相关论文: Pixel-Grounded Prototypical Part Networks

We model the process of human full interpretation of object images, namely the ability to identify and localize all semantic features and parts that are recognized by human observers. The task is approached by dividing the interpretation of…

The human vision and perception system is inherently incremental where new knowledge is continually learned over time whilst existing knowledge is retained. On the other hand, deep learning networks are ill-equipped for incremental…

Object detection is a challenging task in visual understanding domain, and even more so if the supervision is to be weak. Recently, few efforts to handle the task without expensive human annotations is established by promising deep neural…

Inspired by CapsNet's routing-by-agreement mechanism with its ability to learn object properties, we explore if those properties in turn can determine new properties of the objects, such as the locations. We then propose a CapsNet…

Deep-predictive-coding networks (DPCNs) are hierarchical, generative models. They rely on feed-forward and feed-back connections to modulate latent feature representations of stimuli in a dynamic and context-sensitive manner. A crucial…

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…

Models for image representation learning are typically designed for either recognition or generation. Various forms of contrastive learning help models learn to convert images to embeddings that are useful for classification, detection, and…

We present ProtoViT, a method for interpretable image classification combining deep learning and case-based reasoning. This method classifies an image by comparing it to a set of learned prototypes, providing explanations of the form ``this…

In the past five years we have observed the rise of incredibly well performing feed-forward neural networks trained supervisedly for vision related tasks. These models have achieved super-human performance on object recognition,…

The presence of occlusions has provided substantial challenges to typically-powerful object recognition algorithms. Additional sources of information can be extremely valuable to reduce errors caused by occlusions. Scene context is known to…

We introduce Graph-Structured Sum-Product Networks (GraphSPNs), a probabilistic approach to structured prediction for problems where dependencies between latent variables are expressed in terms of arbitrary, dynamic graphs. While many…

Transparent objects present multiple distinct challenges to visual perception systems. First, their lack of distinguishing visual features makes transparent objects harder to detect and localize than opaque objects. Even humans find certain…

Learning the physical dynamics of deformable objects with particle-based representation has been the objective of many computational models in machine learning. While several state-of-the-art models have achieved this objective in simulated…

Part-prototype networks (e.g., ProtoPNet, ProtoTree, and ProtoPool) have attracted broad research interest for their intrinsic interpretability and comparable accuracy to non-interpretable counterparts. However, recent works find that the…

Most modern convolutional neural networks (CNNs) used for object recognition are built using the same principles: Alternating convolution and max-pooling layers followed by a small number of fully connected layers. We re-evaluate the state…

We study end-to-end learning strategies for 3D shape inference from images, in particular from a single image. Several approaches in this direction have been investigated that explore different shape representations and suitable learning…

Human body parsing remains a challenging problem in natural scenes due to multi-instance and inter-part semantic confusions as well as occlusions. This paper proposes a novel approach to decomposing multiple human bodies into semantic part…

Models based on Convolutional Neural Networks (CNNs) have been proven very successful for semantic segmentation and object parsing that yield hierarchies of features. Our key insight is to build convolutional networks that take input of…

The process of aligning a pair of shapes is a fundamental operation in computer graphics. Traditional approaches rely heavily on matching corresponding points or features to guide the alignment, a paradigm that falters when significant…

Nowadays, service robots are appearing more and more in our daily life. For this type of robot, open-ended object category learning and recognition is necessary since no matter how extensive the training data used for batch learning, the…