Highly Accurate Dichotomous Image Segmentation

  title={Highly Accurate Dichotomous Image Segmentation},
  author={Xuebin Qin and Hang Dai and Xiaobin Hu and Deng-Ping Fan and Ling Shao and and Luc Van Gool},
  booktitle={European Conference on Computer Vision},
We present a systematic study on a new task called dichotomous image segmentation (DIS), which aims to segment highly accurate objects from natural images. To this end, we collected the first large-scale dataset, called DIS5K , which contains 5,470 high-resolution ( e.g ., 2K, 4K or larger) images covering camouflaged, salient, or meticulous objects in various backgrounds. All images are an-notated with extremely fine-grained labels. In addition, we introduce a simple intermediate supervision… 

Salient Object Detection for Images Taken by People With Vision Impairments

A new salient object detection dataset using images taken by people who are visually impaired who were seek-ing to better understand their surroundings, called VizWiz-SalientObject, is introduced, which is the largest and contains unique characteristics.

NeRDi: Single-View NeRF Synthesis with Language-Guided Diffusion as General Image Priors

This work proposes NeRDi, a single-view NeR F synthesis framework with general image priors from 2D di ffusion models, and optimize the NeRF representations by minimizing a diffusion loss on its arbitrary view renderings with a pretrained image diffusion model under the input-view constraint.

Revisiting Image Pyramid Structure for High Resolution Salient Object Detection

This work designs InSPyReNet to produce a strict image pyramid structure of saliency map, which enables to ensemble multiple results with pyramid-based image blending, and designs a pyramid blending method which synthesizes two different image pyramids from a pair of LR and HR scale from the same image to overcome ERF discrepancy.



Scene Parsing through ADE20K Dataset

The ADE20K dataset, spanning diverse annotations of scenes, objects, parts of objects, and in some cases even parts of parts, is introduced and it is shown that the trained scene parsing networks can lead to applications such as image content removal and scene synthesis.

Rethinking BiSeNet For Real-time Semantic Segmentation

A novel and efficient structure named Short-Term Dense Concatenate network (STDC network) is proposed by removing structure redundancy by gradually reducing the dimension of feature maps and use the aggregation of them for image representation, which forms the basic module of STDC network.

Boundary IoU: Improving Object-Centric Image Segmentation Evaluation

This work presents Boundary IoU (Intersection-over-Union), a new segmentation evaluation measure focused on boundary quality that is significantly more sensitive than the standard Mask IoU measure to boundary errors for large objects and does not over-penalize errors on smaller objects.

Deep Interactive Thin Object Selection

The effectiveness of the proposed solution on segmenting thin objects is demonstrated, surpassing the baseline by ~ 30% IoUthin despite using only four clicks, and a novel integrative thin object segmentation network consisting of three streams.

HyperSeg: Patch-wise Hypernetwork for Real-time Semantic Segmentation

A novel, real-time, semantic segmentation network in which the encoder both encodes and generates the parameters (weights) of the decoder, and to allow maximal adaptivity, the weights at each decoder block vary spatially.

Meticulous Object Segmentation

This paper proposes and studies a task named Meticulous Object Segmentation (MOS), which is focused on segmenting well-defined foreground objects with elaborate shapes in high resolution images, and proposes theMeticulousNet which leverages a dedicated decoder to capture the object boundary details.

CascadePSP: Toward Class-Agnostic and Very High-Resolution Segmentation via Global and Local Refinement

This paper presents quantitative and qualitative studies on different datasets to show that CascadePSP can reveal pixel-accurate segmentation boundaries using the novel refinement module without any finetuning.

Towards High-Resolution Salient Object Detection

Experiments illustrate that the proposed novel approach outperforms existing state-of-the-art methods on high-resolution saliency datasets by a large margin, and achieves comparable or even better performance than them on some widely used saliency benchmarks.

Deep High-Resolution Representation Learning for Visual Recognition

The superiority of the proposed HRNet in a wide range of applications, including human pose estimation, semantic segmentation, and object detection, is shown, suggesting that the HRNet is a stronger backbone for computer vision problems.

Salient Object Detection in the Deep Learning Era: An In-Depth Survey

This paper reviews deep SOD algorithms from different perspectives, including network architecture, level of supervision, learning paradigm, and object-/instance-level detection, and looks into the generalization and difficulty of existing SOD datasets.