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

As one of the fundamental techniques for image editing, image cropping discards unrelevant contents and remains the pleasing portions of the image to enhance the overall composition and achieve better visual/aesthetic perception. In this…

Parts provide a good intermediate representation of objects that is robust with respect to the camera, pose and appearance variations. Existing works on part segmentation is dominated by supervised approaches that rely on large amounts of…

Self-supervised representation learning is able to learn semantically meaningful features; however, much of its recent success relies on multiple crops of an image with very few objects. Instead of learning view-invariant representation…

Contrastive learning has been adopted as a core method for unsupervised visual representation learning. Without human annotation, the common practice is to perform an instance discrimination task: Given a query image crop, this task labels…

Contrastive instance discrimination methods outperform supervised learning in downstream tasks such as image classification and object detection. However, these methods rely heavily on data augmentation during representation learning, which…

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…

To date, most existing self-supervised learning methods are designed and optimized for image classification. These pre-trained models can be sub-optimal for dense prediction tasks due to the discrepancy between image-level prediction and…

We present a simple method, CropMix, for the purpose of producing a rich input distribution from the original dataset distribution. Unlike single random cropping, which may inadvertently capture only limited information, or irrelevant…

Humans naturally decompose their environment into entities at the appropriate level of abstraction to act in the world. Allowing machine learning algorithms to derive this decomposition in an unsupervised way has become an important line of…

To enhance the perception and reasoning capabilities of multimodal large language models in complex visual scenes, recent research has introduced agent-based workflows. In these works, MLLMs autonomously utilize image cropping tool to…

In continual learning, a system must incrementally learn from a non-stationary data stream without catastrophic forgetting. Recently, multiple methods have been devised for incrementally learning classes on large-scale image classification…

Self-supervised learning holds promise in leveraging large numbers of unlabeled data. However, its success heavily relies on the highly-curated dataset, e.g., ImageNet, which still needs human cleaning. Directly learning representations…

Most successful self-supervised learning methods are trained to align the representations of two independent views from the data. State-of-the-art methods in video are inspired by image techniques, where these two views are similarly…

The promise of self-supervised learning (SSL) is to leverage large amounts of unlabeled data to solve complex tasks. While there has been excellent progress with simple, image-level learning, recent methods have shown the advantage of…

Automatic image cropping aims to extract the most visually salient regions while preserving essential composition elements. Traditional saliency-aware cropping methods optimize a single bounding box, making them ineffective for applications…

The central idea of contrastive learning is to discriminate between different instances and force different views from the same instance to share the same representation. To avoid trivial solutions, augmentation plays an important role in…

Recent self-supervised models have demonstrated equal or better performance than supervised methods, opening for AI systems to learn visual representations from practically unlimited data. However, these methods are typically…

Multi-label Learning on Image data has been widely exploited with deep learning models. However, supervised training on deep CNN models often cannot discover sufficient discriminative features for classification. As a result, numerous…

Leveraging nearest neighbor retrieval for self-supervised representation learning has proven beneficial with object-centric images. However, this approach faces limitations when applied to scene-centric datasets, where multiple objects…

We propose a novel unsupervised object localization method that allows us to explain the predictions of the model by utilizing self-supervised pre-trained models without additional finetuning. Existing unsupervised and self-supervised…