Related papers: Beyond Single Images: Retrieval Self-Augmented Uns…
Deep learning-based methods have garnered significant attention in remote sensing (RS) image compression due to their superior performance. Most of these methods focus on enhancing the coding capability of the compression network and…
Here we explore two related but important tasks based on the recently released REalistic Single Image DEhazing (RESIDE) benchmark dataset: (i) single image dehazing as a low-level image restoration problem; and (ii) high-level visual…
In this paper, we improve the challenging monocular 3D object detection problem with a general semi-supervised framework. Specifically, having observed that the bottleneck of this task lies in lacking reliable and informative samples to…
Vision-language foundation models have shown promising zero-shot generalization for Cross-Domain Few-Shot Object Detection (CD-FSOD). However, they face two critical challenges in fine-tuning: insufficient support set utilization due to…
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…
Camouflaged Object Detection (COD) aims to identify objects that blend seamlessly into their surroundings. The inherent visual complexity of camouflaged objects, including their low contrast with the background, diverse textures, and subtle…
We propose D-RISE, a method for generating visual explanations for the predictions of object detectors. Utilizing the proposed similarity metric that accounts for both localization and categorization aspects of object detection allows our…
A novel representation of images for image retrieval is introduced in this paper, by using a new type of feature with remarkable discriminative power. Despite the multi-scale nature of objects, most existing models perform feature…
With the rapid development of self-supervised learning (e.g., contrastive learning), the importance of having large-scale images (even without annotations) for training a more generalizable AI model has been widely recognized in medical…
Remote sensing (RS) images are usually stored in compressed format to reduce the storage size of the archives. Thus, existing content-based image retrieval (CBIR) systems in RS require decoding images before applying CBIR (which is…
Though deep learning based scene text detection has achieved great progress, well-trained detectors suffer from severe performance degradation for different domains. In general, a tremendous amount of data is indispensable to train the…
Recognizing multiple objects in an image is challenging due to occlusions, and becomes even more so when the objects are small. While promising, existing multi-label image recognition models do not explicitly learn context-based…
Self-supervised Learning (SSL) including the mainstream contrastive learning has achieved great success in learning visual representations without data annotations. However, most methods mainly focus on the instance level information (\ie,…
Localizing objects in an unsupervised manner poses significant challenges due to the absence of key visual information such as the appearance, type and number of objects, as well as the lack of labeled object classes typically available in…
Camouflaged object detection (COD), segmenting objects that are elegantly blended into their surroundings, is a valuable yet challenging task. Existing deep-learning methods often fall into the difficulty of accurately identifying the…
Mix-based augmentation has been proven fundamental to the generalization of deep vision models. However, current augmentations only mix samples at the current data batch during training, which ignores the possible knowledge accumulated in…
Source-free domain-adaptive object detection is an interesting but scarcely addressed topic. It aims at adapting a source-pretrained detector to a distinct target domain without resorting to source data during adaptation. So far, there is…
Recent self-training techniques have shown notable improvements in unsupervised domain adaptation for 3D object detection (3D UDA). These techniques typically select pseudo labels, i.e., 3D boxes, to supervise models for the target domain.…
Composed image retrieval (CIR) is the task of retrieving specific images by using a query that involves both a reference image and a relative caption. Most existing CIR models adopt the late-fusion strategy to combine visual and language…
Photo search, the task of retrieving images based on textual queries, has witnessed significant advancements with the introduction of CLIP (Contrastive Language-Image Pretraining) model. CLIP leverages a vision-language pre training…