Related papers: Modality-Aware Zero-Shot Pruning and Sparse Attent…
Continual test-time adaptive object detection (CTTA-OD) aims to online adapt a source pre-trained detector to ever-changing environments during inference under continuous domain shifts. Most existing CTTA-OD methods prioritize effectiveness…
Transformers' quadratic complexity with respect to the input sequence length has motivated a body of work on efficient sparse approximations to softmax. An alternative path, used by entmax transformers, consists of having built-in exact…
Few-shot, fine-grained classification in computer vision poses significant challenges due to the need to differentiate subtle class distinctions with limited data. This paper presents a novel method that enhances the Contrastive…
Sparse attention, which selectively attends to a subset of tokens in the context was supposed to be efficient. However, its theoretical reduction in FLOPs has rarely translated into wall-clock speed-up over its dense attention counterparts…
The quadratic complexity of self-attention in Transformer models remains a significant bottleneck for processing long sequences and deploying large language models efficiently. For this approach, there has been significant research into…
This paper presents a parameter-efficient prompt tuning method, named PPT, to adapt a large multi-modal model for 3D point cloud understanding. Existing strategies are quite expensive in computation and storage, and depend on time-consuming…
Self-attention-based transformer models have achieved tremendous success in the domain of natural language processing. Despite their efficacy, accelerating the transformer is challenging due to its quadratic computational complexity and…
Zero-shot point cloud segmentation aims to make deep models capable of recognizing novel objects in point cloud that are unseen in the training phase. Recent trends favor the pipeline which transfers knowledge from seen classes with labels…
In this research, an effort is made to address microgrid systems' operational challenges, characterized by power oscillations that eventually contribute to grid instability. An integrated strategy is proposed, leveraging the strengths of…
In Federated Learning (FL), training is conducted on client devices, typically with limited computational resources and storage capacity. To address these constraints, we propose an automatic pruning scheme tailored for FL systems. Our…
Recent advances in large language models highlighted the excessive quadratic cost of self-attention. Despite the significant research efforts, subquadratic attention methods still suffer from inferior performance in practice. We hypothesize…
Graph transformers achieve strong results on molecular and long-range reasoning tasks, yet remain hampered by over-smoothing (the progressive collapse of node representations with depth) and attention entropy degeneration. We observe that…
Deep Neural Networks (DNNs) have achieved remarkable success in many computer vision tasks recently, but the huge number of parameters and the high computation overhead hinder their deployments on resource-constrained edge devices. It is…
The missing modality problem poses a fundamental challenge in multimodal sentiment analysis, significantly degrading model accuracy and generalization in real world scenarios. Existing approaches primarily improve robustness through prompt…
Transformers have shown superior performance on various computer vision tasks with their capabilities to capture long-range dependencies. Despite the success, it is challenging to directly apply Transformers on point clouds due to their…
Due to its significant capability of modeling long-range dependencies, vision transformer (ViT) has achieved promising success in both holistic and occluded person re-identification (Re-ID) tasks. However, the inherent problems of…
Diffusion Transformers, particularly for video generation, achieve remarkable quality but suffer from quadratic attention complexity, leading to prohibitive latency. Existing acceleration methods face a fundamental trade-off: dynamically…
Understanding intricate and fast-paced movements of body parts is essential for the recognition and translation of sign language. The inclusion of additional information intended to identify and locate the moving body parts has been an…
Multi-modality image fusion, particularly infrared and visible, plays a crucial role in integrating diverse modalities to enhance scene understanding. Although early research prioritized visual quality, preserving fine details and adapting…
Various forms of sparse attention have been explored to mitigate the quadratic computational and memory cost of the attention mechanism in transformers. We study sparse transformers not through a lens of efficiency but rather in terms of…