Large pre-trained models have had a significant impact on computer vision by enabling multi-modal learning, where the CLIP model has achieved impressive results in image classification, object detection, and semantic segmentation. However, the model's performance on 3D point cloud processing tasks is limited due to the domain gap between depth maps from 3D projection and training images of CLIP. This paper proposes DiffCLIP, a new pre-training framework that incorporates stable diffusion with ControlNet to minimize the domain gap in the visual branch. Additionally, a style-prompt generation module is introduced for few-shot tasks in the textual branch. Extensive experiments on the ModelNet10, ModelNet40, and ScanObjectNN datasets show that DiffCLIP has strong abilities for 3D understanding. By using stable diffusion and style-prompt generation, DiffCLIP achieves an accuracy of 43.2\% for zero-shot classification on OBJ\_BG of ScanObjectNN, which is state-of-the-art performance, and an accuracy of 80.6\% for zero-shot classification on ModelNet10, which is comparable to state-of-the-art performance.
Single domain generalization aims to learn a model from a single training domain (source domain) and apply it to multiple unseen test domains (target domains). Existing methods focus on expanding the distribution of the training domain to cover the target domains, but without estimating the domain shift between the source and target domains. In this paper, we propose a new learning paradigm, namely simulate-analyze-reduce, which first simulates the domain shift by building an auxiliary domain as the target domain, then learns to analyze the causes of domain shift, and finally learns to reduce the domain shift for model adaptation. Under this paradigm, we propose a meta-causal learning method to learn meta-knowledge, that is, how to infer the causes of domain shift between the auxiliary and source domains during training. We use the meta-knowledge to analyze the shift between the target and source domains during testing. Specifically, we perform multiple transformations on source data to generate the auxiliary domain, perform counterfactual inference to learn to discover the causal factors of the shift between the auxiliary and source domains, and incorporate the inferred causality into factor-aware domain alignments. Extensive experiments on several benchmarks of image classification show the effectiveness of our method.
In real teaching scenarios, an excellent teacher always teaches what he (or she) is good at but the student is not. This method gives the student the best assistance in making up for his (or her) weaknesses and becoming a good one overall. Enlightened by this, we introduce the approach to the knowledge distillation framework and propose a data-based distillation method named ``Teaching what you Should Teach (TST)''. To be specific, TST contains a neural network-based data augmentation module with the priori bias, which can assist in finding what the teacher is good at while the student are not by learning magnitudes and probabilities to generate suitable samples. By training the data augmentation module and the generalized distillation paradigm in turn, a student model that has excellent generalization ability can be created. To verify the effectiveness of TST, we conducted extensive comparative experiments on object recognition (CIFAR-100 and ImageNet-1k), detection (MS-COCO), and segmentation (Cityscapes) tasks. As experimentally demonstrated, TST achieves state-of-the-art performance on almost all teacher-student pairs. Furthermore, we conduct intriguing studies of TST, including how to solve the performance degradation caused by the stronger teacher and what magnitudes and probabilities are needed for the distillation framework.
Few-shot action recognition in videos is challenging for its lack of supervision and difficulty in generalizing to unseen actions. To address this task, we propose a simple yet effective method, called knowledge prompting, which leverages commonsense knowledge of actions from external resources to prompt a powerful pre-trained vision-language model for few-shot classification. We first collect large-scale language descriptions of actions, defined as text proposals, to build an action knowledge base. The collection of text proposals is done by filling in handcraft sentence templates with external action-related corpus or by extracting action-related phrases from captions of Web instruction videos.Then we feed these text proposals into the pre-trained vision-language model along with video frames to generate matching scores of the proposals to each frame, and the scores can be treated as action semantics with strong generalization. Finally, we design a lightweight temporal modeling network to capture the temporal evolution of action semantics for classification.Extensive experiments on six benchmark datasets demonstrate that our method generally achieves the state-of-the-art performance while reducing the training overhead to 0.001 of existing methods.
Domain generalization aims to learn a model that can generalize well on the unseen test dataset, i.e., out-of-distribution data, which has different distribution from the training dataset. To address domain generalization in computer vision, we introduce the loss landscape theory into this field. Specifically, we bootstrap the generalization ability of the deep learning model from the loss landscape perspective in four aspects, including backbone, regularization, training paradigm, and learning rate. We verify the proposed theory on the NICO++, PACS, and VLCS datasets by doing extensive ablation studies as well as visualizations. In addition, we apply this theory in the ECCV 2022 NICO Challenge1 and achieve the 3rd place without using any domain invariant methods.
Language-driven action localization in videos is a challenging task that involves not only visual-linguistic matching but also action boundary prediction. Recent progress has been achieved through aligning language query to video segments, but estimating precise boundaries is still under-explored. In this paper, we propose entity-aware and motion-aware Transformers that progressively localizes actions in videos by first coarsely locating clips with entity queries and then finely predicting exact boundaries in a shrunken temporal region with motion queries. The entity-aware Transformer incorporates the textual entities into visual representation learning via cross-modal and cross-frame attentions to facilitate attending action-related video clips. The motion-aware Transformer captures fine-grained motion changes at multiple temporal scales via integrating long short-term memory into the self-attention module to further improve the precision of action boundary prediction. Extensive experiments on the Charades-STA and TACoS datasets demonstrate that our method achieves better performance than existing methods.
Entity-aware image captioning aims to describe named entities and events related to the image by utilizing the background knowledge in the associated article. This task remains challenging as it is difficult to learn the association between named entities and visual cues due to the long-tail distribution of named entities. Furthermore, the complexity of the article brings difficulty in extracting fine-grained relationships between entities to generate informative event descriptions about the image. To tackle these challenges, we propose a novel approach that constructs a multi-modal knowledge graph to associate the visual objects with named entities and capture the relationship between entities simultaneously with the help of external knowledge collected from the web. Specifically, we build a text sub-graph by extracting named entities and their relationships from the article, and build an image sub-graph by detecting the objects in the image. To connect these two sub-graphs, we propose a cross-modal entity matching module trained using a knowledge base that contains Wikipedia entries and the corresponding images. Finally, the multi-modal knowledge graph is integrated into the captioning model via a graph attention mechanism. Extensive experiments on both GoodNews and NYTimes800k datasets demonstrate the effectiveness of our method.
How to model fine-grained spatial-temporal dynamics in videos has been a challenging problem for action recognition. It requires learning deep and rich features with superior distinctiveness for the subtle and abstract motions. Most existing methods generate features of a layer in a pure feedforward manner, where the information moves in one direction from inputs to outputs. And they rely on stacking more layers to obtain more powerful features, bringing extra non-negligible overheads. In this paper, we propose an Adaptive Recursive Circle (ARC) framework, a fine-grained decorator for pure feedforward layers. It inherits the operators and parameters of the original layer but is slightly different in the use of those operators and parameters. Specifically, the input of the layer is treated as an evolving state, and its update is alternated with the feature generation. At each recursive step, the input state is enriched by the previously generated features and the feature generation is made with the newly updated input state. We hope the ARC framework can facilitate fine-grained action recognition by introducing deeply refined features and multi-scale receptive fields at a low cost. Significant improvements over feedforward baselines are observed on several benchmarks. For example, an ARC-equipped TSM-ResNet18 outperforms TSM-ResNet50 with 48% fewer FLOPs and 52% model parameters on Something-Something V1 and Diving48.
Exploiting relationships among objects has achieved remarkable progress in interpreting images or videos by natural language. Most existing methods resort to first detecting objects and their relationships, and then generating textual descriptions, which heavily depends on pre-trained detectors and leads to performance drop when facing problems of heavy occlusion, tiny-size objects and long-tail in object detection. In addition, the separate procedure of detecting and captioning results in semantic inconsistency between the pre-defined object/relation categories and the target lexical words. We exploit prior human commonsense knowledge for reasoning relationships between objects without any pre-trained detectors and reaching semantic coherency within one image or video in captioning. The prior knowledge (e.g., in the form of knowledge graph) provides commonsense semantic correlation and constraint between objects that are not explicit in the image and video, serving as useful guidance to build semantic graph for sentence generation. Particularly, we present a joint reasoning method that incorporates 1) commonsense reasoning for embedding image or video regions into semantic space to build semantic graph and 2) relational reasoning for encoding semantic graph to generate sentences. Extensive experiments on the MS-COCO image captioning benchmark and the MSVD video captioning benchmark validate the superiority of our method on leveraging prior commonsense knowledge to enhance relational reasoning for visual captioning.
Partial domain adaptation aims to transfer knowledge from a label-rich source domain to a label-scarce target domain which relaxes the fully shared label space assumption across different domains. In this more general and practical scenario, a major challenge is how to select source instances in the shared classes across different domains for positive transfer. To address this issue, we propose a Domain Adversarial Reinforcement Learning (DARL) framework to automatically select source instances in the shared classes for circumventing negative transfer as well as to simultaneously learn transferable features between domains by reducing the domain shift. Specifically, in this framework, we employ deep Q-learning to learn policies for an agent to make selection decisions by approximating the action-value function. Moreover, domain adversarial learning is introduced to learn domain-invariant features for the selected source instances by the agent and the target instances, and also to determine rewards for the agent based on how relevant the selected source instances are to the target domain. Experiments on several benchmark datasets demonstrate that the superior performance of our DARL method over existing state of the arts for partial domain adaptation.