相关论文: Simplified priors for Object-Centric Learning

Salient object detection (SOD) is a task that involves identifying and segmenting the most visually prominent object in an image. Existing solutions can accomplish this use a multi-scale feature fusion mechanism to detect the global context…

Prompt learning has emerged as an efficient and effective approach for transferring foundational Vision-Language Models (e.g., CLIP) to downstream tasks. However, current methods tend to overfit to seen categories, thereby limiting their…

Computer vision algorithms with pixel-wise labeling tasks, such as semantic segmentation and salient object detection, have gone through a significant accuracy increase with the incorporation of deep learning. Deep segmentation methods…

We propose a scalable method for semi-supervised (transductive) learning from massive network-structured datasets. Our approach to semi-supervised learning is based on representing the underlying hypothesis as a graph signal with small…

Most convolutional neural networks (CNNs) for image classification use a global average pooling (GAP) followed by a fully-connected (FC) layer for output logits. However, this spatial aggregation procedure inherently restricts the…

We present a novel attention-based mechanism to learn enhanced point features for point cloud processing tasks, e.g., classification and segmentation. Unlike prior works, which were trained to optimize the weights of a pre-selected set of…

Although DALL-E has shown an impressive ability of composition-based systematic generalization in image generation, it requires the dataset of text-image pairs and the compositionality is provided by the text. In contrast, object-centric…

Humans have a unique ability to learn new representations from just a handful of examples with little to no supervision. Deep learning models, however, require an abundance of data and supervision to perform at a satisfactory level.…

We investigate the emergence of objects in visual perception in the absence of any semantic annotation. The resulting model has received no supervision, does not use any pre-trained features, and yet it can segment the domain of an image…

Humans are remarkably good at understanding and reasoning about complex visual scenes. The capability to decompose low-level observations into discrete objects allows us to build a grounded abstract representation and identify the…

Convolutions are a fundamental building block of modern computer vision systems. Recent approaches have argued for going beyond convolutions in order to capture long-range dependencies. These efforts focus on augmenting convolutional models…

Slot-based object-centric learning represents an image as a set of latent slots with a decoder that combines them into an image or features. The decoder specifies how slots are combined into an output, but the slot set is typically fixed:…

Recently many effective attention modules are proposed to boot the model performance by exploiting the internal information of convolutional neural networks in computer vision. In general, many previous works ignore considering the design…

Selective attention helps us focus on task-relevant aspects in the constant flood of our sensory input. This constraint in our perception allows us to robustly generalize under distractions and to new compositions of perceivable concepts.…

The scarcity of labeled action data poses a considerable challenge for developing machine learning algorithms for robotic object manipulation. It is expensive and often infeasible for a robot to interact with many objects. Conversely,…

Advanced methods of applying deep learning to structured data such as graphs have been proposed in recent years. In particular, studies have focused on generalizing convolutional neural networks to graph data, which includes redefining the…

Medical image segmentation is a fundamental task for medical image analysis and surgical planning. In recent years, UNet-based networks have prevailed in the field of medical image segmentation. However, convolution-neural networks (CNNs)…

Video Panoptic Segmentation (VPS) aims at assigning a class label to each pixel, uniquely segmenting and identifying all object instances consistently across all frames. Classic solutions usually decompose the VPS task into several…

Object-centric representation learning aims to decompose visual scenes into fixed-size vectors called "slots" or "object files", where each slot captures a distinct object. Current state-of-the-art object-centric models have shown…

Self-attention based Transformer has demonstrated the state-of-the-art performances in a number of natural language processing tasks. Self-attention is able to model long-term dependencies, but it may suffer from the extraction of…