arXiv subjects

Guosheng Lin

Publications and source records attributed to Guosheng Lin.

At least 127 records · Page 7Linked to original sources

arXiv2023

3D Cinemagraphy from a Single Image

We present 3D Cinemagraphy, a new technique that marries 2D image animation with 3D photography. Given a single still image as input, our goal is to generate a video that contains both visual content animation and camera motion. We empirically find that naively combining existing 2D image animation and 3D photography methods leads to obvious artifacts or inconsistent animation. Our key insight is that representing and animating the scene in 3D space offers a natural solution to this task. To this end, we first convert the input image into feature-based layered depth images using predicted depth values, followed by unprojecting them to a feature point cloud. To animate the scene, we perform motion estimation and lift the 2D motion into the 3D scene flow. Finally, to resolve the problem of hole emergence as points move forward, we propose to bidirectionally displace the point cloud as per the scene flow and synthesize novel views by separately projecting them into target image planes and blending the results. Extensive experiments demonstrate the effectiveness of our method. A user study is also conducted to validate the compelling rendering results of our method.

cs.CV↗

arXiv2023

Point Discriminative Learning for Data-efficient 3D Point Cloud Analysis

3D point cloud analysis has drawn a lot of research attention due to its wide applications. However, collecting massive labelled 3D point cloud data is both time-consuming and labor-intensive. This calls for data-efficient learning methods. In this work we propose PointDisc, a point discriminative learning method to leverage self-supervisions for data-efficient 3D point cloud classification and segmentation. PointDisc imposes a novel point discrimination loss on the middle and global level features produced by the backbone network. This point discrimination loss enforces learned features to be consistent with points belonging to the corresponding local shape region and inconsistent with randomly sampled noisy points. We conduct extensive experiments on 3D object classification, 3D semantic and part segmentation, showing the benefits of PointDisc for data-efficient learning. Detailed analysis demonstrate that PointDisc learns unsupervised features that well capture local and global geometry.

cs.CV↗

arXiv2023

Self-Training Vision Language BERTs with a Unified Conditional Model

Natural language BERTs are trained with language corpus in a self-supervised manner. Unlike natural language BERTs, vision language BERTs need paired data to train, which restricts the scale of VL-BERT pretraining. We propose a self-training approach that allows training VL-BERTs from unlabeled image data. The proposed method starts with our unified conditional model -- a vision language BERT model that can perform zero-shot conditional generation. Given different conditions, the unified conditional model can generate captions, dense captions, and even questions. We use the labeled image data to train a teacher model and use the trained model to generate pseudo captions on unlabeled image data. We then combine the labeled data and pseudo labeled data to train a student model. The process is iterated by putting the student model as a new teacher. By using the proposed self-training approach and only 300k unlabeled extra data, we are able to get competitive or even better performances compared to the models of similar model size trained with 3 million extra image data.

cs.CV↗

arXiv2023

Effective End-to-End Vision Language Pretraining with Semantic Visual Loss

Current vision language pretraining models are dominated by methods using region visual features extracted from object detectors. Given their good performance, the extract-then-process pipeline significantly restricts the inference speed and therefore limits their real-world use cases. However, training vision language models from raw image pixels is difficult, as the raw image pixels give much less prior knowledge than region features. In this paper, we systematically study how to leverage auxiliary visual pretraining tasks to help training end-to-end vision language models. We introduce three types of visual losses that enable much faster convergence and better finetuning accuracy. Compared with region feature models, our end-to-end models could achieve similar or better performance on downstream tasks and run more than 10 times faster during inference. Compared with other end-to-end models, our proposed method could achieve similar or better performance when pretrained for only 10% of the pretraining GPU hours.

cs.CV↗

arXiv2022

Efficient Few-Shot Object Detection via Knowledge Inheritance

Few-shot object detection (FSOD), which aims at learning a generic detector that can adapt to unseen tasks with scarce training samples, has witnessed consistent improvement recently. However, most existing methods ignore the efficiency issues, e.g., high computational complexity and slow adaptation speed. Notably, efficiency has become an increasingly important evaluation metric for few-shot techniques due to an emerging trend toward embedded AI. To this end, we present an efficient pretrain-transfer framework (PTF) baseline with no computational increment, which achieves comparable results with previous state-of-the-art (SOTA) methods. Upon this baseline, we devise an initializer named knowledge inheritance (KI) to reliably initialize the novel weights for the box classifier, which effectively facilitates the knowledge transfer process and boosts the adaptation speed. Within the KI initializer, we propose an adaptive length re-scaling (ALR) strategy to alleviate the vector length inconsistency between the predicted novel weights and the pretrained base weights. Finally, our approach not only achieves the SOTA results across three public benchmarks, i.e., PASCAL VOC, COCO and LVIS, but also exhibits high efficiency with 1.8-100x faster adaptation speed against the other methods on COCO/LVIS benchmark during few-shot transfer. To our best knowledge, this is the first work to consider the efficiency problem in FSOD. We hope to motivate a trend toward powerful yet efficient few-shot technique development. The codes are publicly available at https://github.com/Ze-Yang/Efficient-FSOD.

cs.CV↗

arXiv2022

Generalizable Person Re-Identification via Viewpoint Alignment and Fusion

In the current person Re-identification (ReID) methods, most domain generalization works focus on dealing with style differences between domains while largely ignoring unpredictable camera view change, which we identify as another major factor leading to a poor generalization of ReID methods. To tackle the viewpoint change, this work proposes to use a 3D dense pose estimation model and a texture mapping module to map the pedestrian images to canonical view images. Due to the imperfection of the texture mapping module, the canonical view images may lose the discriminative detail clues from the original images, and thus directly using them for ReID will inevitably result in poor performance. To handle this issue, we propose to fuse the original image and canonical view image via a transformer-based module. The key insight of this design is that the cross-attention mechanism in the transformer could be an ideal solution to align the discriminative texture clues from the original image with the canonical view image, which could compensate for the low-quality texture information of the canonical view image. Through extensive experiments, we show that our method can lead to superior performance over the existing approaches in various evaluation settings.

cs.CV↗

arXiv2022

Engineered Octave Frequency Comb in Integrated Chalcogenide Dual-ring Microresonators

Broadband Kerr combs with a flat comb spectral profile are expected in a number of applications, such as high-capacity optical communication. Here, we propose novel concentric dual-ring microresonators (DRMs) for advanced dispersion engineering to tailor the comb spectral profile. The dispersion can be flexibly engineered not only by the cross-section of the DRMs, but also by the gap between concentric dual-ring microresonators, which provides a new path to geometrically control the spectral profile of the soliton Kerr combs. An octave-spanning dissipative Kerr soliton comb with superior spectral flatness has been achieved numerically, covering from the telecommunication band to the mid-infrared (MIR) band region with a -40 dB bandwidth of 1265 nm (99.82 THz). Our results are promising to fully understand the nonlinear dynamics in hybrid modes in DRMs, which helps control broadband comb formation.

physics.optics↗

arXiv2022

Indoor Smartphone SLAM with Learned Echoic Location Features

Indoor self-localization is a highly demanded system function for smartphones. The current solutions based on inertial, radio frequency, and geomagnetic sensing may have degraded performance when their limiting factors take effect. In this paper, we present a new indoor simultaneous localization and mapping (SLAM) system that utilizes the smartphone's built-in audio hardware and inertial measurement unit (IMU). Our system uses a smartphone's loudspeaker to emit near-inaudible chirps and then the microphone to record the acoustic echoes from the indoor environment. Our profiling measurements show that the echoes carry location information with sub-meter granularity. To enable SLAM, we apply contrastive learning to construct an echoic location feature (ELF) extractor, such that the loop closures on the smartphone's trajectory can be accurately detected from the associated ELF trace. The detection results effectively regulate the IMU-based trajectory reconstruction. Extensive experiments show that our ELF-based SLAM achieves median localization errors of $0.1\,\text{m}$, $0.53\,\text{m}$, and $0.4\,\text{m}$ on the reconstructed trajectories in a living room, an office, and a shopping mall, and outperforms the Wi-Fi and geomagnetic SLAM systems.

cs.RO↗

arXiv2022

Long-tailed Recognition by Learning from Latent Categories

In this work, we address the challenging task of long-tailed image recognition. Previous long-tailed recognition methods commonly focus on the data augmentation or re-balancing strategy of the tail classes to give more attention to tail classes during the model training. However, due to the limited training images for tail classes, the diversity of tail class images is still restricted, which results in poor feature representations. In this work, we hypothesize that common latent features among the head and tail classes can be used to give better feature representation. Motivated by this, we introduce a Latent Categories based long-tail Recognition (LCReg) method. Specifically, we propose to learn a set of class-agnostic latent features shared among the head and tail classes. Then, we implicitly enrich the training sample diversity via applying semantic data augmentation to the latent features. Extensive experiments on five long-tailed image recognition datasets demonstrate that our proposed LCReg is able to significantly outperform previous methods and achieve state-of-the-art results.

cs.CV↗

arXiv2022

CRCNet: Few-shot Segmentation with Cross-Reference and Region-Global Conditional Networks

Few-shot segmentation aims to learn a segmentation model that can be generalized to novel classes with only a few training images. In this paper, we propose a Cross-Reference and Local-Global Conditional Networks (CRCNet) for few-shot segmentation. Unlike previous works that only predict the query image's mask, our proposed model concurrently makes predictions for both the support image and the query image. Our network can better find the co-occurrent objects in the two images with a cross-reference mechanism, thus helping the few-shot segmentation task. To further improve feature comparison, we develop a local-global conditional module to capture both global and local relations. We also develop a mask refinement module to refine the prediction of the foreground regions recurrently. Experiments on the PASCAL VOC 2012, MS COCO, and FSS-1000 datasets show that our network achieves new state-of-the-art performance.

cs.CV↗

arXiv2022

Learning Structural Representations for Recipe Generation and Food Retrieval

Food is significant to human daily life. In this paper, we are interested in learning structural representations for lengthy recipes, that can benefit the recipe generation and food cross-modal retrieval tasks. Different from the common vision-language data, here the food images contain mixed ingredients and target recipes are lengthy paragraphs, where we do not have annotations on structure information. To address the above limitations, we propose a novel method to unsupervisedly learn the sentence-level tree structures for the cooking recipes. Our approach brings together several novel ideas in a systematic framework: (1) exploiting an unsupervised learning approach to obtain the sentence-level tree structure labels before training; (2) generating trees of target recipes from images with the supervision of tree structure labels learned from (1); and (3) integrating the learned tree structures into the recipe generation and food cross-modal retrieval procedure. Our proposed model can produce good-quality sentence-level tree structures and coherent recipes. We achieve the state-of-the-art recipe generation and food cross-modal retrieval performance on the benchmark Recipe1M dataset.

cs.CV↗

arXiv2022

Cross-Modal Graph with Meta Concepts for Video Captioning

Video captioning targets interpreting the complex visual contents as text descriptions, which requires the model to fully understand video scenes including objects and their interactions. Prevailing methods adopt off-the-shelf object detection networks to give object proposals and use the attention mechanism to model the relations between objects. They often miss some undefined semantic concepts of the pretrained model and fail to identify exact predicate relationships between objects. In this paper, we investigate an open research task of generating text descriptions for the given videos, and propose Cross-Modal Graph (CMG) with meta concepts for video captioning. Specifically, to cover the useful semantic concepts in video captions, we weakly learn the corresponding visual regions for text descriptions, where the associated visual regions and textual words are named cross-modal meta concepts. We further build meta concept graphs dynamically with the learned cross-modal meta concepts. We also construct holistic video-level and local frame-level video graphs with the predicted predicates to model video sequence structures. We validate the efficacy of our proposed techniques with extensive experiments and achieve state-of-the-art results on two public datasets.

cs.CV↗

arXiv2022

Paired Cross-Modal Data Augmentation for Fine-Grained Image-to-Text Retrieval

This paper investigates an open research problem of generating text-image pairs to improve the training of fine-grained image-to-text cross-modal retrieval task, and proposes a novel framework for paired data augmentation by uncovering the hidden semantic information of StyleGAN2 model. Specifically, we first train a StyleGAN2 model on the given dataset. We then project the real images back to the latent space of StyleGAN2 to obtain the latent codes. To make the generated images manipulatable, we further introduce a latent space alignment module to learn the alignment between StyleGAN2 latent codes and the corresponding textual caption features. When we do online paired data augmentation, we first generate augmented text through random token replacement, then pass the augmented text into the latent space alignment module to output the latent codes, which are finally fed to StyleGAN2 to generate the augmented images. We evaluate the efficacy of our augmented data approach on two public cross-modal retrieval datasets, in which the promising experimental results demonstrate the augmented text-image pair data can be trained together with the original data to boost the image-to-text cross-modal retrieval performance.

cs.CV↗

arXiv2022

Few-shot Open-set Recognition Using Background as Unknowns

Few-shot open-set recognition aims to classify both seen and novel images given only limited training data of seen classes. The challenge of this task is that the model is required not only to learn a discriminative classifier to classify the pre-defined classes with few training data but also to reject inputs from unseen classes that never appear at training time. In this paper, we propose to solve the problem from two novel aspects. First, instead of learning the decision boundaries between seen classes, as is done in standard close-set classification, we reserve space for unseen classes, such that images located in these areas are recognized as the unseen classes. Second, to effectively learn such decision boundaries, we propose to utilize the background features from seen classes. As these background regions do not significantly contribute to the decision of close-set classification, it is natural to use them as the pseudo unseen classes for classifier learning. Our extensive experiments show that our proposed method not only outperforms multiple baselines but also sets new state-of-the-art results on three popular benchmarks, namely tieredImageNet, miniImageNet, and Caltech-USCD Birds-200-2011 (CUB).

cs.CV↗

arXiv2022

Dual Adaptive Transformations for Weakly Supervised Point Cloud Segmentation

Weakly supervised point cloud segmentation, i.e. semantically segmenting a point cloud with only a few labeled points in the whole 3D scene, is highly desirable due to the heavy burden of collecting abundant dense annotations for the model training. However, existing methods remain challenging to accurately segment 3D point clouds since limited annotated data may lead to insufficient guidance for label propagation to unlabeled data. Considering the smoothness-based methods have achieved promising progress, in this paper, we advocate applying the consistency constraint under various perturbations to effectively regularize unlabeled 3D points. Specifically, we propose a novel DAT (\textbf{D}ual \textbf{A}daptive \textbf{T}ransformations) model for weakly supervised point cloud segmentation, where the dual adaptive transformations are performed via an adversarial strategy at both point-level and region-level, aiming at enforcing the local and structural smoothness constraints on 3D point clouds. We evaluate our proposed DAT model with two popular backbones on the large-scale S3DIS and ScanNet-V2 datasets. Extensive experiments demonstrate that our model can effectively leverage the unlabeled 3D points and achieve significant performance gains on both datasets, setting new state-of-the-art performance for weakly supervised point cloud segmentation.

cs.CV↗

arXiv2022

Cross-Image Region Mining with Region Prototypical Network for Weakly Supervised Segmentation

Weakly supervised image segmentation trained with image-level labels usually suffers from inaccurate coverage of object areas during the generation of the pseudo groundtruth. This is because the object activation maps are trained with the classification objective and lack the ability to generalize. To improve the generality of the objective activation maps, we propose a region prototypical network RPNet to explore the cross-image object diversity of the training set. Similar object parts across images are identified via region feature comparison. Object confidence is propagated between regions to discover new object areas while background regions are suppressed. Experiments show that the proposed method generates more complete and accurate pseudo object masks, while achieving state-of-the-art performance on PASCAL VOC 2012 and MS COCO. In addition, we investigate the robustness of the proposed method on reduced training sets.

cs.CV↗

arXiv2022

Few-shot Segmentation with Optimal Transport Matching and Message Flow

We tackle the challenging task of few-shot segmentation in this work. It is essential for few-shot semantic segmentation to fully utilize the support information. Previous methods typically adopt masked average pooling over the support feature to extract the support clues as a global vector, usually dominated by the salient part and lost certain essential clues. In this work, we argue that every support pixel's information is desired to be transferred to all query pixels and propose a Correspondence Matching Network (CMNet) with an Optimal Transport Matching module to mine out the correspondence between the query and support images. Besides, it is critical to fully utilize both local and global information from the annotated support images. To this end, we propose a Message Flow module to propagate the message along the inner-flow inside the same image and cross-flow between support and query images, which greatly helps enhance the local feature representations. Experiments on PASCAL VOC 2012, MS COCO, and FSS-1000 datasets show that our network achieves new state-of-the-art few-shot segmentation performance.

cs.CV↗

arXiv2022

A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection

Humans tend to mine objects by learning from a group of images or several frames of video since we live in a dynamic world. In the computer vision area, many researches focus on co-segmentation (CoS), co-saliency detection (CoSD) and video salient object detection (VSOD) to discover the co-occurrent objects. However, previous approaches design different networks on these similar tasks separately, and they are difficult to apply to each other, which lowers the upper bound of the transferability of deep learning frameworks. Besides, they fail to take full advantage of the cues among inter- and intra-feature within a group of images. In this paper, we introduce a unified framework to tackle these issues, term as UFO (Unified Framework for Co-Object Segmentation). Specifically, we first introduce a transformer block, which views the image feature as a patch token and then captures their long-range dependencies through the self-attention mechanism. This can help the network to excavate the patch structured similarities among the relevant objects. Furthermore, we propose an intra-MLP learning module to produce self-mask to enhance the network to avoid partial activation. Extensive experiments on four CoS benchmarks (PASCAL, iCoseg, Internet and MSRC), three CoSD benchmarks (Cosal2015, CoSOD3k, and CocA) and four VSOD benchmarks (DAVIS16, FBMS, ViSal and SegV2) show that our method outperforms other state-of-the-arts on three different tasks in both accuracy and speed by using the same network architecture , which can reach 140 FPS in real-time.

cs.CV↗