Related papers: X-Paste: Revisiting Scalable Copy-Paste for Instan…

We introduce a new method to efficiently create text-to-image models from a pre-trained CLIP and StyleGAN. It enables text driven sampling with an existing generative model without any external data or fine-tuning. This is achieved by…

In this paper, we propose a data augmentation method for action recognition using instance segmentation. Although many data augmentation methods have been proposed for image recognition, few of them are tailored for action recognition. Our…

Recent advances in self-supervised contrastive learning yield good image-level representation, which favors classification tasks but usually neglects pixel-level detailed information, leading to unsatisfactory transfer performance to dense…

Semantic segmentation and object detection research have recently achieved rapid progress. However, the former task has no notion of different instances of the same object, and the latter operates at a coarse, bounding-box level. We propose…

We propose CLIP-Lite, an information efficient method for visual representation learning by feature alignment with textual annotations. Compared to the previously proposed CLIP model, CLIP-Lite requires only one negative image-text sample…

We present a robotic system for picking a target from a pile of objects that is capable of finding and grasping the target object by removing obstacles in the appropriate order. The fundamental idea is to segment instances with both visible…

Transfer learning enables the sharing of common knowledge among models for a variety of downstream tasks, but traditional methods suffer in limited training data settings and produce narrow models incapable of effectively generalizing under…

Occlusion is a long-standing problem in computer vision, particularly in instance segmentation. ACM MMSports 2023 DeepSportRadar has introduced a dataset that focuses on segmenting human subjects within a basketball context and a…

Existing 3D instance segmentation methods are predominated by the bottom-up design -- manually fine-tuned algorithm to group points into clusters followed by a refinement network. However, by relying on the quality of the clusters, these…

We propose instance segmentation as a useful tool for image analysis in materials science. Instance segmentation is an advanced technique in computer vision which generates individual segmentation masks for every object of interest that is…

Due to the few annotated labels of 3D point clouds, how to learn discriminative features of point clouds to segment object instances is a challenging problem. In this paper, we propose a simple yet effective 3D instance segmentation…

Image-text contrastive learning models such as CLIP have demonstrated strong task transfer ability. The high generality and usability of these visual models is achieved via a web-scale data collection process to ensure broad concept…

Diffusion models have become prominent in creating high-quality images. However, unlike GAN models celebrated for their ability to edit images in a disentangled manner, diffusion-based text-to-image models struggle to achieve the same level…

3D Gaussian Splatting (GS) enables fast and high-quality scene reconstruction, but it lacks an object-consistent and semantically aware structure. We propose Split&Splat, a framework for panoptic scene reconstruction using 3DGS. Our…

The current state-of-the-art methods in 3D instance segmentation typically involve a clustering step, despite the tendency towards heuristics, greedy algorithms, and a lack of robustness to the changes in data statistics. In contrast, we…

The continual learning setting aims to learn new tasks over time without forgetting the previous ones. The literature reports several significant efforts to tackle this problem with limited or no access to previous task data. Among such…

Recent attention in instance segmentation has focused on query-based models. Despite being non-maximum suppression (NMS)-free and end-to-end, the superiority of these models on high-accuracy real-time benchmarks has not been well…

One of the challenges of supervised learning training is the need to procure an substantial amount of tagged data. A well-known method of solving this problem is to use synthetic data in a copy-paste fashion, so that we cut objects and…

Diffusion models excel at photorealistic synthesis but struggle with precise object counts, especially in high-density settings. We introduce COUNTLOOP, a training-free framework that achieves precise instance control through iterative,…

Semantic segmentation has a broad range of applications, but its real-world impact has been significantly limited by the prohibitive annotation costs necessary to enable deployment. Segmentation methods that forgo supervision can side-step…