Related papers: SEA: Bridging the Gap Between One- and Two-stage D…

Achieving joint learning of Salient Object Detection (SOD) and Camouflaged Object Detection (COD) is extremely challenging due to their distinct object characteristics, i.e., saliency and camouflage. The only preliminary research treats…

Deep features extracted from certain layers of a pre-trained deep model show superior performance over the conventional hand-crafted features. Compared with fine-tuning or linear probing that can explore diverse augmentations, \eg, random…

Knowledge distillation is an effective method for model compression. However, it is still a challenging topic to apply knowledge distillation to detection tasks. There are two key points resulting in poor distillation performance for…

Weakly supervised semantic segmentation is a challenging task as it only takes image-level information as supervision for training but produces pixel-level predictions for testing. To address such a challenging task, most recent…

Pixel-level annotation demands expensive human efforts and limits the performance of deep networks that usually benefits from more such training data. In this work we aim to achieve high quality instance and semantic segmentation results…

In instance-level detection tasks (e.g., object detection), reducing input resolution is an easy option to improve runtime efficiency. However, this option traditionally hurts the detection performance much. This paper focuses on boosting…

3D object detection task from lidar or camera sensors is essential for autonomous driving. Pioneer attempts at multi-modality fusion complement the sparse lidar point clouds with rich semantic texture information from images at the cost of…

Knowledge distillation has shown great success in classification, however, it is still challenging for detection. In a typical image for detection, representations from different locations may have different contributions to detection…

Knowledge distillation has emerged as a highly effective method for bridging the representation discrepancy between large-scale models and lightweight models. Prevalent approaches involve leveraging appropriate metrics to minimize the…

Block attention, which processes the input as separate blocks that cannot attend to one another, offers significant potential to improve KV cache reuse in long-context scenarios such as Retrieval-Augmented Generation (RAG). However, its…

Although deep CNNs have brought significant improvement to image saliency detection, most CNN based models are sensitive to distortion such as compression and noise. In this paper, we propose an end-to-end generic salient object…

While nowadays deep neural networks achieve impressive performances on semantic segmentation tasks, they are usually trained by optimizing pixel-wise losses such as cross-entropy. As a result, the predictions outputted by such networks…

Continual Semantic Segmentation (CSS) requires learning new classes without forgetting previously acquired knowledge, addressing the fundamental challenge of catastrophic forgetting in dense prediction tasks. However, existing CSS methods…

Recent studies have highlighted the potential of adapting the Segment Anything Model (SAM) for various downstream tasks. However, constructing a more powerful and generalizable encoder to further enhance performance remains an open…

One-stage object detectors such as SSD or YOLO already have shown promising accuracy with small memory footprint and fast speed. However, it is widely recognized that one-stage detectors have difficulty in detecting small objects while they…

In this paper, we focus on the challenging multicategory instance segmentation problem in remote sensing images (RSIs), which aims at predicting the categories of all instances and localizing them with pixel-level masks. Although many…

We propose a novel method for semantic segmentation, the task of labeling each pixel in an image with a semantic class. Our method combines the advantages of the two main competing paradigms. Methods based on region classification offer…

Panoptic segmentation (PS) is a complex scene understanding task that requires providing high-quality segmentation for both thing objects and stuff regions. Previous methods handle these two classes with semantic and instance segmentation…

In this paper, we introduce a novel knowledge distillation approach for the semantic segmentation task. Unlike previous methods that rely on power-trained teachers or other modalities to provide additional knowledge, our approach does not…

Medical image segmentation, or computing voxelwise semantic masks, is a fundamental yet challenging task to compute a voxel-level semantic mask. To increase the ability of encoder-decoder neural networks to perform this task across large…