Related papers: Transformer with Peak Suppression and Knowledge Gu…

Learning a powerful representation from point clouds is a fundamental and challenging problem in the field of computer vision. Different from images where RGB pixels are stored in the regular grid, for point clouds, the underlying semantic…

In this paper, we present a novel deep image clustering approach termed PICI, which enforces the partial information discrimination and the cross-level interaction in a joint learning framework. In particular, we leverage a Transformer…

Image compression constitutes a significant challenge amidst the era of information explosion. Recent studies employing deep learning methods have demonstrated the superior performance of learning-based image compression methods over…

The self-attention mechanism, a cornerstone of Transformer-based state-of-the-art deep learning architectures, is largely heuristic-driven and fundamentally challenging to interpret. Establishing a robust theoretical foundation to explain…

Existing computer vision research in categorization struggles with fine-grained attributes recognition due to the inherently high intra-class variances and low inter-class variances. SOTA methods tackle this challenge by locating the most…

Utilizing transformer architectures for semantic segmentation of high-resolution images is hindered by the attention's quadratic computational complexity in the number of tokens. A solution to this challenge involves decreasing the number…

Real-world scenarios pose several challenges to deep learning based computer vision techniques despite their tremendous success in research. Deeper models provide better performance, but are challenging to deploy and knowledge distillation…

Fine-grained image labels are desirable for many computer vision applications, such as visual search or mobile AI assistant. These applications rely on image classification models that can produce hundreds of thousands (e.g. 100K) of…

Fine-grained visual classification is a challenging task due to the high similarity between categories and distinct differences among data within one single category. To address the challenges, previous strategies have focused on localizing…

Unified models aim to support both understanding and generation by encoding images into discrete tokens and processing them alongside text within a single autoregressive framework. This unified design offers architectural simplicity and…

Image fusion is a technique to integrate information from multiple source images with complementary information to improve the richness of a single image. Due to insufficient task-specific training data and corresponding ground truth, most…

Visual perception plays a pivotal role in enabling autonomous behavior, offering a cost-effective and efficient alternative to complex multi-sensor systems. However, robust segmentation remains a challenge in complex scenarios. To address…

Fine-grained image classification has witnessed significant advancements with the advent of deep learning and computer vision technologies. However, the scarcity of detailed annotations remains a major challenge, especially in scenarios…

In this paper, we consider the problem of fine-grained image retrieval in an incremental setting, when new categories are added over time. On the one hand, repeatedly training the representation on the extended dataset is time-consuming. On…

Image inpainting for completing complicated semantic environments and diverse hole patterns of corrupted images is challenging even for state-of-the-art learning-based inpainting methods trained on large-scale data. A reference image…

Deep learning has driven significant advances in medical image analysis, yet its adoption in clinical practice remains constrained by the large size and lack of transparency in modern models. Advances in interpretability techniques such as…

Transformers have transformed modern machine learning, driving breakthroughs in computer vision, natural language processing, and robotics. At the core of their success lies the attention mechanism, which enables the modeling of global…

Extracting robust feature representation is one of the key challenges in object re-identification (ReID). Although convolution neural network (CNN)-based methods have achieved great success, they only process one local neighborhood at a…

It has long been considered a significant problem to improve the visual quality of lossy image and video compression. Recent advances in computing power together with the availability of large training data sets has increased interest in…

Weakly supervised object localization is a challenging task which aims to localize objects with coarse annotations such as image categories. Existing deep network approaches are mainly based on class activation map, which focuses on…