562 citations · 1.7k across the 17 of their papers we have counts for
13 papers · 1 filter
Segment Anything
Alexander Kirillov, Eric Mintun, Nikhila Ravi +9
We introduce the Segment Anything (SA) project: a new task, model, and dataset for image segmentation. Using our efficient model in a data collection loop, we built the largest seg…
Masked Visual Pre-training for Motor Control
Tete Xiao, Ilija Radosavovic, Trevor Darrell +1
This paper shows that self-supervised visual pre-training from real-world images is effective for learning motor control tasks from pixels. We first train the visual representation…
Early Convolutions Help Transformers See Better
Tete Xiao, Mannat Singh, Eric Mintun +3
Vision transformer (ViT) models exhibit substandard optimizability. In particular, they are sensitive to the choice of optimizer (AdamW vs. SGD), optimizer hyperparameters, and tra…
Region Similarity Representation Learning
Tete Xiao, Colorado J Reed, Xiaolong Wang +2
We present Region Similarity Representation Learning (ReSim), a new approach to self-supervised representation learning for localization-based tasks such as object detection and se…
What Should Not Be Contrastive in Contrastive Learning
Tete Xiao, Xiaolong Wang, Alexei A. Efros +1
Recent self-supervised contrastive methods have been able to produce impressive transferable visual representations by learning to be invariant to different data augmentations. How…
Something-Else: Compositional Action Recognition with Spatial-Temporal Interaction Networks
Joanna Materzynska, Tete Xiao, Roei Herzig +3
Human action is naturally compositional: humans can easily recognize and perform actions with objects that are different from those used in training demonstrations. In this paper,…
Reasoning About Human-Object Interactions Through Dual Attention Networks
Tete Xiao, Quanfu Fan, Dan Gutfreund +3
Objects are entities we act upon, where the functionality of an object is determined by how we interact with it. In this work we propose a Dual Attention Network model which reason…
Acquisition of Localization Confidence for Accurate Object Detection
Borui Jiang, Ruixuan Luo, Jiayuan Mao +2
Modern CNN-based object detectors rely on bounding box regression and non-maximum suppression to localize objects. While the probabilities for class labels naturally reflect classi…
Unified Perceptual Parsing for Scene Understanding
Tete Xiao, Yingcheng Liu, Bolei Zhou +2
Humans recognize the visual world at multiple levels: we effortlessly categorize scenes and detect objects inside, while also identifying the textures and surfaces of the objects a…
CrowdHuman: A Benchmark for Detecting Human in a Crowd
Shuai Shao, Zijian Zhao, Boxun Li +4
Human detection has witnessed impressive progress in recent years. However, the occlusion issue of detecting human in highly crowded environments is far from solved. To make matter…
Repulsion Loss: Detecting Pedestrians in a Crowd
Xinlong Wang, Tete Xiao, Yuning Jiang +3
Detecting individual pedestrians in a crowd remains a challenging problem since the pedestrians often gather together and occlude each other in real-world scenarios. In this paper,…
MegDet: A Large Mini-Batch Object Detector
Chao Peng, Tete Xiao, Zeming Li +5
The improvements in recent CNN-based object detection works, from R-CNN [11], Fast/Faster R-CNN [10, 31] to recent Mask R-CNN [14] and RetinaNet [24], mainly come from new network,…
What Can Help Pedestrian Detection?
Jiayuan Mao, Tete Xiao, Yuning Jiang +1
Aggregating extra features has been considered as an effective approach to boost traditional pedestrian detection methods. However, there is still a lack of studies on whether and…