Related papers: Top-Down Unsupervised Image Segmentation (it sound…

Neural Networks require large amounts of memory and compute to process high resolution images, even when only a small part of the image is actually informative for the task at hand. We propose a method based on a differentiable Top-K…

Many computer vision systems require low-cost segmentation algorithms based on deep learning, either because of the enormous size of input images or limited computational budget. Common solutions uniformly downsample the input images to…

Image attribution analysis seeks to highlight the feature representations learned by visual models such that the highlighted feature maps can reflect the pixel-wise importance of inputs. Gradient integration is a building block in the…

In recent years, with the development of deep neural networks, end-to-end optimized image compression has made significant progress and exceeded the classic methods in terms of rate-distortion performance. However, most learning-based image…

Each year, numerous segmentation and classification algorithms are invented or reused to solve problems where machine vision is needed. Generally, the efficiency of these algorithms is compared against the results given by one or many human…

We address the problem of segmenting an object given a natural language expression that describes it. Current techniques tackle this task by either (\textit{i}) directly or recursively merging linguistic and visual information in the…

We address the unsupervised learning of several interconnected problems in low-level vision: single view depth prediction, camera motion estimation, optical flow, and segmentation of a video into the static scene and moving regions. Our key…

Image segmentation is the foundation of several computer vision tasks, where pixel-wise knowledge is a prerequisite for achieving the desired target. Deep learning has shown promising performance in supervised image segmentation. However,…

Fine-grained image recognition is challenging because discriminative clues are usually fragmented, whether from a single image or multiple images. Despite their significant improvements, most existing methods still focus on the most…

The latest trend in the bottom-up perspective for arbitrary-shape scene text detection is to reason the links between text segments using Graph Convolutional Network (GCN). Notwithstanding, the performance of the best performing bottom-up…

Unsupervised video object segmentation aims to segment a target object in the video without a ground truth mask in the initial frame. This challenging task requires extracting features for the most salient common objects within a video…

Generalization to unseen degradations remains a fundamental challenge for low-level vision models. This paper aims to investigate the underlying mechanism of this failure, using image deraining as a primary case study due to its…

Co-part segmentation is an important problem in computer vision for its rich applications. We propose an unsupervised learning approach for co-part segmentation from images. For the training stage, we leverage motion information embedded in…

Fine-grained image classification remains challenging due to the large intra-class variance and small inter-class variance. Since the subtle visual differences are only in local regions of discriminative parts among subcategories, part…

Contour detection has been a fundamental component in many image segmentation and object detection systems. Most previous work utilizes low-level features such as texture or saliency to detect contours and then use them as cues for a…

This dissertation addresses visual scene understanding and enhances segmentation performance and generalization, training efficiency of networks, and holistic understanding. First, we investigate semantic segmentation in the context of…

Activity recognition from long unstructured egocentric photo-streams has several applications in assistive technology such as health monitoring and frailty detection, just to name a few. However, one of its main technical challenges is to…

Findings in recent years on the sensitivity of convolutional neural networks to additive noise, light conditions and to the wholeness of the training dataset, indicate that this technology still lacks the robustness needed for the…

Current semantic segmentation methods focus only on mining "local" context, i.e., dependencies between pixels within individual images, by context-aggregation modules (e.g., dilated convolution, neural attention) or structure-aware…

High-level visual brain regions contain subareas in which neurons appear to respond more strongly to examples of a particular semantic category, like faces or bodies, rather than objects. However, recent work has shown that while this…