (DETR) models have obtained remarkable performance. Its success cannot be achieved without the re-introduction of multi-scale feature fusion in the encoder. However, the excessively increased tokens in…
Recently the problem of cross-domain object detection has started drawing attention in the computer vision community. In this paper, we propose a novel unsupervised cross-domain detection model that exploits the annotated data in a source…
3D object detection is a significant task for autonomous driving. Recently with the progress of vision transformers, the 2D object detection problem is being treated with the set-to-set loss. Inspired by these approaches on 2D object…
DETR is a recently proposed Transformer-based method which views object detection as a set prediction problem and achieves state-of-the-art performance but demands extra-long training time to converge. In this paper, we investigate the…
Multimodal information (e.g., visible and thermal) can generate robust pedestrian detections to facilitate around-the-clock computer vision applications, such as autonomous driving and video surveillance. However, it still remains a crucial…