Related papers: End-to-End Refinement Guided by Pre-trained Protot…

Modern video generators still struggle with complex physical dynamics, often falling short of physical realism. Existing approaches address this using external verifiers or additional training on augmented data, which is computationally…

Pre-trained representation is one of the key elements in the success of modern deep learning. However, existing works on continual learning methods have mostly focused on learning models incrementally from scratch. In this paper, we explore…

Machine learning algorithms based on artificial neural networks have proven very useful for a variety of classification problems. Here we apply them to a well-known problem in crystallography, namely the classification of X-ray diffraction…

Machine learning classifiers often produce probabilistic predictions that are critical for accurate and interpretable decision-making in various domains. The quality of these predictions is generally evaluated with proper losses, such as…

We present a novel approach to leverage prior knowledge encapsulated in pre-trained text-to-image diffusion models for blind super-resolution (SR). Specifically, by employing our time-aware encoder, we can achieve promising restoration…

Template matching is a fundamental task in computer vision and has been studied for decades. It plays an essential role in manufacturing industry for estimating the poses of different parts, facilitating downstream tasks such as robotic…

Imitation Learning offers a promising approach to learn directly from data without requiring explicit models, simulations, or detailed task definitions. During inference, actions are sampled from the learned distribution and executed on the…

In this paper, we discuss an imitation learning based method for reducing the calibration error for a mixed reality system consisting of a vision sensor and a projector. Unlike a head mounted display, in this setup, augmented information is…

Knowing the similarity between sets of data has a number of positive implications in training an effective model, such as assisting an informed selection out of known datasets favorable to model transfer or data augmentation problems with…

Modern deep learning models in computer vision require large datasets of real images, which are difficult to curate and pose privacy and legal concerns, limiting their commercial use. Recent works suggest synthetic data as an alternative,…

Electron backscatter diffraction (EBSD) is a well-established method of characterisation for crystalline materials. This technique can rapidly acquire and index diffraction patterns to provide phase and orientation information about the…

Foundation models pretrained on large-scale natural images are widely adapted to various cross-domain low-resource downstream tasks, benefiting from generalizable and transferable patterns captured by their representations. However, these…

Pre-training foundation models has become the de-facto procedure for deep learning approaches, yet its application remains limited in the geological studies, where in needs of the model transferability to break the shackle of data scarcity.…

Over the years, computer vision researchers have spent an immense amount of effort on designing image features for the visual object recognition task. We propose to incorporate this valuable experience to guide the task of training deep…

Language models have demonstrated remarkable performance in solving reasoning tasks; however, even the strongest models still occasionally make reasoning mistakes. Recently, there has been active research aimed at improving reasoning…

Pretrained foundation models learn embeddings that can be used for a wide range of downstream tasks. These embeddings optimise general performance, and if insufficiently accurate at a specific task the model can be fine-tuned to improve…

Pre-training a large transformer model on a massive amount of unlabeled data and fine-tuning it on labeled datasets for diverse downstream tasks has proven to be a successful strategy, for a variety of vision and natural language processing…

In inductive transfer learning, fine-tuning pre-trained convolutional networks substantially outperforms training from scratch. When using fine-tuning, the underlying assumption is that the pre-trained model extracts generic features, which…

Standard supervised classification trains models to imitate the exact labels provided by a perfect oracle. This imitation happens in a single pass, restricting the model to a fixed compute budget even when inputs vary in complexity.…

Fabric image retrieval is beneficial to many applications including clothing searching, online shopping and cloth modeling. Learning pairwise image similarity is of great importance to an image retrieval task. With the resurgence of…