arXiv subjects

Zicheng Liu

Publications and source records attributed to Zicheng Liu.

At least 163 records · Page 9Linked to original sources

arXiv2022

SwinBERT: End-to-End Transformers with Sparse Attention for Video Captioning

The canonical approach to video captioning dictates a caption generation model to learn from offline-extracted dense video features. These feature extractors usually operate on video frames sampled at a fixed frame rate and are often trained on image/video understanding tasks, without adaption to video captioning data. In this work, we present SwinBERT, an end-to-end transformer-based model for video captioning, which takes video frame patches directly as inputs, and outputs a natural language description. Instead of leveraging multiple 2D/3D feature extractors, our method adopts a video transformer to encode spatial-temporal representations that can adapt to variable lengths of video input without dedicated design for different frame rates. Based on this model architecture, we show that video captioning can benefit significantly from more densely sampled video frames as opposed to previous successes with sparsely sampled video frames for video-and-language understanding tasks (e.g., video question answering). Moreover, to avoid the inherent redundancy in consecutive video frames, we propose adaptively learning a sparse attention mask and optimizing it for task-specific performance improvement through better long-range video sequence modeling. Through extensive experiments on 5 video captioning datasets, we show that SwinBERT achieves across-the-board performance improvements over previous methods, often by a large margin. The learned sparse attention masks in addition push the limit to new state of the arts, and can be transferred between different video lengths and between different datasets. Code is available at https://github.com/microsoft/SwinBERT

cs.CV↗

arXiv2022

An Intriguing Property of Geophysics Inversion

Inversion techniques are widely used to reconstruct subsurface physical properties (e.g., velocity, conductivity) from surface-based geophysical measurements (e.g., seismic, electric/magnetic (EM) data). The problems are governed by partial differential equations (PDEs) like the wave or Maxwell's equations. Solving geophysical inversion problems is challenging due to the ill-posedness and high computational cost. To alleviate those issues, recent studies leverage deep neural networks to learn the inversion mappings from measurements to the property directly. In this paper, we show that such a mapping can be well modeled by a very shallow (but not wide) network with only five layers. This is achieved based on our new finding of an intriguing property: a near-linear relationship between the input and output, after applying integral transform in high dimensional space. In particular, when dealing with the inversion from seismic data to subsurface velocity governed by a wave equation, the integral results of velocity with Gaussian kernels are linearly correlated to the integral of seismic data with sine kernels. Furthermore, this property can be easily turned into a light-weight encoder-decoder network for inversion. The encoder contains the integration of seismic data and the linear transformation without need for fine-tuning. The decoder only consists of a single transformer block to reverse the integral of velocity. Experiments show that this interesting property holds for two geophysics inversion problems over four different datasets. Compared to much deeper InversionNet, our method achieves comparable accuracy, but consumes significantly fewer parameters.

cs.LG↗

arXiv2022

Consistent Video Instance Segmentation with Inter-Frame Recurrent Attention

Video instance segmentation aims at predicting object segmentation masks for each frame, as well as associating the instances across multiple frames. Recent end-to-end video instance segmentation methods are capable of performing object segmentation and instance association together in a direct parallel sequence decoding/prediction framework. Although these methods generally predict higher quality object segmentation masks, they can fail to associate instances in challenging cases because they do not explicitly model the temporal instance consistency for adjacent frames. We propose a consistent end-to-end video instance segmentation framework with Inter-Frame Recurrent Attention to model both the temporal instance consistency for adjacent frames and the global temporal context. Our extensive experiments demonstrate that the Inter-Frame Recurrent Attention significantly improves temporal instance consistency while maintaining the quality of the object segmentation masks. Our model achieves state-of-the-art accuracy on both YouTubeVIS-2019 (62.1\%) and YouTubeVIS-2021 (54.7\%) datasets. In addition, quantitative and qualitative results show that the proposed methods predict more temporally consistent instance segmentation masks.

cs.CV↗

arXiv2022

LAVENDER: Unifying Video-Language Understanding as Masked Language Modeling

Unified vision-language frameworks have greatly advanced in recent years, most of which adopt an encoder-decoder architecture to unify image-text tasks as sequence-to-sequence generation. However, existing video-language (VidL) models still require task-specific designs in model architecture and training objectives for each task. In this work, we explore a unified VidL framework LAVENDER, where Masked Language Modeling (MLM) is used as the common interface for all pre-training and downstream tasks. Such unification leads to a simplified model architecture, where only a lightweight MLM head, instead of a decoder with much more parameters, is needed on top of the multimodal encoder. Surprisingly, experimental results show that this unified framework achieves competitive performance on 14 VidL benchmarks, covering video question answering, text-to-video retrieval and video captioning. Extensive analyses further demonstrate the advantage of LAVENDER over existing VidL methods in: (i) supporting all downstream tasks with just a single set of parameter values when multi-task finetuned; (ii) few-shot generalization on various downstream tasks; and (iii) enabling zero-shot evaluation on video question answering tasks. Code is available at https://github.com/microsoft/LAVENDER.

cs.CV↗

arXiv2022

Cross-modal Representation Learning for Zero-shot Action Recognition

We present a cross-modal Transformer-based framework, which jointly encodes video data and text labels for zero-shot action recognition (ZSAR). Our model employs a conceptually new pipeline by which visual representations are learned in conjunction with visual-semantic associations in an end-to-end manner. The model design provides a natural mechanism for visual and semantic representations to be learned in a shared knowledge space, whereby it encourages the learned visual embedding to be discriminative and more semantically consistent. In zero-shot inference, we devise a simple semantic transfer scheme that embeds semantic relatedness information between seen and unseen classes to composite unseen visual prototypes. Accordingly, the discriminative features in the visual structure could be preserved and exploited to alleviate the typical zero-shot issues of information loss, semantic gap, and the hubness problem. Under a rigorous zero-shot setting of not pre-training on additional datasets, the experiment results show our model considerably improves upon the state of the arts in ZSAR, reaching encouraging top-1 accuracy on UCF101, HMDB51, and ActivityNet benchmark datasets. Code will be made available.

cs.CV↗

arXiv2022

VIOLET : End-to-End Video-Language Transformers with Masked Visual-token Modeling

A great challenge in video-language (VidL) modeling lies in the disconnection between fixed video representations extracted from image/video understanding models and downstream VidL data. Recent studies try to mitigate this disconnection via end-to-end training. To make it computationally feasible, prior works tend to "imagify" video inputs, i.e., a handful of sparsely sampled frames are fed into a 2D CNN, followed by a simple mean-pooling or concatenation to obtain the overall video representations. Although achieving promising results, such simple approaches may lose temporal information that is essential for performing downstream VidL tasks. In this work, we present VIOLET, a fully end-to-end VIdeO-LanguagE Transformer, which adopts a video transformer to explicitly model the temporal dynamics of video inputs. Further, unlike previous studies that found pre-training tasks on video inputs (e.g., masked frame modeling) not very effective, we design a new pre-training task, Masked Visual-token Modeling (MVM), for better video modeling. Specifically, the original video frame patches are "tokenized" into discrete visual tokens, and the goal is to recover the original visual tokens based on the masked patches. Comprehensive analysis demonstrates the effectiveness of both explicit temporal modeling via video transformer and MVM. As a result, VIOLET achieves new state-of-the-art performance on 5 video question answering tasks and 4 text-to-video retrieval tasks.

cs.CV↗

arXiv2022

Improving Vision Transformers for Incremental Learning

This paper proposes a working recipe of using Vision Transformer (ViT) in class incremental learning. Although this recipe only combines existing techniques, developing the combination is not trivial. Firstly, naive application of ViT to replace convolutional neural networks (CNNs) in incremental learning results in serious performance degradation. Secondly, we nail down three issues of naively using ViT: (a) ViT has very slow convergence when the number of classes is small, (b) more bias towards new classes is observed in ViT than CNN-based architectures, and (c) the conventional learning rate of ViT is too low to learn a good classifier layer. Finally, our solution, named ViTIL (ViT for Incremental Learning) achieves new state-of-the-art on both CIFAR and ImageNet datasets for all three class incremental learning setups by a clear margin. We believe this advances the knowledge of transformer in the incremental learning community. Code will be publicly released.

cs.CV↗

arXiv2022

Injecting Semantic Concepts into End-to-End Image Captioning

Tremendous progress has been made in recent years in developing better image captioning models, yet most of them rely on a separate object detector to extract regional features. Recent vision-language studies are shifting towards the detector-free trend by leveraging grid representations for more flexible model training and faster inference speed. However, such development is primarily focused on image understanding tasks, and remains less investigated for the caption generation task. In this paper, we are concerned with a better-performing detector-free image captioning model, and propose a pure vision transformer-based image captioning model, dubbed as ViTCAP, in which grid representations are used without extracting the regional features. For improved performance, we introduce a novel Concept Token Network (CTN) to predict the semantic concepts and then incorporate them into the end-to-end captioning. In particular, the CTN is built on the basis of a vision transformer and is designed to predict the concept tokens through a classification task, from which the rich semantic information contained greatly benefits the captioning task. Compared with the previous detector-based models, ViTCAP drastically simplifies the architectures and at the same time achieves competitive performance on various challenging image captioning datasets. In particular, ViTCAP reaches 138.1 CIDEr scores on COCO-caption Karpathy-split, 93.8 and 108.6 CIDEr scores on nocaps, and Google-CC captioning datasets, respectively.

cs.CV↗

arXiv2022

Lifelong Unsupervised Domain Adaptive Person Re-identification with Coordinated Anti-forgetting and Adaptation

Unsupervised domain adaptive person re-identification (ReID) has been extensively investigated to mitigate the adverse effects of domain gaps. Those works assume the target domain data can be accessible all at once. However, for the real-world streaming data, this hinders the timely adaptation to changing data statistics and sufficient exploitation of increasing samples. In this paper, to address more practical scenarios, we propose a new task, Lifelong Unsupervised Domain Adaptive (LUDA) person ReID. This is challenging because it requires the model to continuously adapt to unlabeled data in the target environments while alleviating catastrophic forgetting for such a fine-grained person retrieval task. We design an effective scheme for this task, dubbed CLUDA-ReID, where the anti-forgetting is harmoniously coordinated with the adaptation. Specifically, a meta-based Coordinated Data Replay strategy is proposed to replay old data and update the network with a coordinated optimization direction for both adaptation and memorization. Moreover, we propose Relational Consistency Learning for old knowledge distillation/inheritance in line with the objective of retrieval-based tasks. We set up two evaluation settings to simulate the practical application scenarios. Extensive experiments demonstrate the effectiveness of our CLUDA-ReID for both scenarios with stationary target streams and scenarios with dynamic target streams.

cs.CV↗

arXiv2022

Scaling Up Vision-Language Pre-training for Image Captioning

In recent years, we have witnessed significant performance boost in the image captioning task based on vision-language pre-training (VLP). Scale is believed to be an important factor for this advance. However, most existing work only focuses on pre-training transformers with moderate sizes (e.g., 12 or 24 layers) on roughly 4 million images. In this paper, we present LEMON, a LargE-scale iMage captiONer, and provide the first empirical study on the scaling behavior of VLP for image captioning. We use the state-of-the-art VinVL model as our reference model, which consists of an image feature extractor and a transformer model, and scale the transformer both up and down, with model sizes ranging from 13 to 675 million parameters. In terms of data, we conduct experiments with up to 200 million image-text pairs which are automatically collected from web based on the alt attribute of the image (dubbed as ALT200M). Extensive analysis helps to characterize the performance trend as the model size and the pre-training data size increase. We also compare different training recipes, especially for training on large-scale noisy data. As a result, LEMON achieves new state of the arts on several major image captioning benchmarks, including COCO Caption, nocaps, and Conceptual Captions. We also show LEMON can generate captions with long-tail visual concepts when used in a zero-shot manner.

cs.CV↗

arXiv2022

Unsupervised Learning of Full-Waveform Inversion: Connecting CNN and Partial Differential Equation in a Loop

This paper investigates unsupervised learning of Full-Waveform Inversion (FWI), which has been widely used in geophysics to estimate subsurface velocity maps from seismic data. This problem is mathematically formulated by a second order partial differential equation (PDE), but is hard to solve. Moreover, acquiring velocity map is extremely expensive, making it impractical to scale up a supervised approach to train the mapping from seismic data to velocity maps with convolutional neural networks (CNN). We address these difficulties by integrating PDE and CNN in a loop, thus shifting the paradigm to unsupervised learning that only requires seismic data. In particular, we use finite difference to approximate the forward modeling of PDE as a differentiable operator (from velocity map to seismic data) and model its inversion by CNN (from seismic data to velocity map). Hence, we transform the supervised inversion task into an unsupervised seismic data reconstruction task. We also introduce a new large-scale dataset OpenFWI, to establish a more challenging benchmark for the community. Experiment results show that our model (using seismic data alone) yields comparable accuracy to the supervised counterpart (using both seismic data and velocity map). Furthermore, it outperforms the supervised model when involving more seismic data.

cs.LG↗

arXiv2022

An Empirical Study of Training End-to-End Vision-and-Language Transformers

Vision-and-language (VL) pre-training has proven to be highly effective on various VL downstream tasks. While recent work has shown that fully transformer-based VL models can be more efficient than previous region-feature-based methods, their performance on downstream tasks often degrades significantly. In this paper, we present METER, a Multimodal End-to-end TransformER framework, through which we investigate how to design and pre-train a fully transformer-based VL model in an end-to-end manner. Specifically, we dissect the model designs along multiple dimensions: vision encoders (e.g., CLIP-ViT, Swin transformer), text encoders (e.g., RoBERTa, DeBERTa), multimodal fusion module (e.g., merged attention vs. co-attention), architectural design (e.g., encoder-only vs. encoder-decoder), and pre-training objectives (e.g., masked image modeling). We conduct comprehensive experiments and provide insights on how to train a performant VL transformer. METER achieves an accuracy of 77.64% on the VQAv2 test-std set using only 4M images for pre-training, surpassing the state-of-the-art region-feature-based model by 1.04%, and outperforming the previous best fully transformer-based model by 1.6%. Notably, when further scaled up, our best VQA model achieves an accuracy of 80.54%. Code and pre-trained models are released at https://github.com/zdou0830/METER.

cs.CV↗

arXiv2022

The Overlooked Classifier in Human-Object Interaction Recognition

Human-Object Interaction (HOI) recognition is challenging due to two factors: (1) significant imbalance across classes and (2) requiring multiple labels per image. This paper shows that these two challenges can be effectively addressed by improving the classifier with the backbone architecture untouched. Firstly, we encode the semantic correlation among classes into the classification head by initializing the weights with language embeddings of HOIs. As a result, the performance is boosted significantly, especially for the few-shot subset. Secondly, we propose a new loss named LSE-Sign to enhance multi-label learning on a long-tailed dataset. Our simple yet effective method enables detection-free HOI classification, outperforming the state-of-the-arts that require object detection and human pose by a clear margin. Moreover, we transfer the classification model to instance-level HOI detection by connecting it with an off-the-shelf object detector. We achieve state-of-the-art without additional fine-tuning.

cs.CV↗

arXiv2022

The Overlooked Classifier in Human-Object Interaction Recognition

cs.CV↗

arXiv2022

Mobile-Former: Bridging MobileNet and Transformer

We present Mobile-Former, a parallel design of MobileNet and transformer with a two-way bridge in between. This structure leverages the advantages of MobileNet at local processing and transformer at global interaction. And the bridge enables bidirectional fusion of local and global features. Different from recent works on vision transformer, the transformer in Mobile-Former contains very few tokens (e.g. 6 or fewer tokens) that are randomly initialized to learn global priors, resulting in low computational cost. Combining with the proposed light-weight cross attention to model the bridge, Mobile-Former is not only computationally efficient, but also has more representation power. It outperforms MobileNetV3 at low FLOP regime from 25M to 500M FLOPs on ImageNet classification. For instance, Mobile-Former achieves 77.9\% top-1 accuracy at 294M FLOPs, gaining 1.3\% over MobileNetV3 but saving 17\% of computations. When transferring to object detection, Mobile-Former outperforms MobileNetV3 by 8.6 AP in RetinaNet framework. Furthermore, we build an efficient end-to-end detector by replacing backbone, encoder and decoder in DETR with Mobile-Former, which outperforms DETR by 1.1 AP but saves 52\% of computational cost and 36\% of parameters.

cs.CV↗

arXiv2022

SA-VQA: Structured Alignment of Visual and Semantic Representations for Visual Question Answering

Visual Question Answering (VQA) attracts much attention from both industry and academia. As a multi-modality task, it is challenging since it requires not only visual and textual understanding, but also the ability to align cross-modality representations. Previous approaches extensively employ entity-level alignments, such as the correlations between the visual regions and their semantic labels, or the interactions across question words and object features. These attempts aim to improve the cross-modality representations, while ignoring their internal relations. Instead, we propose to apply structured alignments, which work with graph representation of visual and textual content, aiming to capture the deep connections between the visual and textual modalities. Nevertheless, it is nontrivial to represent and integrate graphs for structured alignments. In this work, we attempt to solve this issue by first converting different modality entities into sequential nodes and the adjacency graph, then incorporating them for structured alignments. As demonstrated in our experimental results, such a structured alignment improves reasoning performance. In addition, our model also exhibits better interpretability for each generated answer. The proposed model, without any pretraining, outperforms the state-of-the-art methods on GQA dataset, and beats the non-pretrained state-of-the-art methods on VQA-v2 dataset.

cs.CV↗

arXiv2021

Playing Lottery Tickets with Vision and Language

Large-scale pre-training has recently revolutionized vision-and-language (VL) research. Models such as LXMERT and UNITER have significantly lifted the state of the art over a wide range of VL tasks. However, the large number of parameters in such models hinders their application in practice. In parallel, work on the lottery ticket hypothesis (LTH) has shown that deep neural networks contain small matching subnetworks that can achieve on par or even better performance than the dense networks when trained in isolation. In this work, we perform the first empirical study to assess whether such trainable subnetworks also exist in pre-trained VL models. We use UNITER as the main testbed (also test on LXMERT and ViLT), and consolidate 7 representative VL tasks for experiments, including visual question answering, visual commonsense reasoning, visual entailment, referring expression comprehension, image-text retrieval, GQA, and NLVR$^2$. Through comprehensive analysis, we summarize our main findings as follows. ($i$) It is difficult to find subnetworks that strictly match the performance of the full model. However, we can find "relaxed" winning tickets at 50%-70% sparsity that maintain 99% of the full accuracy. ($ii$) Subnetworks found by task-specific pruning transfer reasonably well to the other tasks, while those found on the pre-training tasks at 60%/70% sparsity transfer universally, matching 98%/96% of the full accuracy on average over all the tasks. ($iii$) Besides UNITER, other models such as LXMERT and ViLT can also play lottery tickets. However, the highest sparsity we can achieve for ViLT is far lower than LXMERT and UNITER (30% vs. 70%). ($iv$) LTH also remains relevant when using other training methods (e.g., adversarial training).

cs.CV↗

arXiv2021

MLP Architectures for Vision-and-Language Modeling: An Empirical Study

We initiate the first empirical study on the use of MLP architectures for vision-and-language (VL) fusion. Through extensive experiments on 5 VL tasks and 5 robust VQA benchmarks, we find that: (i) Without pre-training, using MLPs for multimodal fusion has a noticeable performance gap compared to transformers; (ii) However, VL pre-training can help close the performance gap; (iii) Instead of heavy multi-head attention, adding tiny one-head attention to MLPs is sufficient to achieve comparable performance to transformers. Moreover, we also find that the performance gap between MLPs and transformers is not widened when being evaluated on the harder robust VQA benchmarks, suggesting using MLPs for VL fusion can generalize roughly to a similar degree as using transformers. These results hint that MLPs can effectively learn to align vision and text features extracted from lower-level encoders without heavy reliance on self-attention. Based on this, we ask an even bolder question: can we have an all-MLP architecture for VL modeling, where both VL fusion and the vision encoder are replaced with MLPs? Our result shows that an all-MLP VL model is sub-optimal compared to state-of-the-art full-featured VL models when both of them get pre-trained. However, pre-training an all-MLP can surprisingly achieve a better average score than full-featured transformer models without pre-training. This indicates the potential of large-scale pre-training of MLP-like architectures for VL modeling and inspires the future research direction on simplifying well-established VL modeling with less inductive design bias. Our code is publicly available at: https://github.com/easonnie/mlp-vil

cs.CV↗