Related papers: Object-Aware Cropping for Self-Supervised Learning

Most self-supervised learning (SSL) methods often work on curated datasets where the object-centric assumption holds. This assumption breaks down in uncurated images. Existing scene image SSL methods try to find the two views from original…

Self-supervised learning is a powerful way to learn useful representations from natural data. It has also been suggested as one possible means of building visual representation in humans, but the specific objective and algorithm are…

Contrastive self-supervised learning has outperformed supervised pretraining on many downstream tasks like segmentation and object detection. However, current methods are still primarily applied to curated datasets like ImageNet. In this…

How to frame (or crop) a photo often depends on the image subject and its context; e.g., a human portrait. Recent works have defined the subject-aware image cropping task as a nuanced and practical version of image cropping. We propose a…

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…

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…

Perceptual understanding of the scene and the relationship between its different components is important for successful completion of robotic tasks. Representation learning has been shown to be a powerful technique for this, but most of the…

Contrastive self-supervised learning has largely narrowed the gap to supervised pre-training on ImageNet. However, its success highly relies on the object-centric priors of ImageNet, i.e., different augmented views of the same image…

Crop-based training strategies decouple training resolution from GPU memory consumption, allowing the use of large-capacity panoptic segmentation networks on multi-megapixel images. Using crops, however, can introduce a bias towards…

Self-supervised learning (SSL) has emerged as a powerful technique for learning visual representations. While recent SSL approaches achieve strong results in global image understanding, they are limited in capturing the structured…

In this work, we study different approaches to self-supervised pretraining of object detection models. We first design a general framework to learn a spatially consistent dense representation from an image, by randomly sampling and…

Self-supervised representation learning approaches have recently surpassed their supervised learning counterparts on downstream tasks like object detection and image classification. Somewhat mysteriously the recent gains in performance come…

Well structured visual representations can make robot learning faster and can improve generalization. In this paper, we study how we can acquire effective object-centric representations for robotic manipulation tasks without human labeling…

Recent successes in self-supervised learning (SSL) model spatial co-occurrences of visual features either by masking portions of an image or by aggressively cropping it. Here, we propose a new way to model spatial co-occurrences by aligning…

The goal of image cropping is to identify visually appealing crops in an image. Conventional methods are trained on specific datasets and fail to adapt to new requirements. Recent breakthroughs in large vision-language models (VLMs) enable…

One of the important bottlenecks in training modern object detectors is the need for labeled images where bounding box annotations have to be produced for each object present in the image. This bottleneck is further exacerbated in aerial…

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…

Most invariance-based self-supervised methods rely on single object-centric images (e.g., ImageNet images) for pretraining, learning features that invariant to geometric transformation. However, when images are not object-centric, the…

Image cropping aims at improving the aesthetic quality of images by adjusting their composition. Most weakly supervised cropping methods (without bounding box supervision) rely on the sliding window mechanism. The sliding window mechanism…

Self-supervision allows learning meaningful representations of natural images, which usually contain one central object. How well does it transfer to multi-entity scenes? We discuss key aspects of learning structured object-centric…