Related papers: Recurrent Glimpse-based Decoder for Detection with…

Referring image segmentation aims to segment an object referred to by natural language expression from an image. The primary challenge lies in the efficient propagation of fine-grained semantic information from textual features to visual…

Synthetic Aperture Radar (SAR) target detection has long been impeded by inherent speckle noise and the prevalence of diminutive, ambiguous targets. While deep neural networks have advanced SAR target detection, their intrinsic…

Surface defect detection is an extremely crucial step to ensure the quality of industrial products. Nowadays, convolutional neural networks (CNNs) based on encoder-decoder architecture have achieved tremendous success in various defect…

Referring image segmentation segments an image from a language expression. With the aim of producing high-quality masks, existing methods often adopt iterative learning approaches that rely on RNNs or stacked attention layers to refine…

Diffusion transformers (DiTs) have emerged as a dominant architecture for text-to-image generation, yet their performance drops when generating at resolutions beyond their training range. Existing training-free approaches mitigate this by…

Real-time object detection has achieved substantial progress through meticulously designed architectures and optimization strategies. However, the pursuit of high-speed inference via lightweight network designs often leads to degraded…

Existing studies on salient object detection (SOD) focus on extracting distinct objects with edge information and aggregating multi-level features to improve SOD performance. To achieve satisfactory performance, the methods employ refined…

Although open-vocabulary object detectors can generalize to unseen categories, they still rely on predefined textual prompts or classifier heads during inference. Recent generative object detectors address this limitation by coupling an…

RT-DETR is the first real-time end-to-end transformer-based object detector. Its efficiency comes from the framework design and the Hungarian matching. However, compared to dense supervision detectors like the YOLO series, the Hungarian…

Change detection, i.e. identification per pixel of changes for some classes of interest from a set of bi-temporal co-registered images, is a fundamental task in the field of remote sensing. It remains challenging due to unrelated forms of…

Panoptic segmentation involves a combination of joint semantic segmentation and instance segmentation, where image contents are divided into two types: things and stuff. We present Panoptic SegFormer, a general framework for panoptic…

In the domain of computer vision, Parameter-Efficient Tuning (PET) is increasingly replacing the traditional paradigm of pre-training followed by full fine-tuning. PET is particularly favored for its effectiveness in large foundation…

Recent developments in transformer models for visual data have led to significant improvements in recognition and detection tasks. In particular, using learnable queries in place of region proposals has given rise to a new class of…

Recent self-supervised pretraining methods for object detection largely focus on pretraining the backbone of the object detector, neglecting key parts of detection architecture. Instead, we introduce DETReg, a new self-supervised method…

Object detection has made tremendous strides in computer vision. Small object detection with appearance degradation is a prominent challenge, especially for aerial observations. To collect sufficient positive/negative samples for heuristic…

Accurate tracking is still a challenging task due to appearance variations, pose and view changes, and geometric deformations of target in videos. Recent anchor-free trackers provide an efficient regression mechanism but fail to produce…

In this study, we introduce an innovative EEG signal reconstruction sub-module designed to enhance the performance of deep learning models on EEG eye-tracking tasks. This sub-module can integrate with all Encoder-Classifier-based deep…

DETR is a novel end-to-end transformer architecture object detector, which significantly outperforms classic detectors when scaling up. In this paper, we focus on the compression of DETR with knowledge distillation. While knowledge…

The integration of Artificial Intelligence into the modern educational system is rapidly evolving, particularly in monitoring student behavior in classrooms, a task traditionally dependent on manual observation. This conventional method is…

Modern detection transformers (DETRs) use a set of object queries to predict a list of bounding boxes, sort them by their classification confidence scores, and select the top-ranked predictions as the final detection results for the given…