Related papers: Selective Contrastive Learning for Weakly Supervis…
Contrastive learning has achieved remarkable success in learning effective representations, with supervised contrastive learning often outperforming self-supervised approaches. However, in real-world scenarios, data annotations are often…
Weakly supervised visual recognition using inexact supervision is a critical yet challenging learning problem. It significantly reduces human labeling costs and traditionally relies on multi-instance learning and pseudo-labeling. This paper…
Weakly supervised segmentation requires assigning a label to every pixel based on training instances with partial annotations such as image-level tags, object bounding boxes, labeled points and scribbles. This task is challenging, as coarse…
The goal of self-supervised visual representation learning is to learn strong, transferable image representations, with the majority of research focusing on object or scene level. On the other hand, representation learning at part level has…
As a computer vision task, automatic object segmentation remains challenging in specialized image domains without massive labeled data, such as synthetic aperture sonar images, remote sensing, biomedical imaging, etc. In any domain,…
Perceiving potential ``action possibilities'' (\ie, affordance) regions of images and learning interactive functionalities of objects from human demonstration is a challenging task due to the diversity of human-object interactions.…
We propose an approach for unsupervised adaptation of object detectors from label-rich to label-poor domains which can significantly reduce annotation costs associated with detection. Recently, approaches that align distributions of source…
Weakly-supervised video scene graph generation (WS-VSGG) aims to parse video content into structured relational triplets without bounding box annotations and with only sparse temporal labeling, significantly reducing annotation costs.…
Visual saliency detection tries to mimic human vision psychology which concentrates on sparse, important areas in natural image. Saliency prediction research has been traditionally based on low level features such as contrast, edge, etc.…
Artificial intelligence is essential to succeed in challenging activities that involve dynamic environments, such as object manipulation tasks in indoor scenes. Most of the state-of-the-art literature explores robotic grasping methods by…
Machine unlearning, the efficient deletion of the impact of specific data in a trained model, remains a challenging problem. Current machine unlearning approaches that focus primarily on data-centric or weight-based strategies frequently…
When humans describe images they tend to use combinations of nouns and adjectives, corresponding to objects and their associated attributes respectively. To generate such a description automatically, one needs to model objects, attributes…
Weakly supervised object detection (WSOD) aims to classify and locate objects with only image-level supervision. Many WSOD approaches adopt multiple instance learning as the initial model, which is prone to converge to the most…
This work aims to leverage pre-trained foundation models, such as contrastive language-image pre-training (CLIP) and segment anything model (SAM), to address weakly supervised semantic segmentation (WSSS) using image-level labels. To this…
Weakly supervised object detection has recently received much attention, since it only requires image-level labels instead of the bounding-box labels consumed in strongly supervised learning. Nevertheless, the save in labeling expense is…
Weakly supervised object detection aims at reducing the amount of supervision required to train detection models. Such models are traditionally learned from images/videos labelled only with the object class and not the object bounding box.…
Robotic grasping is a fundamental ability for a robot to interact with the environment. Current methods focus on how to obtain a stable and reliable grasping pose in object level, while little work has been studied on part (shape)-wise…
The deep generative adversarial networks (GAN) recently have been shown to be promising for different computer vision applications, like image edit- ing, synthesizing high resolution images, generating videos, etc. These networks and the…
When humans perform a task with an articulated object, they interact with the object only in a handful of ways, while the space of all possible interactions is nearly endless. This is because humans have prior knowledge about what…
This paper addresses weakly supervised object detection with only image-level supervision at training stage. Previous approaches train detection models with entire images all at once, making the models prone to being trapped in sub-optimums…