Camouflaged object detection (COD) is the challenging task of identifying camouflaged
objects visually blended into surroundings. Albeit achieving remarkable success, existing …

This study addresses the Domain-Class Incremental Learning problem, a realistic but
challenging continual learning scenario where both the domain distribution and target …

This paper identifies significant redundancy in the query-key interactions within self-attention
mechanisms of diffusion transformer models, particularly during the early stages of …

Offline-to-online reinforcement learning (RL) is a training paradigm that combines pre-
training on a pre-collected dataset with fine-tuning in an online environment. However, the …

Oriented object detection, an emerging task in recent years, aims to identify and locate
objects across varied orientations. This requires the detector to accurately capture the …

This paper presents a general scheme for enhancing the convergence and performance of
DETR (DEtection TRansformer). We investigate the slow convergence problem in …

Transformer models are evolving rapidly in standard natural language processing tasks;
however, their application is drastically proliferating in computer vision (CV) as well …

DETR accomplishes end-to-end object detection through iteratively generating multiple
object candidates based on image features and promoting one candidate for each ground …

We introduce Hyper-YOLO, a new object detection method that integrates hypergraph
computations to capture the complex high-order correlations among visual features …

Significant progress has been achieved in the field of oriented object detection (OOD) in
recent years. Compared to natural images, objects in remote sensing images exhibit …