相关论文: Explicitly Modeled Attention Maps for Image Classi…

Vision Transformers have shown great promise recently for many vision tasks due to the insightful architecture design and attention mechanism. By revisiting the self-attention responses in Transformers, we empirically observe two…

Recently, deep learning-based models have exhibited remarkable performance for image manipulation detection. However, most of them suffer from poor universality of handcrafted or predetermined features. Meanwhile, they only focus on…

Small inter-class and large intra-class variations are the main challenges in fine-grained visual classification. Objects from different classes share visually similar structures and objects in the same class can have different poses and…

A human's attention can intuitively adapt to corrupted areas of an image by recalling a similar uncorrupted image they have previously seen. This observation motivates us to improve the attention of adversarial images by considering their…

Traditional geometric registration based estimation methods only exploit the CAD model implicitly, which leads to their dependence on observation quality and deficiency to occlusion. To address the problem,the paper proposes a bidirectional…

Transformers have demonstrated remarkable performance across diverse domains. The key component of Transformers is self-attention, which learns the relationship between any two tokens in the input sequence. Recent studies have revealed that…

Lossless image compression is an essential research field in image compression. Recently, learning-based image compression methods achieved impressive performance compared with traditional lossless methods, such as WebP, JPEG2000, and FLIF.…

Breast cancer is the most widespread neoplasm among women and early detection of this disease is critical. Deep learning techniques have become of great interest to improve diagnostic performance. However, distinguishing between malignant…

This paper presents experiments extending the work of Ba et al. (2014) on recurrent neural models for attention into less constrained visual environments, specifically fine-grained categorization on the Stanford Dogs data set. In this work…

Fine-grained visual recognition typically depends on modeling subtle difference from object parts. However, these parts often exhibit dramatic visual variations such as occlusions, viewpoints, and spatial transformations, making it hard to…

Vision Transformers (ViTs) have shown competitive accuracy in image classification tasks compared with CNNs. Yet, they generally require much more data for model pre-training. Most of recent works thus are dedicated to designing more…

Self-attention has recently been adopted for a wide range of sequence modeling problems. Despite its effectiveness, self-attention suffers from quadratic compute and memory requirements with respect to sequence length. Successful approaches…

While significant advances in deep learning has resulted in state-of-the-art performance across a large number of complex visual perception tasks, the widespread deployment of deep neural networks for TinyML applications involving…

High-definition (HD) map is crucial for autonomous driving systems. Most existing works design map elements detection heads based on the DETR decoder. However, the initial queries lack explicit incorporation of physical positional…

The demand for accurate food quantification has increased in the recent years, driven by the needs of applications in dietary monitoring. At the same time, computer vision approaches have exhibited great potential in automating tasks within…

Applying convolutional neural networks to large images is computationally expensive because the amount of computation scales linearly with the number of image pixels. We present a novel recurrent neural network model that is capable of…

Fine-grained classification is challenging because categories can only be discriminated by subtle and local differences. Variances in the pose, scale or rotation usually make the problem more difficult. Most fine-grained classification…

Self-attention is one of the most successful designs in deep learning, which calculates the similarity of different tokens and reconstructs the feature based on the attention matrix. Originally designed for NLP, self-attention is also…

Image compression is a fundamental research field and many well-known compression standards have been developed for many decades. Recently, learned compression methods exhibit a fast development trend with promising results. However, there…

Although existing monocular depth estimation methods have made great progress, predicting an accurate absolute depth map from a single image is still challenging due to the limited modeling capacity of networks and the scale ambiguity…