Related papers: Inter2Former: Dynamic Hybrid Attention for Efficie…

3D semantic scene completion and 2D semantic segmentation are two tightly correlated tasks that are both essential for indoor scene understanding, because they predict the same semantic classes, using positively correlated high-level…

The Segment Anything Model (SAM) achieves strong open-vocabulary segmentation, but its ViT-based image encoders dominate inference latency and memory. Existing activation compression methods, such as token merging, reduce the token length…

The increasing demand for long-context modeling in large language models (LLMs) is bottlenecked by the quadratic complexity of the standard self-attention mechanism. The community has proposed sparse attention to mitigate this issue.…

Domain adaptive segmentation (DAS) is a promising paradigm for delineating intracellular structures from various large-scale electron microscopy (EM) without incurring extensive annotated data in each domain. However, the prevalent…

This paper introduces a novel attention mechanism, called dual attention, which is both efficient and effective. The dual attention mechanism consists of two parallel components: local attention generated by Convolutional Neural Networks…

In continual learning, solving the catastrophic forgetting problem may make the models fall into the stability-plasticity dilemma. Moreover, inter-task confusion will also occur due to the lack of knowledge exchanges between different…

Interactive medical image segmentation refers to the accurate segmentation of the target of interest through interaction (e.g., click) between the user and the image. It has been widely studied in recent years as it is less dependent on…

This paper introduces Dynamic Embeddings with Task-Oriented prompting (DETOT), a novel approach aimed at improving the adaptability and efficiency of machine learning models by implementing a flexible embedding layer. Unlike traditional…

Diffusion Transformers (DiTs) have revolutionized high-fidelity video generation, yet their $\mathcal{O}(L^2)$ attention complexity poses a formidable bottleneck for long-sequence synthesis. While recent sparse-linear attention hybrids aim…

Current hierarchical attention methods, such as NSA and InfLLMv2, select the top-k relevant key-value (KV) blocks based on coarse attention scores and subsequently apply fine-grained softmax attention on the selected tokens. However, the…

Recently, autoregressive recommendation models (ARMs), such as Meta's HSTU model, have emerged as a major breakthrough over traditional Deep Learning Recommendation Models (DLRMs), exhibiting the highly sought-after scaling law behaviour.…

Attention serves as the fundamental mechanism for long-context modeling in large language models (LLMs), yet dense attention becomes structurally prohibitive for long sequences due to its quadratic complexity. Consequently, sparse attention…

Most instance segmentation models are not end-to-end trainable due to either the incorporation of proposal estimation (RPN) as a pre-processing or non-maximum suppression (NMS) as a post-processing. Here we propose a novel end-to-end…

Since their introduction the Trasformer architectures emerged as the dominating architectures for both natural language processing and, more recently, computer vision applications. An intrinsic limitation of this family of "fully-attentive"…

Deep neural networks have been widely applied in dichotomous medical image segmentation (DMIS) of many anatomical structures in several modalities, achieving promising performance. However, existing networks tend to struggle with…

Automatically segmenting objects from optical remote sensing images (ORSIs) is an important task. Most existing models are primarily based on either convolutional or Transformer features, each offering distinct advantages. Exploiting both…

Segment Anything Model 2 (SAM2) demonstrated impressive zero-shot capabilities on natural images but faces challenges in biomedical segmentation due to significant domain shifts and prompt dependency. To address these limitations, we…

Diffusion Transformers (DiTs) have emerged as a leading architecture for text-to-image synthesis, producing high-quality and photorealistic images. However, the quadratic scaling properties of the attention in DiTs hinder image generation…

Recently, deep learning methods have been widely used for tumor segmentation of multimodal medical images with promising results. However, most existing methods are limited by insufficient representational ability, specific modality number…

Recently, LiDAR point cloud processing and analysis have made great progress due to the development of 3D Transformers. However, existing 3D Transformer methods usually are computationally expensive and inefficient due to their huge and…