相关论文: Diffusion-Refined VQA Annotations for Semi-Supervi…

Unsupervised visual object tracking is a challenging task that requires following arbitrary targets in videos without training on ground-truth annotations. Despite considerable progress, existing state-of-the-art unsupervised trackers often…

We introduce Diff-Tracker, a novel approach for the challenging unsupervised visual tracking task leveraging the pre-trained text-to-image diffusion model. Our main idea is to leverage the rich knowledge encapsulated within the pre-trained…

Although instance segmentation methods have improved considerably, the dominant paradigm is to rely on fully-annotated training images, which are tedious to obtain. To alleviate this reliance, and boost results, semi-supervised approaches…

Foundation models have advanced computer vision by enabling strong performance across diverse tasks through large-scale pretraining and supervised fine-tuning. However, they may underperform in domains with distribution shifts and scarce…

Vision Transformer(ViT) is one of the most widely used models in the computer vision field with its great performance on various tasks. In order to fully utilize the ViT-based architecture in various applications, proper visualization…

The attention mechanisms in deep neural networks are inspired by human's attention that sequentially focuses on the most relevant parts of the information over time to generate prediction output. The attention parameters in those models are…

Visual explanation (attention)-guided learning uses not only labels but also explanations to guide model reasoning process. While visual attention-guided learning has shown promising results, it requires a large number of explanation…

The current success of modern visual reasoning systems is arguably attributed to cross-modality attention mechanisms. However, in deliberative reasoning such as in VQA, attention is unconstrained at each step, and thus may serve as a…

Achieving high-quality shadow removal with strong generalizability is challenging in scenes with complex global illumination. Due to the limited diversity in shadow removal datasets, current methods are prone to overfitting training data,…

Gaze-annotated facial data is crucial for training deep neural networks (DNNs) for gaze estimation. However, obtaining these data is labor-intensive and requires specialized equipment due to the challenge of accurately annotating the gaze…

The challenge of fine-grained visual recognition often lies in discovering the key discriminative regions. While such regions can be automatically identified from a large-scale labeled dataset, a similar method might become less effective…

Diffusion models, while increasingly adept at generating realistic images, are notably hindered by hallucinations -- unrealistic or incorrect features inconsistent with the trained data distribution. In this work, we propose Adaptive…

Medical Visual Question Answering (Med-VQA) systems benefit the interpretation of medical images containing critical clinical information. However, the challenge of noisy labels and limited high-quality datasets remains underexplored. To…

Versatile 3D tasks (e.g., generation or editing) that distill from Text-to-Image (T2I) diffusion models have attracted significant research interest for not relying on extensive 3D training data. However, T2I models exhibit limitations…

The performance of existing supervised layout estimation methods heavily relies on the quality of data annotations. However, obtaining large-scale and high-quality datasets remains a laborious and time-consuming challenge. To solve this…

Diffusion Transformers (DiT) have become the de-facto model for generating high-quality visual content like videos and images. A huge bottleneck is the attention mechanism where complexity scales quadratically with resolution and video…

Despite the rapid advancement of unsupervised learning in visual representation, it requires training on large-scale datasets that demand costly data collection, and pose additional challenges due to concerns regarding data privacy.…

Diffusion models are widely used for generative tasks across domains. Given a pre-trained diffusion model, it is often desirable to fine-tune it further either to correct for errors in learning or to align with downstream applications.…

Human gaze is known to be an intention-revealing signal in human demonstrations of tasks. In this work, we use gaze cues from human demonstrators to enhance the performance of agents trained via three popular imitation learning methods --…

To address the larger computation and storage requirements associated with large video datasets, video dataset distillation aims to capture spatial and temporal information in a significantly smaller dataset, such that training on the…