相关论文: Foundations and Models in Modern Computer Vision: …

Vision Transformers (ViT) have recently emerged as a powerful alternative to convolutional networks (CNNs). Although hybrid models attempt to bridge the gap between these two architectures, the self-attention layers they rely on induce a…

Object detection is a central downstream task used to test if pre-trained network parameters confer benefits, such as improved accuracy or training speed. The complexity of object detection methods can make this benchmarking non-trivial…

Despite the growing use of transformer models in computer vision, a mechanistic understanding of these networks is still needed. This work introduces a method to reverse-engineer Vision Transformers trained to solve image classification…

We introduce a model-based image reconstruction framework with a convolution neural network (CNN) based regularization prior. The proposed formulation provides a systematic approach for deriving deep architectures for inverse problems with…

Conventional computer vision models rely on very deep, feedforward networks processing whole images and trained offline with extensive labeled data. In contrast, biological vision relies on comparatively shallow, recurrent networks that…

Computer vision methods that explicitly detect object parts and reason on them are a step towards inherently interpretable models. Existing approaches that perform part discovery driven by a fine-grained classification task make very…

This survey explores the adaptation of visual transformer models in Autonomous Driving, a transition inspired by their success in Natural Language Processing. Surpassing traditional Recurrent Neural Networks in tasks like sequential image…

The paradigm shift from shallow classifiers with hand-crafted features to end-to-end trainable deep learning models has shown significant improvements on supervised learning tasks. Despite the promising power of deep neural networks (DNN),…

Transformers are transforming the landscape of computer vision, especially for recognition tasks. Detection transformers are the first fully end-to-end learning systems for object detection, while vision transformers are the first fully…

Vision transformers (ViTs) are quickly becoming the de-facto architecture for computer vision, yet we understand very little about why they work and what they learn. While existing studies visually analyze the mechanisms of convolutional…

Recent advances on Vision Transformer (ViT) and its improved variants have shown that self-attention-based networks surpass traditional Convolutional Neural Networks (CNNs) in most vision tasks. However, existing ViTs focus on the standard…

Recent progress in diffusion-based visual generation has largely relied on latent diffusion models with variational autoencoders (VAEs). While effective for high-fidelity synthesis, this VAE+diffusion paradigm suffers from limited training…

Over the past decade, deep learning models have exhibited considerable advancements, reaching or even exceeding human-level performance in a range of visual perception tasks. This remarkable progress has sparked interest in applying deep…

Generative AI is transforming image synthesis, enabling the creation of high-quality, diverse, and photorealistic visuals across industries like design, media, healthcare, and autonomous systems. Advances in techniques such as…

The recent explosive interest on transformers has suggested their potential to become powerful "universal" models for computer vision tasks, such as classification, detection, and segmentation. While those attempts mainly study the…

It is a challenging task to learn discriminative representation from images and videos, due to large local redundancy and complex global dependency in these visual data. Convolution neural networks (CNNs) and vision transformers (ViTs) have…

Action recognition is a fundamental problem in computer vision with a lot of potential applications such as video surveillance, human computer interaction, and robot learning. Given pre-segmented videos, the task is to recognize actions…

Today, more and more, it is necessary that most applications and documents developed in previous or current technologies to be accessible online on cloud-based infrastructures. That is why the migration of legacy systems including their…

Deep learning (DL) has emerged as a powerful subset of machine learning (ML) and artificial intelligence (AI), outperforming traditional ML methods, especially in handling unstructured and large datasets. Its impact spans across various…

Holistic methods using CNNs and margin-based losses have dominated research on face recognition. In this work, we depart from this setting in two ways: (a) we employ the Vision Transformer as an architecture for training a very strong…