Related papers: Efficient-SAM2: Accelerating SAM2 with Object-Awar…
Scaling Transformers to ultra-long contexts is bottlenecked by the $O(n^2 d)$ cost of self-attention. Existing methods reduce this cost along the sequence axis through local windows, kernel approximations, or token-level sparsity, but these…
This paper proposes a deep learning model to efficiently detect salient regions in videos. It addresses two important issues: (1) deep video saliency model training with the absence of sufficiently large and pixel-wise annotated video data,…
Current CNN-based super-resolution (SR) methods process all locations equally with computational resources being uniformly assigned in space. However, since missing details in low-resolution (LR) images mainly exist in regions of edges and…
Single-point annotation in visual tasks, with the goal of minimizing labelling costs, is becoming increasingly prominent in research. Recently, visual foundation models, such as Segment Anything (SAM), have gained widespread usage due to…
Space-time memory (STM) based video object segmentation (VOS) networks usually keep increasing memory bank every several frames, which shows excellent performance. However, 1) the hardware cannot withstand the ever-increasing memory…
Sharpness-Aware Minimization (SAM) improves model generalization but doubles the computational cost of Stochastic Gradient Descent (SGD) by requiring twice the gradient calculations per optimization step. To mitigate this, we propose…
Segmentation of indicated targets aids in the precise analysis of optical coherence tomography angiography (OCTA) samples. Existing segmentation methods typically perform on 2D projection targets, making it challenging to capture the…
Segmenting objects with complex shapes, such as wires, bicycles, or structural grids, remains a significant challenge for current segmentation models, including the Segment Anything Model (SAM) and its high-quality variant SAM-HQ. These…
We present Perceive Anything Model (PAM), a conceptually straightforward and efficient framework for comprehensive region-level visual understanding in images and videos. Our approach extends the powerful segmentation model SAM 2 by…
We propose a simple and efficient algorithm for learning sparse invariant representations from unlabeled data with fast inference. When trained on short movies sequences, the learned features are selective to a range of orientations and…
Recent advancements in foundation models, such as the Segment Anything Model (SAM), have shown strong performance in various vision tasks, particularly image segmentation, due to their impressive zero-shot segmentation capabilities.…
Large Vision-Language Models (VLMs) have achieved remarkable success in multi-modal reasoning, but their inference time efficiency remains a significant challenge due to the memory overhead during decoding, especially when the query and…
Segment anything model (SAM) has achieved great success in the field of natural image segmentation. Nevertheless, SAM tends to consider shadows as background and therefore does not perform segmentation on them. In this paper, we propose…
Recently, promptable segmentation models, such as the Segment Anything Model (SAM), have demonstrated robust zero-shot generalization capabilities on static images. These promptable models exhibit denoising abilities for imprecise prompt…
Recently, Sharpness-Aware Minimization (SAM), which connects the geometry of the loss landscape and generalization, has demonstrated significant performance boosts on training large-scale models such as vision transformers. However, the…
Deep convolutional neural network significantly boosted the capability of salient object detection in handling large variations of scenes and object appearances. However, convolution operations seek to generate strong responses on…
Learning descriptive spatio-temporal object models from data is paramount for the task of semi-supervised video object segmentation. Most existing approaches mainly rely on models that estimate the segmentation mask based on a reference…
World model based planning has significantly improved decision-making in complex environments by enabling agents to simulate future states and make informed choices. This computational burden is particularly restrictive in robotics, where…
Performing a real-time and accurate instrument segmentation from videos is of great significance for improving the performance of robotic-assisted surgery. We identify two important clues for surgical instrument perception, including local…
In this paper, we propose a novel Visual Reference Prompt (VRP) encoder that empowers the Segment Anything Model (SAM) to utilize annotated reference images as prompts for segmentation, creating the VRP-SAM model. In essence, VRP-SAM can…