Related papers: Instance Localization for Self-supervised Detectio…

In defense-related remote sensing applications, such as vehicle detection on satellite imagery, supervised learning requires a huge number of labeled examples to reach operational performances. Such data are challenging to obtain as it…

Visual domain gaps often impact object detection performance. Image-to-image translation can mitigate this effect, where contrastive approaches enable learning of the image-to-image mapping under unsupervised regimes. However, existing…

While supervised object detection methods achieve impressive accuracy, they generalize poorly to images whose appearance significantly differs from the data they have been trained on. To address this in scenarios where annotating data is…

Self-supervised instance discrimination is an effective contrastive pretext task to learn feature representations and address limited medical image annotations. The idea is to make features of transformed versions of the same images similar…

In a weakly-supervised scenario object detectors need to be trained using image-level annotation alone. Since bounding-box-level ground truth is not available, most of the solutions proposed so far are based on an iterative, Multiple…

After learning a new object category from image-level annotations (with no object bounding boxes), humans are remarkably good at precisely localizing those objects. However, building good object localizers (i.e., detectors) currently…

Quality feature representation is key to instance image retrieval. To attain it, existing methods usually resort to a deep model pre-trained on benchmark datasets or even fine-tune the model with a task-dependent labelled auxiliary dataset.…

Progress has been achieved recently in object detection given advancements in deep learning. Nevertheless, such tools typically require a large amount of training data and significant manual effort to label objects. This limits their…

Most existing approaches to training object detectors rely on fully supervised learning, which requires the tedious manual annotation of object location in a training set. Recently there has been an increasing interest in developing weakly…

Progress in self-supervised learning has brought strong general image representation learning methods. Yet so far, it has mostly focused on image-level learning. In turn, tasks such as unsupervised image segmentation have not benefited from…

We investigate the problem of automatically placing an object into a background image for image compositing. Given a background image and a segmented object, the goal is to train a model to predict plausible placements (location and scale)…

Pixel-level labels are particularly expensive to acquire. Hence, pretraining is a critical step to improve models on a task like semantic segmentation. However, prominent algorithms for pretraining neural networks use image-level…

Training image-based object detectors presents formidable challenges, as it entails not only the complexities of object detection but also the added intricacies of precisely localizing objects within potentially diverse and noisy…

Despite their irresistible success, deep learning algorithms still heavily rely on annotated data. On the other hand, unsupervised settings pose many challenges, especially about determining the right inductive bias in diverse scenarios.…

Weakly supervised learning has emerged as a compelling tool for object detection by reducing the need for strong supervision during training. However, major challenges remain: (1) differentiation of object instances can be ambiguous; (2)…

Self-supervised contrastive learning has demonstrated great potential in learning visual representations. Despite their success in various downstream tasks such as image classification and object detection, self-supervised pre-training for…

Providing ground truth supervision to train visual models has been a bottleneck over the years, exacerbated by domain shifts which degenerate the performance of such models. This was the case when visual tasks relied on handcrafted features…

We study how to leverage Web images to augment human-curated object detection datasets. Our approach is two-pronged. On the one hand, we retrieve Web images by image-to-image search, which incurs less domain shift from the curated data than…

It is challenging for weakly supervised object detection network to precisely predict the positions of the objects, since there are no instance-level category annotations. Most existing methods tend to solve this problem by using a…

Recent advances in self-supervised visual representation learning have paved the way for unsupervised methods tackling tasks such as object discovery and instance segmentation. However, discovering objects in an image with no supervision is…