CVPR 2019

Detect-to-Retrieve: Efficient Regional Aggregation for Image Search

CVPR 2019 tensorflow/models

Then, we demonstrate how a trained landmark detector, using our new dataset, can be leveraged to index image regions and improve retrieval accuracy while being much more efficient than existing regional methods.

IMAGE RETRIEVAL

FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation

CVPR 2019 tensorflow/models

Many of the recent successful methods for video object segmentation (VOS) are overly complicated, heavily rely on fine-tuning on the first frame, and/or are slow, and are hence of limited practical use.

SEMANTIC SEGMENTATION VIDEO OBJECT SEGMENTATION VIDEO SEMANTIC SEGMENTATION

Panoptic Feature Pyramid Networks

CVPR 2019 facebookresearch/detectron2

In this work, we perform a detailed study of this minimally extended version of Mask R-CNN with FPN, which we refer to as Panoptic FPN, and show it is a robust and accurate baseline for both tasks.

INSTANCE SEGMENTATION PANOPTIC SEGMENTATION

Pushing the Boundaries of View Extrapolation with Multiplane Images

CVPR 2019 google-research/google-research

We present a theoretical analysis showing how the range of views that can be rendered from an MPI increases linearly with the MPI disparity sampling frequency, as well as a novel MPI prediction procedure that theoretically enables view extrapolations of up to $4\times$ the lateral viewpoint movement allowed by prior work.

Temporal Cycle-Consistency Learning

CVPR 2019 google-research/google-research

We introduce a self-supervised representation learning method based on the task of temporal alignment between videos.

ANOMALY DETECTION REPRESENTATION LEARNING SELF-SUPERVISED LEARNING VIDEO ALIGNMENT

Unprocessing Images for Learned Raw Denoising

CVPR 2019 google-research/google-research

Machine learning techniques work best when the data used for training resembles the data used for evaluation.

IMAGE DENOISING

Hybrid Task Cascade for Instance Segmentation

CVPR 2019 open-mmlab/mmdetection

In exploring a more effective approach, we find that the key to a successful instance segmentation cascade is to fully leverage the reciprocal relationship between detection and segmentation.

INSTANCE SEGMENTATION OBJECT DETECTION SEMANTIC SEGMENTATION

Region Proposal by Guided Anchoring

CVPR 2019 open-mmlab/mmdetection

State-of-the-art detectors mostly rely on a dense anchoring scheme, where anchors are sampled uniformly over the spatial domain with a predefined set of scales and aspect ratios.

OBJECT DETECTION REGION PROPOSAL

Libra R-CNN: Towards Balanced Learning for Object Detection

CVPR 2019 open-mmlab/mmdetection

In this work, we carefully revisit the standard training practice of detectors, and find that the detection performance is often limited by the imbalance during the training process, which generally consists in three levels - sample level, feature level, and objective level.

OBJECT DETECTION

Grid R-CNN

CVPR 2019 open-mmlab/mmdetection

This paper proposes a novel object detection framework named Grid R-CNN, which adopts a grid guided localization mechanism for accurate object detection.

OBJECT DETECTION OBJECT LOCALIZATION