Related papers: Dynamic Embeddings with Task-Oriented prompting

Parameter-efficient fine-tuning (PEFT) has emerged as an effective method for adapting pre-trained language models to various tasks efficiently. Recently, there has been a growing interest in transferring knowledge from one or multiple…

The Transformer-based detectors (i.e., DETR) have demonstrated impressive performance on end-to-end object detection. However, transferring DETR to different data distributions may lead to a significant performance degradation. Existing…

Uncovering the underlying ordinary differential equations (ODEs) that govern dynamic systems is crucial for advancing our understanding of complex phenomena. Traditional symbolic regression methods often struggle to capture the temporal…

Dynamic neural network is an emerging research topic in deep learning. With adaptive inference, dynamic models can achieve remarkable accuracy and computational efficiency. However, it is challenging to design a powerful dynamic detector,…

Multi-Task Learning (MTL) involves the concurrent training of multiple tasks, offering notable advantages for dense prediction tasks in computer vision. MTL not only reduces training and inference time as opposed to having multiple…

Multi-task learning (MTL) has gained significant popularity in recommender systems as it enables simultaneous optimization of multiple objectives. A key challenge in MTL is negative transfer, but existing studies explored negative transfer…

Learning effective region embeddings from heterogeneous urban data underpins key urban computing tasks (e.g., crime prediction, resource allocation). However, prevailing two-stage methods yield task-agnostic representations, decoupling them…

Robust imitation learning using disturbance injections overcomes issues of limited variation in demonstrations. However, these methods assume demonstrations are optimal, and that policy stabilization can be learned via simple augmentations.…

Pre-training has been investigated to improve the efficiency and performance of training neural operators in data-scarce settings. However, it is largely in its infancy due to the inherent complexity and diversity, such as long…

Diffusion models enable high-quality virtual try-on (VTO) with their established image synthesis abilities. Despite the extensive end-to-end training of large pre-trained models involved in current VTO methods, real-world applications often…

Despite the promising results, existing oriented object detection methods usually involve heuristically designed rules, e.g., RRoI generation, rotated NMS. In this paper, we propose an end-to-end framework for oriented object detection,…

Oblique Decision Tree (ODT) separates the feature space by linear projections, as opposed to the conventional Decision Tree (DT) that forces axis-parallel splits. ODT has been proven to have a stronger representation ability than DT, as it…

The objective of dense material segmentation is to identify the material categories for every image pixel. Recent studies adopt image patches to extract material features. Although the trained networks can improve the segmentation…

With the emergence of large pre-trained vison-language model like CLIP, transferable representations can be adapted to a wide range of downstream tasks via prompt tuning. Prompt tuning tries to probe the beneficial information for…

Initially introduced as a machine translation model, the Transformer architecture has now become the foundation for modern deep learning architecture, with applications in a wide range of fields, from computer vision to natural language…

Incremental object detection (IOD) aims to sequentially learn new classes, while maintaining the capability to locate and identify old ones. As the training data arrives with annotations only with new classes, IOD suffers from catastrophic…

Auxiliary tasks facilitate learning in situations where data is scarce or the principal task of interest is extremely complex. This idea is primarily inspired by the improved generalization capability induced by solving multiple tasks…

Recent token reduction methods for Vision Transformers (ViTs) incorporate token merging, which measures the similarities between token embeddings and combines the most similar pairs. However, their merging policies are directly dependent on…

Multi-object tracking (MOT) is the problem of tracking the state of an unknown and time-varying number of objects using noisy measurements, with important applications such as autonomous driving, tracking animal behavior, defense systems,…

The Decision Transformer (DT) has established a powerful sequence modeling approach to offline reinforcement learning. It conditions its action predictions on Return-to-Go (RTG), using it both to distinguish trajectory quality during…