ICCV 2019

Searching for MobileNetV3

ICCV 2019 tensorflow/models

We achieve new state of the art results for mobile classification, detection and segmentation.

IMAGE CLASSIFICATION NEURAL ARCHITECTURE SEARCH OBJECT DETECTION SEMANTIC SEGMENTATION

A Learned Representation for Scalable Vector Graphics

ICCV 2019 tensorflow/magenta

Dramatic advances in generative models have resulted in near photographic quality for artificially rendered faces, animals and other objects in the natural world.

TensorMask: A Foundation for Dense Object Segmentation

ICCV 2019 facebookresearch/detectron2

To formalize this, we treat dense instance segmentation as a prediction task over 4D tensors and present a general framework called TensorMask that explicitly captures this geometry and enables novel operators on 4D tensors.

INSTANCE SEGMENTATION OBJECT DETECTION SEMANTIC SEGMENTATION

Scale-Aware Trident Networks for Object Detection

ICCV 2019 facebookresearch/detectron2

In this work, we first present a controlled experiment to investigate the effect of receptive fields for scale variation in object detection.

OBJECT DETECTION

Depth from Videos in the Wild: Unsupervised Monocular Depth Learning from Unknown Cameras

ICCV 2019 google-research/google-research

We present a novel method for simultaneous learning of depth, egomotion, object motion, and camera intrinsics from monocular videos, using only consistency across neighboring video frames as supervision signal.

DEPTH ESTIMATION

CARAFE: Content-Aware ReAssembly of FEatures

ICCV 2019 open-mmlab/mmdetection

CARAFE introduces little computational overhead and can be readily integrated into modern network architectures.

INSTANCE SEGMENTATION OBJECT DETECTION SEMANTIC SEGMENTATION

An Empirical Study of Spatial Attention Mechanisms in Deep Networks

ICCV 2019 open-mmlab/mmdetection

Attention mechanisms have become a popular component in deep neural networks, yet there has been little examination of how different influencing factors and methods for computing attention from these factors affect performance.

Rethinking ImageNet Pre-training

ICCV 2019 tensorpack/tensorpack

We report competitive results on object detection and instance segmentation on the COCO dataset using standard models trained from random initialization.

INSTANCE SEGMENTATION OBJECT DETECTION SEMANTIC SEGMENTATION

BMN: Boundary-Matching Network for Temporal Action Proposal Generation

ICCV 2019 PaddlePaddle/models

To address these difficulties, we introduce the Boundary-Matching (BM) mechanism to evaluate confidence scores of densely distributed proposals, which denote a proposal as a matching pair of starting and ending boundaries and combine all densely distributed BM pairs into the BM confidence map.

ACTION DETECTION TEMPORAL ACTION PROPOSAL GENERATION

ShapeMask: Learning to Segment Novel Objects by Refining Shape Priors

ICCV 2019 tensorflow/tpu

However, it is difficult and costly to segment objects in novel categories because a large number of mask annotations is required.

INSTANCE SEGMENTATION SEMANTIC SEGMENTATION