Related papers: Eventful Transformers: Leveraging Temporal Redunda…
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…
Recent advances of Transformers have brought new trust to computer vision tasks. However, on small dataset, Transformers is hard to train and has lower performance than convolutional neural networks. We make vision transformers as…
Recently, Transformers have emerged as the go-to architecture for both vision and language modeling tasks, but their computational efficiency is limited by the length of the input sequence. To address this, several efficient variants of…
Vision Transformer (ViT) models have made breakthroughs in image embedding extraction, which provide state-of-the-art performance in tasks such as zero-shot image classification. However, the models suffer from a high computational burden.…
The development of unsupervised Video Anomaly Detection (VAD) relies on technologies in the field of signal processing. Since the anomaly is quite ambiguous and unbounded, different detection demands may often be raised even in one…
Transformers have recently emerged as a powerful tool for learning visual representations. In this paper, we identify and characterize artifacts in feature maps of both supervised and self-supervised ViT networks. The artifacts correspond…
While the Transformer architecture has become the de-facto standard for natural language processing tasks, its applications to computer vision remain limited. In vision, attention is either applied in conjunction with convolutional…
The Vision Transformer (ViT) achieves remarkable accuracy across visual tasks but remains computationally expensive for edge deployment. This paper presents MicroViTv2, a lightweight Vision Transformer optimized for real-device efficiency.…
Intermediate features of a pre-trained model have been shown informative for making accurate predictions on downstream tasks, even if the model backbone is kept frozen. The key challenge is how to utilize these intermediate features given…
Continual learning aims to enable models to adapt to new datasets without losing performance on previously learned data, often assuming that prior data is no longer available. However, in many practical scenarios, both old and new data are…
This paper describes our solution for the video recognition task of ActivityNet Kinetics challenge that ranked the 1st place. Most of existing state-of-the-art video recognition approaches are in favor of an end-to-end pipeline. One…
This paper proposes a deep learning architecture based on Residual Network that dynamically adjusts the number of executed layers for the regions of the image. This architecture is end-to-end trainable, deterministic and problem-agnostic.…
Transformers have revolutionized machine learning across diverse domains, yet understanding their behavior remains crucial, particularly in high-stakes applications. This paper introduces the contextual counting task, a novel toy problem…
Vision transformer has achieved competitive performance on a variety of computer vision applications. However, their storage, run-time memory, and computational demands are hindering the deployment to mobile devices. Here we present a…
Vision transformers have demonstrated the potential to outperform CNNs in a variety of vision tasks. But the computational and memory requirements of these models prohibit their use in many applications, especially those that depend on…
Visual place recognition tasks often encounter significant challenges in landmark detection due to the presence of irrelevant objects such as humans, cars, and trees, despite the remarkable progress achieved by previous models, especially…
Event cameras report local changes of brightness through an asynchronous stream of output events. Events are spatially sparse at pixel locations with little brightness variation. We propose using a visual transformer (ViT) architecture to…
Large Transformer models routinely achieve state-of-the-art results on a number of tasks but training these models can be prohibitively costly, especially on long sequences. We introduce two techniques to improve the efficiency of…
State-of-the-art systems for semantic image segmentation use feed-forward pipelines with fixed computational costs. Building an image segmentation system that works across a range of computational budgets is challenging and time-intensive…
Real-time video segmentation is a crucial task for many real-world applications such as autonomous driving and robot control. Since state-of-the-art semantic segmentation models are often too heavy for real-time applications despite their…