arXiv subjects

Feng Zheng

Publications and source records attributed to Feng Zheng.

At least 127 records · Page 7Linked to original sources

arXiv2023

Accelerating Vision-Language Pretraining with Free Language Modeling

The state of the arts in vision-language pretraining (VLP) achieves exemplary performance but suffers from high training costs resulting from slow convergence and long training time, especially on large-scale web datasets. An essential obstacle to training efficiency lies in the entangled prediction rate (percentage of tokens for reconstruction) and corruption rate (percentage of corrupted tokens) in masked language modeling (MLM), that is, a proper corruption rate is achieved at the cost of a large portion of output tokens being excluded from prediction loss. To accelerate the convergence of VLP, we propose a new pretraining task, namely, free language modeling (FLM), that enables a 100% prediction rate with arbitrary corruption rates. FLM successfully frees the prediction rate from the tie-up with the corruption rate while allowing the corruption spans to be customized for each token to be predicted. FLM-trained models are encouraged to learn better and faster given the same GPU time by exploiting bidirectional contexts more flexibly. Extensive experiments show FLM could achieve an impressive 2.5x pretraining time reduction in comparison to the MLM-based methods, while keeping competitive performance on both vision-language understanding and generation tasks. Code will be public at https://github.com/TencentARC/FLM.

cs.CV↗

arXiv2023

On the Stability and Generalization of Triplet Learning

Triplet learning, i.e. learning from triplet data, has attracted much attention in computer vision tasks with an extremely large number of categories, e.g., face recognition and person re-identification. Albeit with rapid progress in designing and applying triplet learning algorithms, there is a lacking study on the theoretical understanding of their generalization performance. To fill this gap, this paper investigates the generalization guarantees of triplet learning by leveraging the stability analysis. Specifically, we establish the first general high-probability generalization bound for the triplet learning algorithm satisfying the uniform stability, and then obtain the excess risk bounds of the order $O(n^{-\frac{1}{2}} \mathrm{log}n)$ for both stochastic gradient descent (SGD) and regularized risk minimization (RRM), where $2n$ is approximately equal to the number of training samples. Moreover, an optimistic generalization bound in expectation as fast as $O(n^{-1})$ is derived for RRM in a low noise case via the on-average stability analysis. Finally, our results are applied to triplet metric learning to characterize its theoretical underpinning.

stat.ML↗

arXiv2022

Skating-Mixer: Long-Term Sport Audio-Visual Modeling with MLPs

Figure skating scoring is challenging because it requires judging the technical moves of the players as well as their coordination with the background music. Most learning-based methods cannot solve it well for two reasons: 1) each move in figure skating changes quickly, hence simply applying traditional frame sampling will lose a lot of valuable information, especially in 3 to 5 minutes long videos; 2) prior methods rarely considered the critical audio-visual relationship in their models. Due to these reasons, we introduce a novel architecture, named Skating-Mixer. It extends the MLP framework into a multimodal fashion and effectively learns long-term representations through our designed memory recurrent unit (MRU). Aside from the model, we collected a high-quality audio-visual FS1000 dataset, which contains over 1000 videos on 8 types of programs with 7 different rating metrics, overtaking other datasets in both quantity and diversity. Experiments show the proposed method achieves SOTAs over all major metrics on the public Fis-V and our FS1000 dataset. In addition, we include an analysis applying our method to the recent competitions in Beijing 2022 Winter Olympic Games, proving our method has strong applicability.

cs.CV↗

arXiv2022

Learning Dual-Fused Modality-Aware Representations for RGBD Tracking

With the development of depth sensors in recent years, RGBD object tracking has received significant attention. Compared with the traditional RGB object tracking, the addition of the depth modality can effectively solve the target and background interference. However, some existing RGBD trackers use the two modalities separately and thus some particularly useful shared information between them is ignored. On the other hand, some methods attempt to fuse the two modalities by treating them equally, resulting in the missing of modality-specific features. To tackle these limitations, we propose a novel Dual-fused Modality-aware Tracker (termed DMTracker) which aims to learn informative and discriminative representations of the target objects for robust RGBD tracking. The first fusion module focuses on extracting the shared information between modalities based on cross-modal attention. The second aims at integrating the RGB-specific and depth-specific information to enhance the fused features. By fusing both the modality-shared and modality-specific information in a modality-aware scheme, our DMTracker can learn discriminative representations in complex tracking scenes. Experiments show that our proposed tracker achieves very promising results on challenging RGBD benchmarks.

cs.CV↗

arXiv2022

Does Thermal Really Always Matter for RGB-T Salient Object Detection?

In recent years, RGB-T salient object detection (SOD) has attracted continuous attention, which makes it possible to identify salient objects in environments such as low light by introducing thermal image. However, most of the existing RGB-T SOD models focus on how to perform cross-modality feature fusion, ignoring whether thermal image is really always matter in SOD task. Starting from the definition and nature of this task, this paper rethinks the connotation of thermal modality, and proposes a network named TNet to solve the RGB-T SOD task. In this paper, we introduce a global illumination estimation module to predict the global illuminance score of the image, so as to regulate the role played by the two modalities. In addition, considering the role of thermal modality, we set up different cross-modality interaction mechanisms in the encoding phase and the decoding phase. On the one hand, we introduce a semantic constraint provider to enrich the semantics of thermal images in the encoding phase, which makes thermal modality more suitable for the SOD task. On the other hand, we introduce a two-stage localization and complementation module in the decoding phase to transfer object localization cue and internal integrity cue in thermal features to the RGB modality. Extensive experiments on three datasets show that the proposed TNet achieves competitive performance compared with 20 state-of-the-art methods.

cs.CV↗

arXiv2022

Deep Manifold Hashing: A Divide-and-Conquer Approach for Semi-Paired Unsupervised Cross-Modal Retrieval

Hashing that projects data into binary codes has shown extraordinary talents in cross-modal retrieval due to its low storage usage and high query speed. Despite their empirical success on some scenarios, existing cross-modal hashing methods usually fail to cross modality gap when fully-paired data with plenty of labeled information is nonexistent. To circumvent this drawback, motivated by the Divide-and-Conquer strategy, we propose Deep Manifold Hashing (DMH), a novel method of dividing the problem of semi-paired unsupervised cross-modal retrieval into three sub-problems and building one simple yet efficiency model for each sub-problem. Specifically, the first model is constructed for obtaining modality-invariant features by complementing semi-paired data based on manifold learning, whereas the second model and the third model aim to learn hash codes and hash functions respectively. Extensive experiments on three benchmarks demonstrate the superiority of our DMH compared with the state-of-the-art fully-paired and semi-paired unsupervised cross-modal hashing methods.

cs.CV↗

arXiv2022

Pose-Aided Video-based Person Re-Identification via Recurrent Graph Convolutional Network

Existing methods for video-based person re-identification (ReID) mainly learn the appearance feature of a given pedestrian via a feature extractor and a feature aggregator. However, the appearance models would fail when different pedestrians have similar appearances. Considering that different pedestrians have different walking postures and body proportions, we propose to learn the discriminative pose feature beyond the appearance feature for video retrieval. Specifically, we implement a two-branch architecture to separately learn the appearance feature and pose feature, and then concatenate them together for inference. To learn the pose feature, we first detect the pedestrian pose in each frame through an off-the-shelf pose detector, and construct a temporal graph using the pose sequence. We then exploit a recurrent graph convolutional network (RGCN) to learn the node embeddings of the temporal pose graph, which devises a global information propagation mechanism to simultaneously achieve the neighborhood aggregation of intra-frame nodes and message passing among inter-frame graphs. Finally, we propose a dual-attention method consisting of node-attention and time-attention to obtain the temporal graph representation from the node embeddings, where the self-attention mechanism is employed to learn the importance of each node and each frame. We verify the proposed method on three video-based ReID datasets, i.e., Mars, DukeMTMC and iLIDS-VID, whose experimental results demonstrate that the learned pose feature can effectively improve the performance of existing appearance models.

cs.CV↗

arXiv2022

Class-Aware Contrastive Semi-Supervised Learning

Pseudo-label-based semi-supervised learning (SSL) has achieved great success on raw data utilization. However, its training procedure suffers from confirmation bias due to the noise contained in self-generated artificial labels. Moreover, the model's judgment becomes noisier in real-world applications with extensive out-of-distribution data. To address this issue, we propose a general method named Class-aware Contrastive Semi-Supervised Learning (CCSSL), which is a drop-in helper to improve the pseudo-label quality and enhance the model's robustness in the real-world setting. Rather than treating real-world data as a union set, our method separately handles reliable in-distribution data with class-wise clustering for blending into downstream tasks and noisy out-of-distribution data with image-wise contrastive for better generalization. Furthermore, by applying target re-weighting, we successfully emphasize clean label learning and simultaneously reduce noisy label learning. Despite its simplicity, our proposed CCSSL has significant performance improvements over the state-of-the-art SSL methods on the standard datasets CIFAR100 and STL10. On the real-world dataset Semi-iNat 2021, we improve FixMatch by 9.80% and CoMatch by 3.18%. Code is available https://github.com/TencentYoutuResearch/Classification-SemiCLS.

cs.CV↗

arXiv2022

Prompting for Multi-Modal Tracking

Multi-modal tracking gains attention due to its ability to be more accurate and robust in complex scenarios compared to traditional RGB-based tracking. Its key lies in how to fuse multi-modal data and reduce the gap between modalities. However, multi-modal tracking still severely suffers from data deficiency, thus resulting in the insufficient learning of fusion modules. Instead of building such a fusion module, in this paper, we provide a new perspective on multi-modal tracking by attaching importance to the multi-modal visual prompts. We design a novel multi-modal prompt tracker (ProTrack), which can transfer the multi-modal inputs to a single modality by the prompt paradigm. By best employing the tracking ability of pre-trained RGB trackers learning at scale, our ProTrack can achieve high-performance multi-modal tracking by only altering the inputs, even without any extra training on multi-modal data. Extensive experiments on 5 benchmark datasets demonstrate the effectiveness of the proposed ProTrack.

cs.CV↗

arXiv2022

Subband-based Generative Adversarial Network for Non-parallel Many-to-many Voice Conversion

Voice conversion is to generate a new speech with the source content and a target voice style. In this paper, we focus on one general setting, i.e., non-parallel many-to-many voice conversion, which is close to the real-world scenario. As the name implies, non-parallel many-to-many voice conversion does not require the paired source and reference speeches and can be applied to arbitrary voice transfer. In recent years, Generative Adversarial Networks (GANs) and other techniques such as Conditional Variational Autoencoders (CVAEs) have made considerable progress in this field. However, due to the sophistication of voice conversion, the style similarity of the converted speech is still unsatisfactory. Inspired by the inherent structure of mel-spectrogram, we propose a new voice conversion framework, i.e., Subband-based Generative Adversarial Network for Voice Conversion (SGAN-VC). SGAN-VC converts each subband content of the source speech separately by explicitly utilizing the spatial characteristics between different subbands. SGAN-VC contains one style encoder, one content encoder, and one decoder. In particular, the style encoder network is designed to learn style codes for different subbands of the target speaker. The content encoder network can capture the content information on the source speech. Finally, the decoder generates particular subband content. In addition, we propose a pitch-shift module to fine-tune the pitch of the source speaker, making the converted tone more accurate and explainable. Extensive experiments demonstrate that the proposed approach achieves state-of-the-art performance on VCTK Corpus and AISHELL3 datasets both qualitatively and quantitatively, whether on seen or unseen data. Furthermore, the content intelligibility of SGAN-VC on unseen data even exceeds that of StarGANv2-VC with ASR network assistance.

cs.SD↗

arXiv2022

High-throughput screening of strong electron-phonon couplings in ternary metal diborides

We perform a high-throughput screening on phonon-mediated superconductivity in ternary metal diboride structure with alkali, alkaline earth, and transition metals. We find 17 ground states and 78 low-energy metastable phases. From fast calculations of zone-center electron-phonon coupling, 43 compounds are revealed to show electron-phonon coupling strength higher than that of MgB2. An anti-correlation between energetic stability and electron-phonon coupling strength is identified. We suggest two phases, i.e., Li3ZrB8 and Ca3YB8, to be synthesized, which show reasonable energetic stability and superconducting critical temperature.

cond-mat.supr-con↗

arXiv2022

FedMed-ATL: Misaligned Unpaired Brain Image Synthesis via Affine Transform Loss

The existence of completely aligned and paired multi-modal neuroimaging data has proved its effectiveness in the diagnosis of brain diseases. However, collecting the full set of well-aligned and paired data is impractical, since the practical difficulties may include high cost, long time acquisition, image corruption, and privacy issues. Previously, the misaligned unpaired neuroimaging data (termed as MUD) are generally treated as noisy label. However, such a noisy label-based method fail to accomplish well when misaligned data occurs distortions severely. For example, the angle of rotation is different. In this paper, we propose a novel federated self-supervised learning (FedMed) for brain image synthesis. An affine transform loss (ATL) was formulated to make use of severely distorted images without violating privacy legislation for the hospital. We then introduce a new data augmentation procedure for self-supervised training and fed it into three auxiliary heads, namely auxiliary rotation, auxiliary translation and auxiliary scaling heads. The proposed method demonstrates the advanced performance in both the quality of our synthesized results under a severely misaligned and unpaired data setting, and better stability than other GAN-based algorithms. The proposed method also reduces the demand for deformable registration while encouraging to leverage the misaligned and unpaired data. Experimental results verify the outstanding performance of our learning paradigm compared to other state-of-the-art approaches.

eess.IV↗

arXiv2022

Exploiting Context Information for Generic Event Boundary Captioning

Generic Event Boundary Captioning (GEBC) aims to generate three sentences describing the status change for a given time boundary. Previous methods only process the information of a single boundary at a time, which lacks utilization of video context information. To tackle this issue, we design a model that directly takes the whole video as input and generates captions for all boundaries parallelly. The model could learn the context information for each time boundary by modeling the boundary-boundary interactions. Experiments demonstrate the effectiveness of context information. The proposed method achieved a 72.84 score on the test set, and we reached the $2^{nd}$ place in this challenge. Our code is available at: \url{https://github.com/zjr2000/Context-GEBC}

cs.CV↗

arXiv2022

VLMixer: Unpaired Vision-Language Pre-training via Cross-Modal CutMix

Existing vision-language pre-training (VLP) methods primarily rely on paired image-text datasets, which are either annotated by enormous human labors, or crawled from the internet followed by elaborate data cleaning techniques. To reduce the dependency on well-aligned image-text pairs, it is promising to directly leverage the large-scale text-only and image-only corpora. This paper proposes a data augmentation method, namely cross-modal CutMix (CMC), for implicit cross-modal alignment learning in unpaired VLP. Specifically, CMC transforms natural sentences from the textual view into a multi-modal view, where visually-grounded words in a sentence are randomly replaced by diverse image patches with similar semantics. There are several appealing proprieties of the proposed CMC. First, it enhances the data diversity while keeping the semantic meaning intact for tackling problems where the aligned data are scarce; Second, by attaching cross-modal noise on uni-modal data, it guides models to learn token-level interactions across modalities for better denoising. Furthermore, we present a new unpaired VLP method, dubbed as VLMixer, that integrates CMC with contrastive learning to pull together the uni-modal and multi-modal views for better instance-level alignments among different modalities. Extensive experiments on five downstream tasks show that VLMixer could surpass previous state-of-the-art unpaired VLP methods.

cs.CV↗

arXiv2022

Benchmarks for Corruption Invariant Person Re-identification

When deploying person re-identification (ReID) model in safety-critical applications, it is pivotal to understanding the robustness of the model against a diverse array of image corruptions. However, current evaluations of person ReID only consider the performance on clean datasets and ignore images in various corrupted scenarios. In this work, we comprehensively establish six ReID benchmarks for learning corruption invariant representation. In the field of ReID, we are the first to conduct an exhaustive study on corruption invariant learning in single- and cross-modality datasets, including Market-1501, CUHK03, MSMT17, RegDB, SYSU-MM01. After reproducing and examining the robustness performance of 21 recent ReID methods, we have some observations: 1) transformer-based models are more robust towards corrupted images, compared with CNN-based models, 2) increasing the probability of random erasing (a commonly used augmentation method) hurts model corruption robustness, 3) cross-dataset generalization improves with corruption robustness increases. By analyzing the above observations, we propose a strong baseline on both single- and cross-modality ReID datasets which achieves improved robustness against diverse corruptions. Our codes are available on https://github.com/MinghuiChen43/CIL-ReID.

cs.CV↗

arXiv2022

Structure and motifs of iron oxides from 1 to 3 TPa

Iron oxides are fundamental components of planet-forming materials. Understanding the Fe-O system's behavior and properties under high pressure can help us identify many new phases and states possible in exoplanetary interiors, especially terrestrial ones. Using the adaptive genetic algorithm (AGA), we investigate the structure of iron oxides for a wide range of stoichiometries ($0.25\leq x_O \leq 0.8$) at 1, 2, and 3 TPa. Five unreported ground-state structures with Fe$_2$O, FeO, Fe$_3$O$_5$, FeO$_2$, and FeO$_4$ compositions are identified. The calculated density of states (DOS) suggests that, except for FeO$_4$, all phases are metallic, but their carrier densities decrease with increasing pressure and oxygen content. The cluster alignment analysis of stable and metastable phases shows that several motifs may co-exist in a structure of iron oxides with low O content. In contrast, most iron oxides with high O content adopt a simple BCC motif at TPa pressures. Our results provide a crystal structure database of iron oxides for modeling and understanding the interiors of exoplanets.

cond-mat.mtrl-sci↗

arXiv2022

Semantic-Aware Pretraining for Dense Video Captioning

This report describes the details of our approach for the event dense-captioning task in ActivityNet Challenge 2021. We present a semantic-aware pretraining method for dense video captioning, which empowers the learned features to recognize high-level semantic concepts. Diverse video features of different modalities are fed into an event captioning module to generate accurate and meaningful sentences. Our final ensemble model achieves a 10.00 METEOR score on the test set.

cs.CV↗

arXiv2022

RGBD Object Tracking: An In-depth Review

RGBD object tracking is gaining momentum in computer vision research thanks to the development of depth sensors. Although numerous RGBD trackers have been proposed with promising performance, an in-depth review for comprehensive understanding of this area is lacking. In this paper, we firstly review RGBD object trackers from different perspectives, including RGBD fusion, depth usage, and tracking framework. Then, we summarize the existing datasets and the evaluation metrics. We benchmark a representative set of RGBD trackers, and give detailed analyses based on their performances. Particularly, we are the first to provide depth quality evaluation and analysis of tracking results in depth-friendly scenarios in RGBD tracking. For long-term settings in most RGBD tracking videos, we give an analysis of trackers' performance on handling target disappearance. To enable better understanding of RGBD trackers, we propose robustness evaluation against input perturbations. Finally, we summarize the challenges and provide open directions for this community. All resources are publicly available at https://github.com/memoryunreal/RGBD-tracking-review.

cs.CV↗