Related papers: Interlaced Sparse Self-Attention for Semantic Segm…

Efficiently computing attention maps for videos is challenging due to the motion of objects between frames. While a standard non-local search is high-quality for a window surrounding each query point, the window's small size cannot…

This paper proposes a novel deep learning architecture for semantic segmentation. The proposed Global and Selective Attention Network (GSANet) features Atrous Spatial Pyramid Pooling (ASPP) with a novel sparsemax global attention and a…

This paper proposes to learn reliable dense correspondence from videos in a self-supervised manner. Our learning process integrates two highly related tasks: tracking large image regions \emph{and} establishing fine-grained pixel-level…

Medical image segmentation has witnessed significant advancements with the emergence of deep learning. However, the reliance of most neural network models on a substantial amount of annotated data remains a challenge for medical image…

Efficient inference is critical for long-context language models, where attention computation and KV-cache access dominate the cost. Recent work RAT+, introduces a recurrence-augmented attention backbone that enables flexible dilated…

Weakly-supervised semantic segmentation is a challenging task as no pixel-wise label information is provided for training. Recent methods have exploited classification networks to localize objects by selecting regions with strong response.…

Recently many effective attention modules are proposed to boot the model performance by exploiting the internal information of convolutional neural networks in computer vision. In general, many previous works ignore considering the design…

A new line of research for feature selection based on neural networks has recently emerged. Despite its superiority to classical methods, it requires many training iterations to converge and detect informative features. The computational…

The self-attention mechanism, now central to deep learning architectures such as Transformers, is a modern instance of a more general computational principle: learning and using pairwise affinity matrices to control how information flows…

Existing semantic segmentation approaches either aim to improve the object's inner consistency by modeling the global context, or refine objects detail along their boundaries by multi-scale feature fusion. In this paper, a new paradigm for…

Subspace clustering refers to the problem of clustering high-dimensional data into a union of low-dimensional subspaces. Current subspace clustering approaches are usually based on a two-stage framework. In the first stage, an affinity…

Long-context models are essential for many applications but face inefficiencies in loading large KV caches during decoding. Prior methods enforce fixed token budgets for sparse attention, assuming a set number of tokens can approximate full…

Feature fusion modules from encoder and self-attention module have been adopted in semantic segmentation. However, the computation of these modules is costly and has operational limitations in real-time environments. In addition,…

We establish the universal approximation capability of single-layer, single-head self- and cross-attention mechanisms with minimal attached structures. Our key insight is to interpret single-head attention as an input domain-partition…

Subspace clustering refers to the problem of segmenting data drawn from a union of subspaces. State-of-the-art approaches for solving this problem follow a two-stage approach. In the first step, an affinity matrix is learned from the data…

Large Language Models (LLMs) face efficiency bottlenecks due to the quadratic complexity of the attention mechanism when processing long contexts. Sparse attention methods offer a promising solution, but existing approaches often suffer…

Recent works of point clouds show that mulit-frame spatio-temporal modeling outperforms single-frame versions by utilizing cross-frame information. In this paper, we further improve spatio-temporal point cloud feature learning with a…

Transformers have sprung up in the field of computer vision. In this work, we explore whether the core self-attention module in Transformer is the key to achieving excellent performance in image recognition. To this end, we build an…

In this study, we introduce \textbf{AttendSeg}, a low-precision, highly compact deep neural network tailored for on-device semantic segmentation. AttendSeg possesses a self-attention network architecture comprising of light-weight attention…

Pixel-level annotation demands expensive human efforts and limits the performance of deep networks that usually benefits from more such training data. In this work we aim to achieve high quality instance and semantic segmentation results…