Related papers: CAR-SAM: Cross-Attention Reconstruction for Post-T…
Recently, Segment Anything Model (SAM) shows exceptional performance in generating high-quality object masks and achieving zero-shot image segmentation. However, as a versatile vision model, SAM is primarily trained with large-scale natural…
Fabric defect segmentation is integral to textile quality control. Despite this, the scarcity of high-quality annotated data and the diversity of fabric defects present significant challenges to the application of deep learning in this…
Segment Anything Model (SAM) is an advanced foundational model for image segmentation, which is gradually being applied to remote sensing images (RSIs). Due to the domain gap between RSIs and natural images, traditional methods typically…
Recent advancements in biomedical image analysis have been significantly driven by the Segment Anything Model (SAM). This transformative technology, originally developed for general-purpose computer vision, has found rapid application in…
Quantization-aware training (QAT) has achieved remarkable success in low-bit ($\leq$4-bit) quantization for classification networks. However, when applied to more complex visual tasks such as object detection and image segmentation,…
Model reparameterization is a widely accepted technique for improving inference speed without compromising performance. However, current Post-training Quantization (PTQ) methods often lead to significant accuracy degradation when applied to…
In this paper, we investigate the continual learning of Vision Transformers (ViT) for the challenging exemplar-free scenario, with special focus on how to efficiently distill the knowledge of its crucial self-attention mechanism (SAM). Our…
Transformer-based object detectors often struggle with occlusions, fine-grained localization, and computational inefficiency caused by fixed queries and dense attention. We propose DAMM, Dual-stream Attention with Multi-Modal queries, a…
Recent "segment anything" efforts show promise by learning from large-scale data, but adapting such models directly to medical images remains challenging due to the complexity of medical data, noisy annotations, and continual learning…
Extracting class activation maps (CAM) is a key step for weakly-supervised semantic segmentation (WSSS). The CAM of convolution neural networks fails to capture long-range feature dependency on the image and result in the coverage on only…
Diffusion models have achieved great success in image generation tasks. However, the lengthy denoising process and complex neural networks hinder their low-latency applications in real-world scenarios. Quantization can effectively reduce…
With the emergence of the Segment Anything Model (SAM) as a foundational model for image segmentation, its application has been extensively studied across various domains, including the medical field. However, its potential in the context…
Quantizing a floating-point neural network to its fixed-point representation is crucial for Learned Image Compression (LIC) because it improves decoding consistency for interoperability and reduces space-time complexity for implementation.…
The Segment Anything Model (SAM) marks a significant advancement in segmentation models, offering robust zero-shot abilities and dynamic prompting. However, existing medical SAMs are not suitable for the multi-scale nature of whole-slide…
Recently, Segment Anything Model (SAM) has become a research hotspot in the fields of multimedia and computer vision, which exhibits powerful yet versatile capabilities on various (un) conditional image segmentation tasks. Although SAM can…
This paper introduces CARSS (Cooperative Attention-guided Reinforcement Subpath Synthesis), a novel approach to address the Traveling Salesman Problem (TSP) by leveraging cooperative Multi-Agent Reinforcement Learning (MARL). CARSS…
Autoencoding, which aims to reconstruct the input images through a bottleneck latent representation, is one of the classic feature representation learning strategies. It has been shown effective as an auxiliary task for semi-supervised…
Self-supervised learning (SSL) with Vision Transformers (ViT) has shown immense potential in medical image analysis. However, the quadratic complexity ($\mathcal{O}(N^2)$) of standard self-attention poses a severe barrier for…
Recent segmentation methods, such as OCR and CPNet, utilizing "class level" information in addition to pixel features, have achieved notable success for boosting the accuracy of existing network modules. However, the extracted class-level…
Transformers have achieved state-of-the-art performance across language and vision tasks. This success drives the imperative to interpret their internal mechanisms with the dual goals of enhancing performance and improving behavioral…