Abstract:This paper focuses on open-ended video question answering, which aims to find the correct answers from a large answer set in response to a video-related question. This is essentially a multi-label classification task, since a question may have multiple answers. However, due to annotation costs, the labels in existing benchmarks are always extremely insufficient, typically one answer per question. As a result, existing works tend to directly treat all the unlabeled answers as negative labels, leading to limited ability for generalization. In this work, we introduce a simple yet effective ranking distillation framework (RADI) to mitigate this problem without additional manual annotation. RADI employs a teacher model trained with incomplete labels to generate rankings for potential answers, which contain rich knowledge about label priority as well as label-associated visual cues, thereby enriching the insufficient labeling information. To avoid overconfidence in the imperfect teacher model, we further present two robust and parameter-free ranking distillation approaches: a pairwise approach which introduces adaptive soft margins to dynamically refine the optimization constraints on various pairwise rankings, and a listwise approach which adopts sampling-based partial listwise learning to resist the bias in teacher ranking. Extensive experiments on five popular benchmarks consistently show that both our pairwise and listwise RADIs outperform state-of-the-art methods. Further analysis demonstrates the effectiveness of our methods on the insufficient labeling problem.
Abstract:Analyzing and forecasting trajectories of agents like pedestrians and cars in complex scenes has become more and more significant in many intelligent systems and applications. The diversity and uncertainty in socially interactive behaviors among a rich variety of agents make this task more challenging than other deterministic computer vision tasks. Researchers have made a lot of efforts to quantify the effects of these interactions on future trajectories through different mathematical models and network structures, but this problem has not been well solved. Inspired by marine animals that localize the positions of their companions underwater through echoes, we build a new anglebased trainable social representation, named SocialCircle, for continuously reflecting the context of social interactions at different angular orientations relative to the target agent. We validate the effect of the proposed SocialCircle by training it along with several newly released trajectory prediction models, and experiments show that the SocialCircle not only quantitatively improves the prediction performance, but also qualitatively helps better consider social interactions when forecasting pedestrian trajectories in a way that is consistent with human intuitions.
Abstract:Poisoning efficiency is a crucial factor in poisoning-based backdoor attacks. Attackers prefer to use as few poisoned samples as possible to achieve the same level of attack strength, in order to remain undetected. Efficient triggers have significantly improved poisoning efficiency, but there is still room for improvement. Recently, selecting efficient samples has shown promise, but it requires a proxy backdoor injection task to find an efficient poisoned sample set, which can lead to performance degradation if the proxy attack settings are different from the actual settings used by the victims. In this paper, we propose a novel Proxy-Free Strategy (PFS) that selects efficient poisoned samples based on individual similarity and set diversity, effectively addressing this issue. We evaluate the proposed strategy on several datasets, triggers, poisoning ratios, architectures, and training hyperparameters. Our experimental results demonstrate that PFS achieves higher backdoor attack strength while x500 faster than previous proxy-based selection approaches.
Abstract:Recent deep neural networks (DNNs) have come to rely on vast amounts of training data, providing an opportunity for malicious attackers to exploit and contaminate the data to carry out backdoor attacks. These attacks significantly undermine the reliability of DNNs. However, existing backdoor attack methods make unrealistic assumptions, assuming that all training data comes from a single source and that attackers have full access to the training data. In this paper, we address this limitation by introducing a more realistic attack scenario where victims collect data from multiple sources, and attackers cannot access the complete training data. We refer to this scenario as data-constrained backdoor attacks. In such cases, previous attack methods suffer from severe efficiency degradation due to the entanglement between benign and poisoning features during the backdoor injection process. To tackle this problem, we propose a novel approach that leverages the pre-trained Contrastive Language-Image Pre-Training (CLIP) model. We introduce three CLIP-based technologies from two distinct streams: Clean Feature Suppression, which aims to suppress the influence of clean features to enhance the prominence of poisoning features, and Poisoning Feature Augmentation, which focuses on augmenting the presence and impact of poisoning features to effectively manipulate the model's behavior. To evaluate the effectiveness, harmlessness to benign accuracy, and stealthiness of our method, we conduct extensive experiments on 3 target models, 3 datasets, and over 15 different settings. The results demonstrate remarkable improvements, with some settings achieving over 100% improvement compared to existing attacks in data-constrained scenarios. Our research contributes to addressing the limitations of existing methods and provides a practical and effective solution for data-constrained backdoor attacks.
Abstract:With the fast development of AI-related techniques, the applications of trajectory prediction are no longer limited to easier scenes and trajectories. More and more heterogeneous trajectories with different representation forms, such as 2D or 3D coordinates, 2D or 3D bounding boxes, and even high-dimensional human skeletons, need to be analyzed and forecasted. Among these heterogeneous trajectories, interactions between different elements within a frame of trajectory, which we call the ``Dimension-Wise Interactions'', would be more complex and challenging. However, most previous approaches focus mainly on a specific form of trajectories, which means these methods could not be used to forecast heterogeneous trajectories, not to mention the dimension-wise interaction. Besides, previous methods mostly treat trajectory prediction as a normal time sequence generation task, indicating that these methods may require more work to directly analyze agents' behaviors and social interactions at different temporal scales. In this paper, we bring a new ``view'' for trajectory prediction to model and forecast trajectories hierarchically according to different frequency portions from the spectral domain to learn to forecast trajectories by considering their frequency responses. Moreover, we try to expand the current trajectory prediction task by introducing the dimension $M$ from ``another view'', thus extending its application scenarios to heterogeneous trajectories vertically. Finally, we adopt the bilinear structure to fuse two factors, including the frequency response and the dimension-wise interaction, to forecast heterogeneous trajectories via spectrums hierarchically in a generic way. Experiments show that the proposed model outperforms most state-of-the-art methods on ETH-UCY, Stanford Drone Dataset and nuScenes with heterogeneous trajectories, including 2D coordinates, 2D and 3D bounding boxes.
Abstract:Transparent objects are widely used in industrial automation and daily life. However, robust visual recognition and perception of transparent objects have always been a major challenge. Currently, most commercial-grade depth cameras are still not good at sensing the surfaces of transparent objects due to the refraction and reflection of light. In this work, we present a transformer-based transparent object depth estimation approach from a single RGB-D input. We observe that the global characteristics of the transformer make it easier to extract contextual information to perform depth estimation of transparent areas. In addition, to better enhance the fine-grained features, a feature fusion module (FFM) is designed to assist coherent prediction. Our empirical evidence demonstrates that our model delivers significant improvements in recent popular datasets, e.g., 25% gain on RMSE and 21% gain on REL compared to previous state-of-the-art convolutional-based counterparts in ClearGrasp dataset. Extensive results show that our transformer-based model enables better aggregation of the object's RGB and inaccurate depth information to obtain a better depth representation. Our code and the pre-trained model will be available at https://github.com/yuchendoudou/TODE.
Abstract:Generative Adversarial Networks (GANs) have achieved remarkable achievements in image synthesis. These successes of GANs rely on large scale datasets, requiring too much cost. With limited training data, how to stable the training process of GANs and generate realistic images have attracted more attention. The challenges of Data-Efficient GANs (DE-GANs) mainly arise from three aspects: (i) Mismatch Between Training and Target Distributions, (ii) Overfitting of the Discriminator, and (iii) Imbalance Between Latent and Data Spaces. Although many augmentation and pre-training strategies have been proposed to alleviate these issues, there lacks a systematic survey to summarize the properties, challenges, and solutions of DE-GANs. In this paper, we revisit and define DE-GANs from the perspective of distribution optimization. We conclude and analyze the challenges of DE-GANs. Meanwhile, we propose a taxonomy, which classifies the existing methods into three categories: Data Selection, GANs Optimization, and Knowledge Sharing. Last but not the least, we attempt to highlight the current problems and the future directions.
Abstract:Trajectory prediction aims to predict the movement trend of the agents like pedestrians, bikers, vehicles. It is helpful to analyze and understand human activities in crowded spaces and widely applied in many areas such as surveillance video analysis and autonomous driving systems. Thanks to the success of deep learning, trajectory prediction has made significant progress. The current methods are dedicated to studying the agents' future trajectories under the social interaction and the sceneries' physical constraints. Moreover, how to deal with these factors still catches researchers' attention. However, they ignore the \textbf{Semantic Shift Phenomenon} when modeling these interactions in various prediction sceneries. There exist several kinds of semantic deviations inner or between social and physical interactions, which we call the "\textbf{Gap}". In this paper, we propose a \textbf{C}ontextual \textbf{S}emantic \textbf{C}onsistency \textbf{Net}work (\textbf{CSCNet}) to predict agents' future activities with powerful and efficient context constraints. We utilize a well-designed context-aware transfer to obtain the intermediate representations from the scene images and trajectories. Then we eliminate the differences between social and physical interactions by aligning activity semantics and scene semantics to cross the Gap. Experiments demonstrate that CSCNet performs better than most of the current methods quantitatively and qualitatively.
Abstract:Learning to understand and predict future motions or behaviors for agents like humans and robots are critical to various autonomous platforms, such as behavior analysis, robot navigation, and self-driving cars. Intrinsic factors such as agents' diversified personalities and decision-making styles bring rich and diverse changes and multi-modal characteristics to their future plannings. Besides, the extrinsic interactive factors have also brought rich and varied changes to their trajectories. Previous methods mostly treat trajectories as time sequences, and reach great prediction performance. In this work, we try to focus on agents' trajectories in another view, i.e., the Fourier spectrums, to explore their future behavior rules in a novel hierarchical way. We propose the Transformer-based V model, which concatenates two continuous keypoints estimation and spectrum interpolation sub-networks, to model and predict agents' trajectories with spectrums in the keypoints and interactions levels respectively. Experimental results show that V outperforms most of current state-of-the-art methods on ETH-UCY and SDD trajectories dataset for about 15\% quantitative improvements, and performs better qualitative results.
Abstract:Generalized zero-shot learning (GZSL) has achieved significant progress, with many efforts dedicated to overcoming the problems of visual-semantic domain gap and seen-unseen bias. However, most existing methods directly use feature extraction models trained on ImageNet alone, ignoring the cross-dataset bias between ImageNet and GZSL benchmarks. Such a bias inevitably results in poor-quality visual features for GZSL tasks, which potentially limits the recognition performance on both seen and unseen classes. In this paper, we propose a simple yet effective GZSL method, termed feature refinement for generalized zero-shot learning (FREE), to tackle the above problem. FREE employs a feature refinement (FR) module that incorporates \textit{semantic$\rightarrow$visual} mapping into a unified generative model to refine the visual features of seen and unseen class samples. Furthermore, we propose a self-adaptive margin center loss (SAMC-loss) that cooperates with a semantic cycle-consistency loss to guide FR to learn class- and semantically-relevant representations, and concatenate the features in FR to extract the fully refined features. Extensive experiments on five benchmark datasets demonstrate the significant performance gain of FREE over its baseline and current state-of-the-art methods. Our codes are available at https://github.com/shiming-chen/FREE .