Related papers: Simplified priors for Object-Centric Learning
Robotic manipulation in complex open-world scenarios requires both reliable physical manipulation skills and effective and generalizable perception. In this paper, we propose a method where general purpose pretrained visual models serve as…
Segmentation is vital for ophthalmology image analysis. But its various modal images hinder most of the existing segmentation algorithms applications, as they rely on training based on a large number of labels or hold weak generalization…
Aiming to predict the complete shapes of partially occluded objects, amodal segmentation is an important step towards visual intelligence. With crucial significance, practical prior knowledge derives from sufficient training, while limited…
Recent advances in image-level self-supervised learning (SSL) have made significant progress, yet learning dense representations for patches remains challenging. Mainstream methods encounter an over-dispersion phenomenon that patches from…
An intelligent system capable of continual learning is one that can process and extract knowledge from potentially infinitely long streams of pattern vectors. The major challenge that makes crafting such a system difficult is known as…
In the face of scarcity in detailed training annotations, the ability to perform object localization tasks in real-time with weak-supervision is very valuable. However, the computational cost of generating and evaluating region proposals is…
Malicious image manipulation threatens public safety and requires efficient localization methods. Existing approaches depend on costly pixel-level annotations which make training expensive. Existing weakly supervised methods rely only on…
Achieving highly accurate and real-time 3D occupancy prediction from cameras is a critical requirement for the safe and practical deployment of autonomous vehicles. While this shift to sparse 3D representations solves the encoding…
Learning invariant representations from images is one of the hardest challenges facing computer vision. Spatial pooling is widely used to create invariance to spatial shifting, but it is restricted to convolutional models. In this paper, we…
The continual learning (CL) ability is vital for deploying large language models (LLMs) in the dynamic world. Existing methods devise the learning module to acquire task-specific knowledge with parameter-efficient tuning (PET) block and the…
The ability to distill object-centric abstractions from intricate visual scenes underpins human-level generalization. Despite the significant progress in object-centric learning methods, learning object-centric representations in the 3D…
Unsupervised video Object-Centric Learning (OCL) is promising as it enables object-level scene representation and understanding as we humans do. Mainstream video OCL methods adopt a recurrent architecture: An aggregator aggregates current…
Unsupervised multi-object representation learning depends on inductive biases to guide the discovery of object-centric representations that generalize. However, we observe that methods for learning these representations are either…
The recent advances in 3D sensing technology have made possible the capture of point clouds in significantly high resolution. However, increased detail usually comes at the expense of high storage, as well as computational costs in terms of…
Recent advances in self-supervised visual representation learning have paved the way for unsupervised methods tackling tasks such as object discovery and instance segmentation. However, discovering objects in an image with no supervision is…
Video Object-Centric Learning seeks to decompose raw videos into a small set of object slots, but existing slot-attention models often suffer from severe over-fragmentation. This is because the model is implicitly encouraged to occupy all…
Few-shot learning (FSL) aims to learn novel visual categories from very few samples, which is a challenging problem in real-world applications. Many methods of few-shot classification work well on general images to learn global…
We present a fast algorithm for training MaxPooling Convolutional Networks to segment images. This type of network yields record-breaking performance in a variety of tasks, but is normally trained on a computationally expensive…
Convolutional Neural Networks (CNNs) excel in local spatial pattern recognition. For many vision tasks, such as object recognition and segmentation, salient information is also present outside CNN's kernel boundaries. However, CNNs struggle…
Explanations obtained from transformer-based architectures in the form of raw attention, can be seen as a class-agnostic saliency map. Additionally, attention-based pooling serves as a form of masking the in feature space. Motivated by this…