Progress on object detection is enabled by datasets that focus the research community's attention on open challenges. This process led us from simple images to complex scenes and from bounding boxes to segmentation masks. In this work, we introduce LVIS (pronounced `el-vis'): a new dataset for Large Vocabulary Instance Segmentation. We plan to collect ~2 million high-quality instance segmentation masks for over 1000 entry-level object categories in 164k images. Due to the Zipfian distribution of categories in natural images, LVIS naturally has a long tail of categories with few training samples. Given that state-of-the-art deep learning methods for object detection perform poorly in the low-sample regime, we believe that our dataset poses an important and exciting new scientific challenge. LVIS is available at http://www.lvisdataset.org.
Scaling object taxonomies is one of the important steps toward a robust real-world deployment of recognition systems. We have faced remarkable progress in images since the introduction of the LVIS benchmark. To continue this success in videos, a new video benchmark, TAO, was recently presented. Given the recent encouraging results from both detection and tracking communities, we are interested in marrying those two advances and building a strong large vocabulary video tracker. However, supervisions in LVIS and TAO are inherently sparse or even missing, posing two new challenges for training th…
Recent object detection and instance segmentation tasks mainly focus on datasets with a relatively small set of categories, e.g. Pascal VOC with 20 classes and COCO with 80 classes. The new large vocabulary dataset LVIS brings new challenges to conventional methods. In this work, we propose an equalization loss to solve the long tail of rare categories problem. Combined with exploiting the data from detection datasets to alleviate the effect of missing-annotation problems during the training, our method achieves 5.1\% overall AP gain and 11.4\% AP gain of rare categories on LVIS benchmark with…
This report introduces the technical details of the team FuXi-Fresher for LVIS Challenge 2021. Our method focuses on the problem in following two aspects: the long-tail distribution and the segmentation quality of mask and boundary. Based on the advanced HTC instance segmentation algorithm, we connect transformer backbone(Swin-L) through composite connections inspired by CBNetv2 to enhance the baseline results. To alleviate the problem of long-tail distribution, we design a Distribution Balanced method which includes dataset balanced and loss function balaced modules. Further, we use a Mask an…
Tencent Youtu Lab（腾讯优图实验室）；East China Normal University（华东师范大学）
Open-vocabulary object detection (OVD) aims to scale up vocabulary size to detect objects of novel categories beyond the training vocabulary. Recent work resorts to the rich knowledge in pre-trained vision-language models. However, existing methods are ineffective in proposal-level vision-language alignment. Meanwhile, the models usually suffer from confidence bias toward base categories and perform worse on novel ones. To overcome the challenges, we present MEDet, a novel and effective OVD framework with proposal mining and prediction equalization. First, we design an online proposal mining t…
Monash University（莫纳什大学）；ByteDance（字节跳动）；The University of Hong Kong（香港大学）
Existing object detection methods are bounded in a fixed-set vocabulary by costly labeled data. When dealing with novel categories, the model has to be retrained with more bounding box annotations. Natural language supervision is an attractive alternative for its annotation-free attributes and broader object concepts. However, learning open-vocabulary object detection from language is challenging since image-text pairs do not contain fine-grained object-language alignments. Previous solutions rely on either expensive grounding annotations or distilling classification-oriented vision models. In…
This article introduces the solutions of the team lvisTraveler for LVIS Challenge 2020. In this work, two characteristics of LVIS dataset are mainly considered: the long-tailed distribution and high quality instance segmentation mask. We adopt a two-stage training pipeline. In the first stage, we incorporate EQL and self-training to learn generalized representation. In the second stage, we utilize Balanced GroupSoftmax to promote the classifier, and propose a novel proposal assignment strategy and a new balanced mask loss for mask head to get more precise mask predictions. Finally, we achieve …
ExDet: Open-Domain Open-Vocabulary Detection with Cross-modal Extrapolation and Rectification
College of Intelligence and Computing, Tianjin University（天津大学智能与计算学部）；Faculty of Computer Science and Artificial Intelligence, Shenzhen University of Advanced Technology（深圳理工大学计算机科学与人工智能学院）；School of Artificial Intelligence, Nanchang University（南昌大学人工智能学院）
Carnegie Mellon University（卡内基梅隆大学）；Facebook AI Research (FAIR)（脸书人工智能研究院）
By design, average precision (AP) for object detection aims to treat all classes independently: AP is computed independently per category and averaged. On one hand, this is desirable as it treats all classes equally. On the other hand, it ignores cross-category confidence calibration, a key property in real-world use cases. Unfortunately, under important conditions (i.e., large vocabulary, high instance counts) the default implementation of AP is neither category independent, nor does it directly reward properly calibrated detectors. In fact, we show that on LVIS the default implementation pro…
The two-stage methods for instance segmentation, e.g. Mask R-CNN, have achieved excellent performance recently. However, the segmented masks are still very coarse due to the downsampling operations in both the feature pyramid and the instance-wise pooling process, especially for large objects. In this work, we propose a new method called RefineMask for high-quality instance segmentation of objects and scenes, which incorporates fine-grained features during the instance-wise segmenting process in a multi-stage manner. Through fusing more detailed information stage by stage, RefineMask is able t…
NGS, National University of Singapore（新加坡国立大学）；ECE Department, National University of Singapore（新加坡国立大学电机与计算机工程系）；Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；Salesforce Research Asia（Salesforce亚洲研究院）
Most existing object instance detection and segmentation models only work well on fairly balanced benchmarks where per-category training sample numbers are comparable, such as COCO. They tend to suffer performance drop on realistic datasets that are usually long-tailed. This work aims to study and address such open challenges. Specifically, we systematically investigate performance drop of the state-of-the-art two-stage instance segmentation model Mask R-CNN on the recent long-tail LVIS dataset, and unveil that a major cause is the inaccurate classification of object proposals. Based on such a…
Meta AI；The University of Texas at Austin（德克萨斯大学奥斯汀分校）
Current object detectors are limited in vocabulary size due to the small scale of detection datasets. Image classifiers, on the other hand, reason about much larger vocabularies, as their datasets are larger and easier to collect. We propose Detic, which simply trains the classifiers of a detector on image classification data and thus expands the vocabulary of detectors to tens of thousands of concepts. Unlike prior work, Detic does not need complex assignment schemes to assign image labels to boxes based on model predictions, making it much easier to implement and compatible with a range of d…
State University of New York at Buffalo（纽约州立大学布法罗分校）；Tianjin University（天津大学）；Horizon Robotics, Inc.（地平线机器人科技有限公司）
Despite the previous success of object analysis, detecting and segmenting a large number of object categories with a long-tailed data distribution remains a challenging problem and is less investigated. For a large-vocabulary classifier, the chance of obtaining noisy logits is much higher, which can easily lead to a wrong recognition. In this paper, we exploit prior knowledge of the relations among object categories to cluster fine-grained classes into coarser parent classes, and construct a classification tree that is responsible for parsing an object instance into a fine-grained category via…
We present F-VLM, a simple open-vocabulary object detection method built upon Frozen Vision and Language Models. F-VLM simplifies the current multi-stage training pipeline by eliminating the need for knowledge distillation or detection-tailored pretraining. Surprisingly, we observe that a frozen VLM: 1) retains the locality-sensitive features necessary for detection, and 2) is a strong region classifier. We finetune only the detector head and combine the detector and VLM outputs for each region at inference time. F-VLM shows compelling scaling behavior and achieves +6.5 mask AP improvement ove…
ODOV: Benchmark the Open-Domain Open-Vocabulary Object Detection
College of Intelligence and Computing, Tianjin University（天津大学智能计算学院）；Key Research Center for Surface Monitoring and Analysis of Relics, State Administration of Cultural Heritage（文物表面监测与分析国家重点研究中心）；Faculty of Computer Science and Artificial Intelligence, Shenzhen University of Advanced Technology（深圳先进技术大学计算机科学与人工智能学院）
Google Research（谷歌研究院）；UC Berkeley（加州大学伯克利分校）；Cornell University（康奈尔大学）
Building instance segmentation models that are data-efficient and can handle rare object categories is an important challenge in computer vision. Leveraging data augmentations is a promising direction towards addressing this challenge. Here, we perform a systematic study of the Copy-Paste augmentation ([13, 12]) for instance segmentation where we randomly paste objects onto an image. Prior studies on Copy-Paste relied on modeling the surrounding visual context for pasting the objects. However, we find that the simple mechanism of pasting objects randomly is good enough and can provide solid ga…
Nanyang Technological University（南洋理工大学）；Max Planck Institute for Informatics（马克斯·普朗克信息学研究所）；University of Ottawa（渥太华大学）；Carnegie Mellon University（卡内基梅隆大学）；MBZUAI（穆罕默德·本·扎耶德人工智能大学）
We design an open-vocabulary image segmentation model to organize an image into meaningful regions indicated by arbitrary texts. Recent works (CLIP and ALIGN), despite attaining impressive open-vocabulary classification accuracy with image-level caption labels, are unable to segment visual concepts with pixels. We argue that these models miss an important step of visual grouping, which organizes pixels into groups before learning visual-semantic alignments. We propose OpenSeg to address the above issue while still making use of scalable image-level supervision of captions. First, it learns to …
Despite great progress in object detection, most existing methods work only on a limited set of object categories, due to the tremendous human effort needed for bounding-box annotations of training data. To alleviate the problem, recent open vocabulary and zero-shot detection methods attempt to detect novel object categories beyond those seen during training. They achieve this goal by training on a pre-defined base categories to induce generalization to novel objects. However, their potential is still constrained by the small set of base categories available for training. To enlarge the set of…
USE: Universal Segment Embeddings for Open-Vocabulary Image Segmentation
Bosch Research North America（博世北美研究院）；Bosch Center for Artificial Intelligence (BCAI)（博世人工智能中心）；The Ohio State University（俄亥俄州立大学）；University of California Davis（加州大学戴维斯分校）
We introduce Patch Aligned Contrastive Learning (PACL), a modified compatibility function for CLIP's contrastive loss, intending to train an alignment between the patch tokens of the vision encoder and the CLS token of the text encoder. With such an alignment, a model can identify regions of an image corresponding to a given text input, and therefore transfer seamlessly to the task of open vocabulary semantic segmentation without requiring any segmentation annotations during training. Using pre-trained CLIP encoders with PACL, we are able to set the state-of-the-art on the task of open vocabul…
Boosting Open-Vocabulary Object Detection by Handling Background Samples
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Nanjing Artificial Intelligence Research of IA（中科院南京人工智能研究院）
Lost in Translation? Vocabulary Alignment for Source-Free Adaptation in Open-Vocabulary Semantic Segmentation
The Good AI Lab（好AI实验室）；ETH Zurich（苏黎世联邦理工学院）；AMD Silo AI；Google（谷歌）；Technical University of Munich（慕尼黑技术大学）；INSAIT, Sofia University, St. Kliment Ohridski（INSAIT，索菲亚大学，圣克莱孟·奥赫里茨基）；University of Bologna（博洛尼亚大学）
Nanyang Technological University（南洋理工大学）；The University of Hong Kong（香港大学）；SenseTime Research and Tetras.AI（商汤研究院与Tetras.AI）；Shanghai AI Laboratory（上海人工智能实验室）
Pre-trained vision-language models (VLMs) learn to align vision and language representations on large-scale datasets, where each image-text pair usually contains a bag of semantic concepts. However, existing open-vocabulary object detectors only align region embeddings individually with the corresponding features extracted from the VLMs. Such a design leaves the compositional structure of semantic concepts in a scene under-exploited, although the structure may be implicitly learned by the VLMs. In this work, we propose to align the embedding of bag of regions beyond individual regions. The pro…
School of Electronic Information, Wuhan University of Science and Technology（武汉科技大学电子信息学院）；State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications（北京邮电大学网络与交换技术国家重点实验室）；Oriental Space Port Research Institute（东方航天港研究院）；School of Artificial Intelligence, Wuhan University（武汉大学人工智能学院）
The goal of this work is to establish a scalable pipeline for expanding an object detector towards novel/unseen categories, using zero manual annotations. To achieve that, we make the following four contributions: (i) in pursuit of generalisation, we propose a two-stage open-vocabulary object detector, where the class-agnostic object proposals are classified with a text encoder from pre-trained visual-language model; (ii) To pair the visual latent space (of RPN box proposals) with that of the pre-trained text encoder, we propose the idea of regional prompt learning to align the textual embeddi…
High-quality instance segmentation has shown emerging importance in computer vision. Without any refinement, DCT-Mask directly generates high-resolution masks by compressed vectors. To further refine masks obtained by compressed vectors, we propose for the first time a compressed vector based multi-stage refinement framework. However, the vanilla combination does not bring significant gains, because changes in some elements of the DCT vector will affect the prediction of the entire mask. Thus, we propose a simple and novel method named PatchDCT, which separates the mask decoded from a DCT vect…
FreeSeg: Unified, Universal and Open-Vocabulary Image Segmentation
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；ByteDance Inc（字节跳动公司）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）
The Hong Kong University of Science and Technology（香港科技大学）；International Digital Economy Academy (IDEA)（国际数字经济研究院（IDEA））；University of Wisconsin-Madison（威斯康星大学麦迪逊分校）；Tsinghua University（清华大学）；Microsoft Research at Redmond（微软雷德蒙德研究院）
We present OpenSeeD, a simple Open-vocabulary Segmentation and Detection framework that jointly learns from different segmentation and detection datasets. To bridge the gap of vocabulary and annotation granularity, we first introduce a pre-trained text encoder to encode all the visual concepts in two tasks and learn a common semantic space for them. This gives us reasonably good results compared with the counterparts trained on segmentation task only. To further reconcile them, we locate two discrepancies: $i$) task discrepancy -- segmentation requires extracting masks for both foreground obje…
Tongji University（同济大学）；SenseTime Research（商汤科技研究院）；The Chinese University of Hong Kong（香港中文大学）；The University of Sydney（悉尼大学）
Object recognition techniques using convolutional neural networks (CNN) have achieved great success. However, state-of-the-art object detection methods still perform poorly on large vocabulary and long-tailed datasets, e.g. LVIS. In this work, we analyze this problem from a novel perspective: each positive sample of one category can be seen as a negative sample for other categories, making the tail categories receive more discouraging gradients. Based on it, we propose a simple but effective loss, named equalization loss, to tackle the problem of long-tailed rare categories by simply ignoring …
