Related papers: MixFormer: End-to-End Tracking with Iterative Mixe…

Spiking Neural Networks have attracted significant attention in recent years due to their distinctive low-power characteristics. Meanwhile, Transformer models, known for their powerful self-attention mechanisms and parallel processing…

Though U-Net has achieved tremendous success in medical image segmentation tasks, it lacks the ability to explicitly model long-range dependencies. Therefore, Vision Transformers have emerged as alternative segmentation structures recently,…

In surveillance and search and rescue applications, it is important to perform multi-target tracking (MOT) in real-time on low-end devices. Today's MOT solutions employ deep neural networks, which tend to have high computation complexity.…

The Mixture of Experts (MoE) framework has become a popular architecture for large language models due to its superior performance over dense models. However, training MoEs from scratch in a large-scale regime is prohibitively expensive.…

Transformers have shown great potential in computer vision tasks. A common belief is their attention-based token mixer module contributes most to their competence. However, recent works show the attention-based module in Transformers can be…

Traditional multiple object tracking methods divide the task into two parts: affinity learning and data association. The separation of the task requires to define a hand-crafted training goal in affinity learning stage and a hand-crafted…

Robust object tracking requires knowledge of tracked objects' appearance, motion and their evolution over time. Although motion provides distinctive and complementary information especially for fast moving objects, most of the recent…

While recent years have witnessed astonishing improvements in visual tracking robustness, the advancements in tracking accuracy have been limited. As the focus has been directed towards the development of powerful classifiers, the problem…

Transformer architecture has been very successful long runner in the field of Deep Learning (DL) and Large Language Models (LLM) because of its powerful attention-based learning and parallel-natured architecture. As the models grow gigantic…

Cross-layer reuse of early attention projections can improve optimization and data efficiency, but it creates a structural conflict: the first layer must simultaneously act as a stable, reusable anchor for all deeper layers and as an…

In order to reduce the computational complexity of large language models, great efforts have been made to to improve the efficiency of transformer models such as linear attention and flash-attention. However, the model size and…

Template-based discriminative trackers are currently the dominant tracking methods due to their robustness and accuracy, and the Siamese-network-based methods that depend on cross-correlation operation between features extracted from…

Semantic segmentation based on sparse annotation has advanced in recent years. It labels only part of each object in the image, leaving the remainder unlabeled. Most of the existing approaches are time-consuming and often necessitate a…

Existing unified image segmentation models either employ a unified architecture across multiple tasks but use separate weights tailored to each dataset, or apply a single set of weights to multiple datasets but are limited to a single task.…

Multi-modal fusion is proven to be an effective method to improve the accuracy and robustness of speaker tracking, especially in complex scenarios. However, how to combine the heterogeneous information and exploit the complementarity of…

Vision Transformers (ViTs) have been shown to enhance visual recognition through modeling long-range dependencies with multi-head self-attention (MHSA), which is typically formulated as Query-Key-Value computation. However, the attention…

The escalating scale of Large Language Models (LLMs) necessitates efficient adaptation techniques. Model merging has gained prominence for its efficiency and controllability. However, existing merging techniques typically serve as post-hoc…

This paper presents CLUSTERFORMER, a universal vision model that is based on the CLUSTERing paradigm with TransFORMER. It comprises two novel designs: 1. recurrent cross-attention clustering, which reformulates the cross-attention mechanism…

Transformers and large language models (LLMs) have revolutionized machine learning, with attention mechanisms at the core of their success. As the landscape of attention variants expands, so too do the challenges of optimizing their…

Motion prediction plays an important role in autonomous driving. This study presents LMFormer, a lane-aware transformer network for trajectory prediction tasks. In contrast to previous studies, our work provides a simple mechanism to…