相关论文: Learning of Proto-object Representations via Fixat…

In this paper we evaluate the quality of the activation layers of a convolutional neural network (CNN) for the gen- eration of object proposals. We generate hypotheses in a sliding-window fashion over different activation layers and show…

Face super-resolution is a technology that transforms a low-resolution face image into the corresponding high-resolution one. In this paper, we build a novel parsing map guided face super-resolution network which extracts the face prior…

Superpixel-based methodologies have become increasingly popular in computer vision, especially when the computation is too expensive in time or memory to perform with a large number of pixels or features. However, rarely is superpixel…

Here we present DeepGaze II, a model that predicts where people look in images. The model uses the features from the VGG-19 deep neural network trained to identify objects in images. Contrary to other saliency models that use deep features,…

Object detection is a fundamental problem in computer vision, aiming at locating and classifying objects in image. Although current devices can easily take very high-resolution images, current approaches of object detection seldom consider…

In this paper we study the application of convolutional neural networks for jointly detecting objects depicted in still images and estimating their 3D pose. We identify different feature representations of oriented objects, and energies…

We propose a new method for fine-grained few-shot recognition via deep object parsing. In our framework, an object is made up of K distinct parts and for each part, we learn a dictionary of templates, which is shared across all instances…

Recent works in self-supervised learning have demonstrated strong performance on scene-level dense prediction tasks by pretraining with object-centric or region-based correspondence objectives. In this paper, we present Region-to-Object…

Despite significant recent progress, machine vision systems lag considerably behind their biological counterparts in performance, scalability, and robustness. A distinctive hallmark of the brain is its ability to automatically discover and…

Capturing contextual dependencies has proven useful to improve the representational power of deep neural networks. Recent approaches that focus on modeling global context, such as self-attention and non-local operation, achieve this goal by…

Crack detection is critical for concrete infrastructure safety, but real-world cracks often appear in low-light environments like tunnels and bridge undersides, degrading computer vision segmentation accuracy. Pixel-level annotation of…

State-of-the-art object detectors usually learn multi-scale representations to get better results by employing feature pyramids. However, the current designs for feature pyramids are still inefficient to integrate the semantic information…

Low-shot visual learning---the ability to recognize novel object categories from very few examples---is a hallmark of human visual intelligence. Existing machine learning approaches fail to generalize in the same way. To make progress on…

Recurrent feedback connections in the mammalian visual system have been hypothesized to play a role in synthesizing input in the theoretical framework of analysis by synthesis. The comparison of internally synthesized representation with…

Deep convolutional neural networks have recently achieved state-of-the-art performance on a number of image recognition benchmarks, including the ImageNet Large-Scale Visual Recognition Challenge (ILSVRC-2012). The winning model on the…

In this paper we propose an ensemble of local and deep features for object classification. We also compare and contrast effectiveness of feature representation capability of various layers of convolutional neural network. We demonstrate…

Recent work has shown that object-centric representations can greatly help improve the accuracy of learning dynamics while also bringing interpretability. In this work, we take this idea one step further, ask the following question: "can…

Object recognition has seen significant progress in the image domain, with focus primarily on 2D perception. We propose to leverage existing large-scale datasets of 3D models to understand the underlying 3D structure of objects seen in an…

The aim of object-centric vision is to construct an explicit representation of the objects in a scene. This representation is obtained via a set of interchangeable modules called \emph{slots} or \emph{object files} that compete for local…

Psychovisual models suggest human vision decouples low-level feature extraction from higher cognition by first forming intermediate abstractions. In contrast, deep learning-based vision models routinely extract and aggregate features using…