Related papers: Scalpel-SAM: A Semi-Supervised Paradigm for Adapti…
Weakly Supervised Object Localization (WSOL), which aims to localize objects by only using image-level labels, has attracted much attention because of its low annotation cost in real applications. Current studies focus on the Class…
This paper presents GoodSAM++, a novel framework utilizing the powerful zero-shot instance segmentation capability of SAM (i.e., teacher) to learn a compact panoramic semantic segmentation model, i.e., student, without requiring any labeled…
In this paper, we tackle the problem of domain shift. Most existing methods perform training on multiple source domains using a single model, and the same trained model is used on all unseen target domains. Such solutions are sub-optimal as…
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…
Image copy detection is the task of detecting edited copies of any image within a reference database. While previous approaches have shown remarkable progress, the large size of their networks and descriptors remains a disadvantage,…
Most of recent attention-guided feature masking distillation methods perform knowledge transfer via global teacher attention maps without delving into fine-grained clues. Instead, performing distillation at finer granularity is conducive to…
The unsupervised 3D object detection is to accurately detect objects in unstructured environments with no explicit supervisory signals. This task, given sparse LiDAR point clouds, often results in compromised performance for detecting…
As a general model compression paradigm, feature-based knowledge distillation allows the student model to learn expressive features from the teacher counterpart. In this paper, we mainly focus on designing an effective feature-distillation…
Weakly Supervised Object Localization (WSOL), which aims to localize objects by only using image-level labels, has attracted much attention because of its low annotation cost in real applications. Recent studies leverage the advantage of…
Transformers trained with self-supervised learning using self-distillation loss (DINO) have been shown to produce attention maps that highlight salient foreground objects. In this paper, we demonstrate a graph-based approach that uses the…
Video representation learning is a vital problem for classification task. Recently, a promising unsupervised paradigm termed self-supervised learning has emerged, which explores inherent supervisory signals implied in massive data for…
Self-supervised learning (SSL) has emerged as a powerful strategy for representation learning under limited annotation regimes, yet its effectiveness remains highly sensitive to many factors, especially the nature of the target task. In…
Recent advances in deep learning has lead to rapid developments in the field of image retrieval. However, the best performing architectures incur significant computational cost. Recent approaches tackle this issue using knowledge…
The performance of deep learning based semantic segmentation models heavily depends on sufficient data with careful annotations. However, even the largest public datasets only provide samples with pixel-level annotations for rather limited…
Most Camouflaged Object Detection (COD) methods heavily rely on mask annotations, which are time-consuming and labor-intensive to acquire. Existing weakly-supervised COD approaches exhibit significantly inferior performance compared to…
We address the challenge of getting efficient yet accurate recognition systems with limited labels. While recognition models improve with model size and amount of data, many specialized applications of computer vision have severe resource…
Weakly supervised object detection (WSOD) aims to tackle the object detection problem using only labeled image categories as supervision. A common approach used in WSOD to deal with the lack of localization information is Multiple Instance…
Object detection in satellite-borne Synthetic Aperture Radar (SAR) imagery holds immense potential in tasks such as urban monitoring and disaster response. However, the inherent complexities of SAR data and the scarcity of annotations…
Image-level weakly supervised semantic segmentation is a challenging problem that has been deeply studied in recent years. Most of advanced solutions exploit class activation map (CAM). However, CAMs can hardly serve as the object mask due…
Incremental learning requires a model to continually learn new tasks from streaming data. However, traditional fine-tuning of a well-trained deep neural network on a new task will dramatically degrade performance on the old task -- a…