Related papers: VIPriors 4: Visual Inductive Priors for Data-Effic…

In this dissertation, we investigated and enhanced Deep Learning (DL) techniques for counting objects, like pedestrians, cells or vehicles, in still images or video frames. In particular, we tackled the challenge related to the lack of data…

Conventional wisdom suggests that pre-training Vision Transformers (ViT) improves downstream performance by learning useful representations. Is this actually true? We investigate this question and find that the features and representations…

Self-supervised pretrain techniques have been widely used to improve the downstream tasks' performance. However, real-world magnetic resonance (MR) studies usually consist of different sets of contrasts due to different acquisition…

Recent neural implicit representations (NIRs) have achieved great success in the tasks of 3D reconstruction and novel view synthesis. However, they require the images of a scene from different camera views to be available for one-time…

Deep neural networks (DNNs) are successful in many computer vision tasks. However, the most accurate DNNs require millions of parameters and operations, making them energy, computation and memory intensive. This impedes the deployment of…

Despite the great progress of Visual Question Answering (VQA), current VQA models heavily rely on the superficial correlation between the question type and its corresponding frequent answers (i.e., language priors) to make predictions,…

Two less addressed issues of deep reinforcement learning are (1) lack of generalization capability to new target goals, and (2) data inefficiency i.e., the model requires several (and often costly) episodes of trial and error to converge,…

Recent research has demonstrated that feature attribution methods for deep networks can themselves be incorporated into training; these attribution priors optimize for a model whose attributions have certain desirable properties -- most…

As an important data selection schema, active learning emerges as the essential component when iterating an Artificial Intelligence (AI) model. It becomes even more critical given the dominance of deep neural network based models, which are…

Vision-Language Models (VLMs) exhibit systematic bias toward visual illusions, recalling memorized facts rather than perceiving actual visual differences. This paper presents a training-free framework for the 5th DataCV Challenge Task 1 at…

We introduce a learning framework called learning using privileged information (LUPI) to the computer vision field. We focus on the prototypical computer vision problem of teaching computers to recognize objects in images. We want the…

Model inversion, which aims to reconstruct the original training data from pre-trained discriminative models, is especially useful when the original training data is unavailable due to privacy, usage rights, or size constraints. However,…

Deep neural networks are a very powerful tool for many computer vision tasks, including image restoration, exhibiting state-of-the-art results. However, the performance of deep learning methods tends to drop once the observation model used…

Deep learning has recently seen rapid development and received significant attention due to its state-of-the-art performance on previously-thought hard problems. However, because of the internal complexity and nonlinear structure of deep…

Various stuff and things in visual data possess specific traits, which can be learned by deep neural networks and are implicitly represented as the visual prior, e.g., object location and shape, in the model. Such prior potentially impacts…

As the size of transformer-based models continues to grow, fine-tuning these large-scale pretrained vision models for new tasks has become increasingly parameter-intensive. Parameter-efficient learning has been developed to reduce the…

We propose VRL3, a powerful data-driven framework with a simple design for solving challenging visual deep reinforcement learning (DRL) tasks. We analyze a number of major obstacles in taking a data-driven approach, and present a suite of…

Deep learning algorithms have significantly reduced the computational time and improved the spatial resolution of particle image velocimetry~(PIV). However, the models trained on synthetic datasets might have a degraded performance on…

Recent advances in 3D perception have shown impressive progress in understanding geometric structures of 3Dshapes and even scenes. Inspired by these advances in geometric understanding, we aim to imbue image-based perception with…

Visual pre-training with large-scale real-world data has made great progress in recent years, showing great potential in robot learning with pixel observations. However, the recipes of visual pre-training for robot manipulation tasks are…