We introduce the problem of referring object manipulation (ROM), which aims to generate photo-realistic image edits regarding two textual descriptions: 1) a text referring to an object in the input image and 2) a text describing how to manipulate the referred object. A successful ROM model would enable users to simply use natural language to manipulate images, removing the need for learning sophisticated image editing software. We present one of the first approach to address this challenging multi-modal problem by combining a referring image segmentation method with a text-guided diffusion model. Specifically, we propose a conditional classifier-free guidance scheme to better guide the diffusion process along the direction from the referring expression to the target prompt. In addition, we provide a new localized ranking method and further improvements to make the generated edits more robust. Experimental results show that the proposed framework can serve as a simple but strong baseline for referring object manipulation. Also, comparisons with several baseline text-guided diffusion models demonstrate the effectiveness of our conditional classifier-free guidance technique.
论文检索
输入标题、作者或关键词，从 8,216 篇学术成果中精准定位
Chart question answering (CQA) is a task used for assessing chart comprehension, which is fundamentally different from understanding natural images. CQA requires analyzing the relationships between the textual and the visual components of a chart, in order to answer general questions or infer numerical values. Most existing CQA datasets and models are based on simplifying assumptions that often enable surpassing human performance. In this work, we address this outcome and propose a new model that jointly learns classification and regression. Our language-vision setup uses co-attention transformers to capture the complex real-world interactions between the question and the textual elements. We validate our design with extensive experiments on the realistic PlotQA dataset, outperforming previous approaches by a large margin, while showing competitive performance on FigureQA. Our model is particularly well suited for realistic questions with out-of-vocabulary answers that require regression.
Most models tasked to ground referential utterances in 2D and 3D scenes learn to select the referred object from a pool of object proposals provided by a pre-trained detector. This is limiting because an utterance may refer to visual entities at various levels of granularity, such as the chair, the leg of the chair, or the tip of the front leg of the chair, which may be missed by the detector. We propose a language grounding model that attends on the referential utterance and on the object proposal pool computed from a pre-trained detector to decode referenced objects with a detection head, without selecting them from the pool. In this way, it is helped by powerful pre-trained object detectors without being restricted by their misses. We call our model Bottom Up Top Down DEtection TRansformers (BUTD-DETR) because it uses both language guidance (top down) and objectness guidance (bottom-up) to ground referential utterances in images and point clouds. Moreover, BUTD-DETR casts object detection as referential grounding and uses object labels as language prompts to be grounded in the visual scene, augmenting supervision for the referential grounding task in this way. The proposed model sets a new state-of-the-art across popular 3D language grounding benchmarks with significant performance gains over previous 3D approaches (12.6% on SR3D, 11.6% on NR3D and 6.3% on ScanRefer). When applied in 2D images, it performs on par with the previous state of the art. We ablate the design choices of our model and quantify their contribution to performance. Our code and checkpoints can be found at the project website https://butd-detr.github.io
Visual entailment is a recently proposed multimodal reasoning task where the goal is to predict the logical relationship of a piece of text to an image. In this paper, we propose an extension of this task, where the goal is to predict the logical relationship of fine-grained knowledge elements within a piece of text to an image. Unlike prior work, our method is inherently explainable and makes logical predictions at different levels of granularity. Because we lack fine-grained labels to train our method, we propose a novel multi-instance learning approach which learns a fine-grained labeling using only sample-level supervision. We also impose novel semantic structural constraints which ensure that fine-grained predictions are internally semantically consistent. We evaluate our method on a new dataset of manually annotated knowledge elements and show that our method achieves 68.18% accuracy at this challenging task while significantly outperforming several strong baselines. Finally, we present extensive qualitative results illustrating our method’s predictions and the visual evidence our method relied on. Our code and annotated dataset can be found at the enclosed link.
Story visualization aims to generate a sequence of images to narrate each sentence in a multi-sentence story with a global consistency across dynamic scenes and characters. Current works still struggle with output images’ quality and consistency, and rely on additional semantic information or auxiliary captioning networks. To address these challenges, we first introduce a new sentence representation, which incorporates word information from all story sentences to mitigate the inconsistency problem. Then, we propose a new discriminator with fusion features and further extend the spatial attention to improve image quality and story consistency. Extensive experiments on different datasets and human evaluation demonstrate the superior performance of our approach, compared to state-of-the-art methods, neither using segmentation masks nor auxiliary captioning networks.
Vision-and-Language Navigation (VLN) requires an agent to follow complex natural language instructions and perceive the visual environment for real-world navigation. Intuitively, we find that instruction disentanglement for each viewpoint along the agent’s path is critical for accurate navigation. However, most methods only utilize the whole complex instruction or inaccurate sub-instructions due to the lack of accurate disentanglement as an intermediate supervision stage. To address this problem, we propose a new Disentanglement framework with Decoupled Labels (DDL) for VLN. Firstly, we manually extend the benchmark dataset Room-to-Room with landmark- and action-aware labels in order to provide fine-grained information for each viewpoint. Furthermore, to enhance the generalization ability, we propose a Decoupled Label Speaker module to generate pseudo-labels for augmented data and reinforcement training. To fully use the proposed fine-grained labels, we design a Disentangled Decoding Module to guide discriminative feature extraction and help alignment of multi-modalities. To reveal the generality of our proposed method, we apply it on a LSTM-based model and two recent Transformer-based models. Extensive experiments on two VLN benchmarks (i.e., R2R and R4R) demonstrate the effectiveness of our approach, achieving better performance than previous state-of-the-art methods.
Machine learning has advanced dramatically, narrowing the accuracy gap to humans in multimodal tasks like visual question answering (VQA). However, while humans can say ""I don’t know"" when they are uncertain (i.e., abstain from answering a question), such ability has been largely neglected in multimodal research, despite the importance of this problem to the usage of VQA in real settings. In this work, we promote a problem formulation for reliable VQA, where we prefer abstention over providing an incorrect answer. We first enable abstention capabilities for several VQA models, and analyze both their coverage, the portion of questions answered, and risk, the error on that portion. For that, we explore several abstention approaches. We find that although the best performing models achieve over 71% accuracy on the VQA v2 dataset, introducing the option to abstain by directly using a model’s softmax scores limits them to answering less than 8% of the questions to achieve a low risk of error (i.e., 1%). This motivates us to utilize a multimodal selection function to directly estimate the correctness of the predicted answers, which we show can increase the coverage by, for example, 2.4x from 6.8% to 16.3% at 1% risk. While it is important to analyze both coverage and risk, these metrics have a trade-off which makes comparing VQA models challenging. To address this, we also propose an Effective Reliability metric for VQA that places a larger cost on incorrect answers compared to abstentions. This new problem formulation, metric, and analysis for VQA provide the groundwork for building effective and reliable VQA models that have the self-awareness to abstain if and only if they don’t know the answer.
Video question answering is a challenging task that requires understanding jointly the language input, the visual information in individual video frames, as well as the temporal information about the events occurring in the video. In this paper, we propose a novel multi-stream video encoder for video question answering that uses multiple video inputs and a new video-text iterative co-tokenization approach to answer a variety of questions related to videos. We experimentally evaluate the model on several datasets, such as MSRVTT-QA, MSVD-QA, IVQA, outperforming the previous state-of-the-art by large margins. Simultaneously, our model reduces the required GFLOPs from 150-360 to only 67, producing a highly efficient video question answering model.
Multi-modal data abounds in biomedicine, such as radiology images and reports. Interpreting this data at scale is essential for improving clinical care and accelerating clinical research. Biomedical text with its complex semantics poses additional challenges in vision-language modelling compared to the general domain, and previous work has used insufficiently adapted models that lack domain-specific language understanding. In this paper, we show that principled textual semantic modelling can substantially improve contrastive learning in self-supervised vision-language processing. We release a language model that achieves state-of-the-art results in radiology natural-language inference through its improved vocabulary and novel language pretraining objective leveraging semantics and discourse characteristics in radiology reports. Further, we propose a self-supervised joint vision-language approach with a focus on better text modelling. It establishes new state of the art results on a wide range of publicly available benchmarks, in part by leveraging our new domain-specific language model. We release a new dataset with locally-aligned phrase grounding annotations by radiologists to facilitate the study of complex semantic modelling in biomedical vision-language processing. A broad evaluation, including on this new dataset, shows that our contrastive learning approach, aided by textual-semantic modelling, outperforms prior methods in segmentation tasks, despite only using a global-alignment objective.
Transformers for visual-language representation learning have been getting a lot of interest and shown tremendous performance on visual question answering (VQA) and grounding. However, most systems that show good performance of those tasks still rely on pre-trained object detectors during training, which limits their applicability to the object classes available for those detectors. To mitigate this limitation, this paper focuses on the problem of weakly supervised grounding in the context of visual question answering in transformers. Our approach leverages capsules by transforming each visual token into a capsule representation in the visual encoder; it then uses activations from language self-attention layers as a text-guided selection module to mask those capsules before they are forwarded to the next layer. We evaluate our approach on the challenging GQA as well as VQA-HAT dataset for VQA grounding. Our experiments show that: while removing the information of masked objects from standard transformer architectures leads to a significant drop in performance, the integration of capsules significantly improves the grounding ability of such systems and provides new state-of-the-art results compared to other approaches in the field.
Pooling methods are necessities for modern neural networks for increasing receptive fields and lowering down computational costs. However, commonly used hand-crafted pooling approaches, e.g. max pooling and average pooling, may not well preserve discriminative features. While many researchers have elaborately designed various pooling variants in spatial domain to handle these limitations with much progress, the temporal aspect is rarely visited where directly applying hand-crafted methods or these specialized spatial variants may not be optimal. In this paper, we derive temporal lift pooling (TLP) from the Lifting Scheme in signal processing to intelligently downsample features of different temporal hierarchies. The Lifting Scheme factorizes input signals into various sub-bands with different frequency, which can be viewed as different temporal movement patterns. Our TLP is a three-stage procedure, which performs signal decomposition, component weighting and information fusion to generate a refined downsized feature map. We select a typical temporal task with long sequences, i.e. continuous sign language recognition (CSLR), as our testbed to verify the effectiveness of TLP. Experiments on two large-scale datasets show TLP outperforms hand-crafted methods and specialized spatial variants by a large margin (1.5%) with similar computational overhead. As a robust feature extractor, TLP exhibits great generalizability upon multiple backbones on various datasets and achieves new state-of-the-art results on two large-scale CSLR datasets. Visualizations further demonstrate the mechanism of TLP in correcting gloss borders.
Contrastive Vision-Language Pre-training, known as CLIP, has provided a new paradigm for learning visual representations using large-scale image-text pairs. It shows impressive performance on downstream tasks by zero-shot knowledge transfer. To further enhance CLIP’s adaption capability, existing methods proposed to fine-tune additional learnable modules, which significantly improves the few-shot performance but introduces extra training time and computational resources. In this paper, we propose a training-free adaption method for CLIP to conduct few-shot classification, termed as Tip-Adapter, which not only inherits the training-free advantage of zero-shot CLIP but also performs comparably to those training-required approaches. Tip-Adapter constructs the adapter via a key-value cache model from the few-shot training set, and updates the prior knowledge encoded in CLIP by feature retrieval. On top of that, the performance of Tip-Adapter can be further boosted to be state-of-the-art on ImageNet by fine-tuning the cache model for 10$\times$ fewer epochs than existing methods, which is both effective and efficient. We conduct extensive experiments of few-shot classification on 11 datasets to demonstrate the superiority of our proposed methods. Code is released at https://github.com/gaopengcuhk/Tip-Adapter.
360° video saliency detection is one of the challenging benchmarks for 360° video understanding since non-negligible distortion and discontinuity occur in the projection of any format of 360° videos, and capture-worthy viewpoint in the omnidirectional sphere is ambiguous by nature. We present a new framework named Panoramic Vision Transformer (PAVER). We design the encoder using Vision Transformer with deformable convolution, which enables us not only to plug pretrained models from normal videos into our architecture without additional modules or finetuning but also to perform geometric approximation only once, unlike previous deep CNN-based approaches. Thanks to its powerful encoder, PAVER can learn the saliency from three simple relative relations among local patch features, outperforming state-of-the-art models for the Wild360 benchmark by large margins without supervision or auxiliary information like class activation. We demonstrate the utility of our saliency prediction model with the omnidirectional video quality assessment task in VQA-ODV, where we consistently improve performance without any form of supervision, including head movement.
In this work, we consider the problem of weakly-supervised multi-step localization in instructional videos. An established approach to this problem is to rely on a given list of steps. However, in reality, there is often more than one way to execute a procedure successfully, by following the set of steps in slightly varying orders. Thus, for successful localization in a given video, recent works require the actual order of procedure steps in the video, to be provided by human annotators at both training and test times. Instead, here, we only rely on generic procedural text that is not tied to a specific video. We represent the various ways to complete the procedure by transforming the list of instructions into a procedure flow graph which captures the partial order of steps. Using the flow graphs reduces both training and test time annotation requirements. To this end, we introduce the new problem of flow graph to video grounding. In this setup, we seek the optimal step ordering consistent with the procedure flow graph and a given video. To solve this problem, we propose a new algorithm - Graph2Vid - that infers the actual ordering of steps in the video and simultaneously localizes them. To show the advantage of our proposed formulation, we extend the CrossTask dataset with procedure flow graph information. Our experiments show that Graph2Vid is both more efficient than the baselines and yields strong step localization results, without the need for step order annotation.
Most online video understanding tasks aim to immediately process each streaming frame and output predictions frame-by-frame. For extension to instance-level predictions of existing online video tasks, Online Temporal Action Localization (On-TAL) has been recently proposed. However, simple On-TAL approaches of grouping per-frame predictions have limitations due to the lack of instance-level context. To this end, we propose Online Anchor Transformer (OAT) to extend the anchor-based action localization model to the online setting. We also introduce an online-applicable post-processing method that suppresses repetitive action proposals. Evaluations of On-TAL on THUMOS’14, MUSES, and BBDB show significant improvements in terms of mAP, and our model shows comparable performance to the state-of-the-art offline TAL methods with a minor change of the post-processing method. In addition to mAP evaluation, we additionally present a new online-oriented metric of early detection for On-TAL, and measure the responsiveness of each On-TAL approach.
The goal of this paper is to bypass the need for labelled examples in few-shot video understanding at run time. While proven effective, in many practical video settings even labelling a few examples appears unrealistic. This is especially true as the level of details in spatio-temporal video understanding and with it, the complexity of annotations continues to increase. Rather than performing few-shot learning with a human oracle to provide a few densely labelled support videos, we propose to automatically learn to find appropriate support videos given a query. We call this self-shot learning and we outline a simple self-supervised learning method to generate an embedding space well-suited for unsupervised retrieval of relevant samples. To showcase this novel setting, we tackle, for the first time, video instance segmentation in a self-shot (and few-shot) setting, where the goal is to segment instances at the pixel-level across the spatial and temporal domains. We provide strong baseline performances that utilize a novel transformer-based model and show that self-shot learning can even surpass few-shot and can be positively combined for further performance gains. Experiments on new benchmarks show that our approach achieves strong performance, is competitive to oracle support in some settings, scales to large unlabelled video collections, and can be combined in a semi-supervised setting.
Trajectory prediction has been widely pursued in many fields, and many model-based and model-free methods have been explored. The former include rule-based, geometric or optimization-based models, and the latter are mainly comprised of deep learning approaches. In this paper, we propose a new method combining both methodologies based on a new Neural Differential Equation model. Our new model (Neural Social Physics or NSP) is a deep neural network within which we use an explicit physics model with learnable parameters. The explicit physics model serves as a strong inductive bias in modeling pedestrian behaviors, while the rest of the network provides a strong data-fitting capability in terms of system parameter estimation and dynamics stochasticity modeling. We compare NSP with 15 recent deep learning methods on 6 datasets and improve the state-of-the-art performance by 5.56%-70%. Besides, we show that NSP has better generalizability in predicting plausible trajectories in drastically different scenarios where the density is 2-5 times as high as the testing data. Finally, we show that the physics model in NSP can provide plausible explanations for pedestrian behaviors, as opposed to black-box deep learning. Code is available: https://github.com/realcrane/Human- Trajectory-Prediction-via-Neural-Social-Physics.
Retrieving accurate semantic information in challenging high dynamic range (HDR) and high-speed conditions remains an open challenge for image-based algorithms due to severe image degradations. Event cameras promise to address these challenges since they feature a much higher dynamic range and are resilient to motion blur. Nonetheless, semantic segmentation with event cameras is still in its infancy which is chiefly due to the lack of high-quality, labeled datasets. In this work, we introduce ESS (Event-based Semantic Segmentation), which tackles this problem by directly transferring the semantic segmentation task from existing labeled image datasets to unlabeled events via unsupervised domain adaptation (UDA). Compared to existing UDA methods, our approach aligns recurrent, motion-invariant event embeddings with image embeddings. For this reason, our method neither requires video data nor per-pixel alignment between images and events and, crucially, does not need to hallucinate motion from still images. Additionally, we introduce DSEC-Semantic, the first large-scale event-based dataset with fine-grained labels. We show that using image labels alone, ESS outperforms existing UDA approaches, and when combined with event labels, it even outperforms state-of-the-art supervised approaches on both DDD17 and DSEC-Semantic. Finally, ESS is general-purpose, which unlocks the vast amount of existing labeled image datasets and paves the way for new and exciting research directions in new fields previously inaccessible for event cameras.
This paper addresses an important problem of ranking the pre-trained deep neural networks and screening the most transferable ones for downstream tasks. It is challenging because the ground-truth model ranking for each task can only be generated by fine-tuning the pre-trained models on the target dataset, which is brute-force and computationally expensive. Recent advanced methods proposed several lightweight transferability metrics to predict the fine-tuning results. However, these approaches only capture static representations but neglect the fine-tuning dynamics. To this end, this paper proposes a new transferability metric, called \textbf{S}elf-challenging \textbf{F}isher \textbf{D}iscriminant \textbf{A}nalysis (\textbf{SFDA}), which has many appealing benefits that existing works do not have. First, SFDA can embed the static features into a Fisher space and refine them for better separability between classes. Second, SFDA uses a self-challenging mechanism to encourage different pre-trained models to differentiate on hard examples. Third, SFDA can easily select multiple pre-trained models for the model ensemble. Extensive experiments on $33$ pre-trained models of $11$ downstream tasks show that SFDA is efficient, effective, and robust when measuring the transferability of pre-trained models. For instance, compared with the state-of-the-art method NLEEP, SFDA demonstrates an average of $59.1$\% gain while bringing $22.5$x speedup in wall-clock time. The code will be available at \url{https://github.com/TencentARC/SFDA}.
Recent years have witnessed a great development of Convolutional Neural Networks in semantic segmentation, where all classes of training images are simultaneously available. In practice, new images are usually made available in a consecutive manner, leading to a problem called Continual Semantic Segmentation (CSS). Typically, CSS faces the forgetting problem since previous training images are unavailable, and the semantic shift problem of the background class. Considering the semantic segmentation as a context-dependent pixel-level classification task, we explore CSS from a new perspective of context analysis in this paper. We observe that the context of old-class pixels in the new images is much more biased on new classes than that in the old images, which can sharply aggravate the old-class forgetting and new-class overfitting. To tackle the obstacle, we propose a biased-context-rectified CSS framework with a context-rectified image-duplet learning scheme and a biased-context-insensitive consistency loss. Furthermore, we propose an adaptive re-weighting class-balanced learning strategy for the biased class distribution. Our approach outperforms state-of-the-art methods by a large margin in existing CSS scenarios.