Related papers: AdaptFormer: Adapting Vision Transformers for Scal…
The past year has witnessed the rapid development of applying the Transformer module to vision problems. While some researchers have demonstrated that Transformer-based models enjoy a favorable ability of fitting data, there are still…
Vision Transformers (ViTs) have become one of the dominant architectures in computer vision, and pre-trained ViT models are commonly adapted to new tasks via fine-tuning. Recent works proposed several parameter-efficient transfer learning…
Vision Transformers (ViTs) have achieved overwhelming success, yet they suffer from vulnerable resolution scalability, i.e., the performance drops drastically when presented with input resolutions that are unseen during training. We…
This work investigates a simple yet powerful dense prediction task adapter for Vision Transformer (ViT). Unlike recently advanced variants that incorporate vision-specific inductive biases into their architectures, the plain ViT suffers…
Vision Transformer (ViT), a radically different architecture than convolutional neural networks offers multiple advantages including design simplicity, robustness and state-of-the-art performance on many vision tasks. However, in contrast…
The pretrain-then-finetune paradigm has been widely adopted in computer vision. But as the size of Vision Transformer (ViT) grows exponentially, the full finetuning becomes prohibitive in view of the heavier storage overhead. Motivated by…
Vision Transformers (ViTs) have become prominent models for solving various vision tasks. However, the interpretability of ViTs has not kept pace with their promising performance. While there has been a surge of interest in developing {\it…
While recent face anti-spoofing methods perform well under the intra-domain setups, an effective approach needs to account for much larger appearance variations of images acquired in complex scenes with different sensors for robust…
This paper tackles a significant challenge faced by Vision Transformers (ViTs): their constrained scalability across different image resolutions. Typically, ViTs experience a performance decline when processing resolutions different from…
Attention-based neural networks such as the Vision Transformer (ViT) have recently attained state-of-the-art results on many computer vision benchmarks. Scale is a primary ingredient in attaining excellent results, therefore, understanding…
Efficient video action recognition remains a challenging problem. One large model after another takes the place of the state-of-the-art on the Kinetics dataset, but real-world efficiency evaluations are often lacking. In this work, we fill…
Learning discriminative spatiotemporal representation is the key problem of video understanding. Recently, Vision Transformers (ViTs) have shown their power in learning long-term video dependency with self-attention. Unfortunately, they…
Recent vision transformer based video models mostly follow the ``image pre-training then finetuning" paradigm and have achieved great success on multiple video benchmarks. However, full finetuning such a video model could be computationally…
Vision-language retrieval is an important multi-modal learning topic, where the goal is to retrieve the most relevant visual candidate for a given text query. Recently, pre-trained models, e.g., CLIP, show great potential on retrieval…
In recent years, vision transformers (ViTs) have emerged as powerful and promising techniques for computer vision tasks such as image classification, object detection, and segmentation. Unlike convolutional neural networks (CNNs), which…
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…
Vision Transformers (ViTs) have demonstrated state-of-the-art performance on many Computer Vision Tasks. Unfortunately, deploying these large-scale ViTs is resource-consuming and impossible for many mobile devices. While most in the…
Vision Transformers (ViTs) have emerged as a foundational model in computer vision, excelling in generalization and adaptation to downstream tasks. However, deploying ViTs to support diverse resource constraints typically requires…
Vision Transformers (ViTs) partition input images into uniformly sized patches regardless of their content, resulting in long input sequence lengths for high-resolution images. We present Adaptive Patch Transformers (APT), which addresses…
Built on top of self-attention mechanisms, vision transformers have demonstrated remarkable performance on a variety of vision tasks recently. While achieving excellent performance, they still require relatively intensive computational cost…