Related papers: Fully Attentional Networks with Self-emerging Toke…

In this work, we propose aligning pretrained visual encoders to serve as tokenizers for latent diffusion models in image generation. Unlike training a variational autoencoder (VAE) from scratch, which primarily emphasizes low-level details,…

Vision transformers (ViT) have made substantial progress for classification tasks in computer vision. Recently, Gong et. al. '21, introduced attention-based modeling for several audio tasks. However, relatively unexplored is the use of a…

Vision Transformer (ViT) and its variants (e.g., Swin, PVT) have achieved great success in various computer vision tasks, owing to their capability to learn long-range contextual information. Layer Normalization (LN) is an essential…

Detecting manipulated media has now become a pressing issue with the recent rise of deepfakes. Most existing approaches fail to generalize across diverse datasets and generation techniques. We thus propose a novel ensemble framework,…

Structured representations, such as Bags of Words, VLAD and Fisher Vectors, have proven highly effective to tackle complex visual recognition tasks. As such, they have recently been incorporated into deep architectures. However, while…

Transformer is a potentially powerful architecture for vision tasks. Although equipped with more parameters and attention mechanism, its performance is not as dominant as CNN currently. CNN is usually computationally cheaper and still the…

LiDAR-based place recognition is one of the key components of SLAM and global localization in autonomous vehicles and robotics applications. With the success of DL approaches in learning useful information from 3D LiDARs, place recognition…

Vision Transformers have achieved impressive performance in many vision tasks. While the token mixer or attention block has been studied in great detail, much less research has been devoted to the channel mixer or feature mixing block (FFN…

Advances in deep learning are re-defining how visual data is processed and understand by the machines. Vision Transformers (ViTs) have recently demonstrated prominent performance in computer vision related tasks. However, their performance…

Label noise in medical image classification datasets significantly hampers the training of supervised deep learning methods, undermining their generalizability. The test performance of a model tends to decrease as the label noise rate…

Transformer has been applied in the field of computer vision due to its excellent performance in natural language processing, surpassing traditional convolutional neural networks and achieving new state-of-the-art. ViT divides an image into…

Attention-based models, exemplified by the Transformer, can effectively model long range dependency, but suffer from the quadratic complexity of self-attention operation, making them difficult to be adopted for high-resolution image…

Quantum Transfer Learning (QTL) offers a promising approach for visual quantum machine learning under near-term constraints, where limited qubit counts, shallow circuit depths, and costly hybrid optimization restrict end-to-end quantum…

In recent years, the Transformer architecture has proven to be very successful in sequence processing, but its application to other data structures, such as graphs, has remained limited due to the difficulty of properly defining positions.…

Transfer learning (TL) leverages previously obtained knowledge to learn new tasks efficiently and has been used to train deep learning (DL) models with limited amount of data. When TL is applied to DL, pretrained (teacher) models are…

The task of Few-shot Learning (FSL) aims to do the inference on novel categories containing only few labeled examples, with the help of knowledge learned from base categories containing abundant labeled training samples. While there are…

There has been a growing interest in extracting formal descriptions of the system behaviors from data. Signal Temporal Logic (STL) is an expressive formal language used to describe spatial-temporal properties with interpretability. This…

This paper studies introducing viewpoint invariant feature representations in existing action recognition architecture. Despite significant progress in action recognition, efficiently handling geometric variations in large-scale datasets…

Vision Transformer (ViT) is becoming more popular in image processing. Specifically, we investigate the effectiveness of test-time adaptation (TTA) on ViT, a technique that has emerged to correct its prediction during test-time by itself.…

Semantic Role Labeling (SRL) is believed to be a crucial step towards natural language understanding and has been widely studied. Recent years, end-to-end SRL with recurrent neural networks (RNN) has gained increasing attention. However, it…