Related papers: MaX-DeepLab: End-to-End Panoptic Segmentation with…

Augmentation for dense prediction typically relies on either sample mixing or generative synthesis. Mixing improves robustness but misaligned masks yield soft label ambiguity. Diffusion synthesis increases apparent diversity but, when…

Recently, multi-modal vision-language foundation models have gained significant attention in the medical field. While these models offer great opportunities, they still face crucial challenges, such as the requirement for fine-grained…

Masked diffusion enables region-specific image synthesis but suffers from computational redundancy, since the entire image is processed each timestep even though only the masked region requires generation. To address this, we introduce…

Modern approaches typically formulate semantic segmentation as a per-pixel classification task, while instance-level segmentation is handled with an alternative mask classification. Our key insight: mask classification is sufficiently…

The realm of Weakly Supervised Instance Segmentation (WSIS) under box supervision has garnered substantial attention, showcasing remarkable advancements in recent years. However, the limitations of box supervision become apparent in its…

Self-attention is of vital importance in semantic segmentation as it enables modeling of long-range context, which translates into improved performance. We argue that it is equally important to model short-range context, especially to…

Labeling objects with pixel-wise segmentation requires a huge amount of human labor compared to bounding boxes. Most existing methods for weakly supervised instance segmentation focus on designing heuristic losses with priors from bounding…

Recently, pre-trained vision-language models have been increasingly used to tackle the challenging zero-shot segmentation task. Typical solutions follow the paradigm of first generating mask proposals and then adopting CLIP to classify…

The key to a successful cascade architecture for precise instance segmentation is to fully leverage the relationship between bounding box detection and mask segmentation across multiple stages. Although modern instance segmentation cascades…

This paper shows that Masking the Deep hierarchical features is an efficient self-supervised method, denoted as MaskDeep. MaskDeep treats each patch in the representation space as an independent instance. We mask part of patches in the…

We propose Mask Auto-Labeler (MAL), a high-quality Transformer-based mask auto-labeling framework for instance segmentation using only box annotations. MAL takes box-cropped images as inputs and conditionally generates their mask…

In this paper, we propose a new approach to applying point-level annotations for weakly-supervised panoptic segmentation. Instead of the dense pixel-level labels used by fully supervised methods, point-level labels only provide a single…

Panoptic segmentation is an important computer vision task, where the current state-of-the-art solutions require specialized components to perform well. We propose a simple generalist framework based on a deep encoder - shallow decoder…

Inverse protein folding generates valid amino acid sequences that can fold into a desired protein structure, with recent deep-learning advances showing strong potential and competitive performance. However, challenges remain, such as…

Panoptic segmentation, combining semantic and instance segmentation, stands as a cutting-edge computer vision task. Despite recent progress with deep learning models, the dynamic nature of real-world applications necessitates continual…

3D instance segmentation is crucial for understanding complex 3D environments, yet fully supervised methods require dense point-level annotations, resulting in substantial annotation costs and labor overhead. To mitigate this, box-level…

Data-driven decision-making processes increasingly utilize end-to-end learnable deep neural networks to render final decisions. Sometimes, the output of the forward functions in certain layers is determined by the solutions to mathematical…

Operating a robot in the open world requires a high level of robustness with respect to previously unseen environments. Optimally, the robot is able to adapt by itself to new conditions without human supervision, e.g., automatically…

In this paper, we aim to tackle the challenging few-shot segmentation task from a new perspective. Typical methods follow the paradigm to firstly learn prototypical features from support images and then match query features in pixel-level…

Accurately perceiving and tracking instances over time is essential for the decision-making processes of autonomous agents interacting safely in dynamic environments. With this intention, we propose Mask4Former for the challenging task of…