Search Results for author:
Found 20 papers, 14 papers with code
Segment Anything
We introduce the Segment Anything (SA) project: a new task, model, and dataset for image segmentation.
Ranked #2 on
Zero-Shot Instance Segmentation
on LVIS v1.0 val
Real-World Humanoid Locomotion with Reinforcement Learning
Humanoid robots that can autonomously operate in diverse environments have the potential to help address labour shortages in factories, assist elderly at homes, and colonize new planets.
Real-World Robot Learning with Masked Visual Pre-training
Finally, we train a 307M parameter vision transformer on a massive collection of 4. 5M images from the Internet and egocentric videos, and demonstrate clearly the benefits of scaling visual pre-training for robot learning.
Masked Visual Pre-training for Motor Control
This paper shows that self-supervised visual pre-training from real-world images is effective for learning motor control tasks from pixels.
Early Convolutions Help Transformers See Better
To test whether this atypical design choice causes an issue, we analyze the optimization behavior of ViT models with their original patchify stem versus a simple counterpart where we replace the ViT stem by a small number of stacked stride-two 3*3 convolutions.
Region Similarity Representation Learning
We present Region Similarity Representation Learning (ReSim), a new approach to self-supervised representation learning for localization-based tasks such as object detection and segmentation.
Learning Cross-Domain Correspondence for Control with Dynamics Cycle-Consistency
We propose \textit{dynamics cycles} that align dynamic robot behavior across two domains using a cycle-consistency constraint.
Reducing Class Collapse in Metric Learning with Easy Positive Sampling
We theoretically prove and empirically show that under reasonable noise assumptions, prevalent embedding losses in metric learning, e. g., triplet loss, tend to project all samples of a class with various modes onto a single point in the embedding space, resulting in a class collapse that usually renders the space ill-sorted for classification or retrieval.
What Should Not Be Contrastive in Contrastive Learning
Recent self-supervised contrastive methods have been able to produce impressive transferable visual representations by learning to be invariant to different data augmentations.
Rethinking preventing class-collapsing in metric learning with margin-based losses
We theoretically prove and empirically show that under reasonable noise assumptions, margin-based losses tend to project all samples of a class with various modes onto a single point in the embedding space, resulting in a class collapse that usually renders the space ill-sorted for classification or retrieval.
Something-Else: Compositional Action Recognition with Spatial-Temporal Interaction Networks
Human action is naturally compositional: humans can easily recognize and perform actions with objects that are different from those used in training demonstrations.
Reasoning About Human-Object Interactions Through Dual Attention Networks
The model not only finds when an action is happening and which object is being manipulated, but also identifies which part of the object is being interacted with.
Acquisition of Localization Confidence for Accurate Object Detection
The network acquires this confidence of localization, which improves the NMS procedure by preserving accurately localized bounding boxes.
Ranked #186 on
Object Detection
on COCO test-dev
Unified Perceptual Parsing for Scene Understanding
In this paper, we study a new task called Unified Perceptual Parsing, which requires the machine vision systems to recognize as many visual concepts as possible from a given image.
Ranked #90 on
Semantic Segmentation
on ADE20K val
Learning Visually-Grounded Semantics from Contrastive Adversarial Samples
Begin with an insightful adversarial attack on VSE embeddings, we show the limitation of current frameworks and image-text datasets (e. g., MS-COCO) both quantitatively and qualitatively.
CrowdHuman: A Benchmark for Detecting Human in a Crowd
There are a total of $470K$ human instances from the train and validation subsets, and $~22. 6$ persons per image, with various kinds of occlusions in the dataset.
Ranked #7 on
Pedestrian Detection
on Caltech
(using extra training data)
Repulsion Loss: Detecting Pedestrians in a Crowd
In this paper, we first explore how a state-of-the-art pedestrian detector is harmed by crowd occlusion via experimentation, providing insights into the crowd occlusion problem.
Ranked #9 on
Pedestrian Detection
on Caltech
(using extra training data)
MegDet: A Large Mini-Batch Object Detector
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, new framework, or novel loss design.
What Can Help Pedestrian Detection?
Aggregating extra features has been considered as an effective approach to boost traditional pedestrian detection methods.
Ranked #15 on
Pedestrian Detection
on Caltech
Semantic Understanding of Scenes through the ADE20K Dataset
Scene parsing, or recognizing and segmenting objects and stuff in an image, is one of the key problems in computer vision.
