Related papers: FlatteNet: A Simple Versatile Framework for Dense …

This paper addresses the challenge of establishing a bridge between deep convolutional neural networks and conventional object detection frameworks for accurate and efficient generic object detection. We introduce Dense Neural Patterns,…

Recent approaches for instance-aware semantic labeling have augmented convolutional neural networks (CNNs) with complex multi-task architectures or computationally expensive graphical models. We present a method that leverages a fully…

Weakly-supervised instance segmentation aims to detect and segment object instances precisely, given imagelevel labels only. Unlike previous methods which are composed of multiple offline stages, we propose Sequential Label Propagation and…

Lensless imaging has emerged as a potential solution towards realizing ultra-miniature cameras by eschewing the bulky lens in a traditional camera. Without a focusing lens, the lensless cameras rely on computational algorithms to recover…

Dense semantic forecasting anticipates future events in video by inferring pixel-level semantics of an unobserved future image. We present a novel approach that is applicable to various single-frame architectures and tasks. Our approach…

Weakly supervised semantic segmentation aims to achieve pixel-level predictions using image-level labels. Existing methods typically entangle semantic recognition and object localization, which often leads models to focus exclusively on…

We explore architectures for general pixel-level prediction problems, from low-level edge detection to mid-level surface normal estimation to high-level semantic segmentation. Convolutional predictors, such as the fully-convolutional…

Semantic labeling (or pixel-level land-cover classification) in ultra-high resolution imagery (< 10cm) requires statistical models able to learn high level concepts from spatial data, with large appearance variations. Convolutional Neural…

In this work, we introduce a Denser Feature Network (DenserNet) for visual localization. Our work provides three principal contributions. First, we develop a convolutional neural network (CNN) architecture which aggregates feature maps at…

The trend towards higher resolution remote sensing imagery facilitates a transition from land-use classification to object-level scene understanding. Rather than relying purely on spectral content, appearance-based image features come into…

Foreground segmentation algorithms aim segmenting moving objects from the background in a robust way under various challenging scenarios. Encoder-decoder type deep neural networks that are used in this domain recently perform impressive…

Hyperspectral Image (HSI) classification based on deep learning has been an attractive area in recent years. However, as a kind of data-driven algorithm, deep learning method usually requires numerous computational resources and…

Fully convolutional networks (FCN) has significantly improved the performance of many pixel-labeling tasks, such as semantic segmentation and depth estimation. However, it still remains non-trivial to thoroughly utilize the multi-level…

Recent progress of deep image classification models has provided great potential to improve state-of-the-art performance in related computer vision tasks. However, the transition to semantic segmentation is hampered by strict memory…

It is well accepted that image segmentation can benefit from utilizing multilevel cues. The paper focuses on utilizing the FCNN-based dense semantic predictions in the bottom-up image segmentation, arguing to take semantic cues into account…

In this paper, we propose deformable deep convolutional neural networks for generic object detection. This new deep learning object detection framework has innovations in multiple aspects. In the proposed new deep architecture, a new…

Fully convolutional networks (FCN) have achieved great success in human parsing in recent years. In conventional human parsing tasks, pixel-level labeling is required for guiding the training, which usually involves enormous human labeling…

Conventional deep convolutional neural networks (CNNs) apply convolution operators uniformly in space across all feature maps for hundreds of layers - this incurs a high computational cost for real-time applications. For many problems such…

This paper focuses on a novel and challenging vision task, dense video captioning, which aims to automatically describe a video clip with multiple informative and diverse caption sentences. The proposed method is trained without explicit…

We propose a novel deep architecture, SegNet, for semantic pixel wise image labelling. SegNet has several attractive properties; (i) it only requires forward evaluation of a fully learnt function to obtain smooth label predictions, (ii)…