The contemporary visual captioning models frequently hallucinate objects that are not actually in a scene, due to the visual misclassification or over-reliance on priors that resulting in the semantic inconsistency between the visual information and the target lexical words. The most common way is to encourage the captioning model to dynamically link generated object words or phrases to appropriate regions of the image, i.e., the grounded image captioning (GIC). However, GIC utilizes an auxiliary task (grounding objects) that has not solved the key issue of object hallucination, i.e., the semantic inconsistency. In this paper, we take a novel perspective on the issue above - exploiting the semantic coherency between the visual and language modalities. Specifically, we propose the Consensus Rraph Representation Learning framework (CGRL) for GIC that incorporates a consensus representation into the grounded captioning pipeline. The consensus is learned by aligning the visual graph (e.g., scene graph) to the language graph that consider both the nodes and edges in a graph. With the aligned consensus, the captioning model can capture both the correct linguistic characteristics and visual relevance, and then grounding appropriate image regions further. We validate the effectiveness of our model, with a significant decline in object hallucination (-9% CHAIRi) on the Flickr30k Entities dataset. Besides, our CGRL also evaluated by several automatic metrics and human evaluation, the results indicate that the proposed approach can simultaneously improve the performance of image captioning (+2.9 Cider) and grounding (+2.3 F1LOC).
Grounded video description (GVD) encourages captioning models to attend to appropriate video regions (e.g., objects) dynamically and generate a description. Such a setting can help explain the decisions of captioning models and prevents the model from hallucinating object words in its description. However, such design mainly focuses on object word generation and thus may ignore fine-grained information and suffer from missing visual concepts. Moreover, relational words (e.g., "jump left or right") are usual spatio-temporal inference results, i.e., these words cannot be grounded on certain spatial regions. To tackle the above limitations, we design a novel relational graph learning framework for GVD, in which a language-refined scene graph representation is designed to explore fine-grained visual concepts. Furthermore, the refined graph can be regarded as relational inductive knowledge to assist captioning models in selecting the relevant information it needs to generate correct words. We validate the effectiveness of our model through automatic metrics and human evaluation, and the results indicate that our approach can generate more fine-grained and accurate description, and it solves the problem of object hallucination to some extent.
Existing Class Incremental Learning (CIL) methods are based on a supervised classification framework sensitive to data labels. When updating them based on the new class data, they suffer from catastrophic forgetting: the model cannot discern old class data clearly from the new. In this paper, we explore the performance of Self-Supervised representation learning in Class Incremental Learning (SSCIL) for the first time, which discards data labels and the model's classifiers. To comprehensively discuss the difference in performance between supervised and self-supervised methods in CIL, we set up three different class incremental schemes: Random Class Scheme, Semantic Class Scheme, and Cluster Scheme, to simulate various class incremental learning scenarios. Besides, we propose Linear Evaluation Protocol (LEP) and Generalization Evaluation Protocol (GEP) to metric the model's representation classification ability and generalization in CIL. Our experiments (on ImageNet-100 and ImageNet) show that SSCIL has better anti-forgetting ability and robustness than supervised strategies in CIL. To understand what alleviates the catastrophic forgetting in SSCIL, we study the major components of SSCIL and conclude that (1) the composition of different data augmentation improves the quality of the model's representation and the \textit{Grayscale} operation reduces the system noise of data augmentation in SSCIL. (2) the projector, like a buffer, reduces unnecessary parameter updates of the model in SSCIL and increases the robustness of the model. Although the performance of SSCIL is significantly higher than supervised methods in CIL, there is still an apparent gap with joint learning. Our exploration gives a baseline of self-supervised class incremental learning on large-scale datasets and contributes some forward strategies for mitigating the catastrophic forgetting in CIL.
This paper investigates the feasibility of learning good representation space with unlabeled client data in the federated scenario. Existing works trivially inherit the supervised federated learning methods, which does not apply to the model heterogeneity and has the potential risk of privacy exposure. To tackle the problems above, we first identify that self-supervised contrastive local training is more robust against the non-i.i.d.-ness than the traditional supervised learning paradigm. Then we propose a novel federated self-supervised contrastive learning framework FLESD that supports architecture-agnostic local training and communication-efficient global aggregation. At each round of communication, the server first gathers a fraction of the clients' inferred similarity matrices on a public dataset. Then FLESD ensembles the similarity matrices and trains the global model via similarity distillation. We verify the effectiveness of our proposed framework by a series of empirical experiments and show that FLESD has three main advantages over the existing methods: it handles the model heterogeneity, is less prone to privacy leak, and is more communication-efficient. We will release the code of this paper in the future.
Given an untrimmed video and a natural language query, Natural Language Video Localization (NLVL) aims to identify the video moment described by the query. To address this task, existing methods can be roughly grouped into two groups: 1) propose-and-rank models first define a set of hand-designed moment candidates and then find out the best-matching one. 2) proposal-free models directly predict two temporal boundaries of the referential moment from frames. Currently, almost all the propose-and-rank methods have inferior performance than proposal-free counterparts. In this paper, we argue that propose-and-rank approach is underestimated due to the predefined manners: 1) Hand-designed rules are hard to guarantee the complete coverage of targeted segments. 2) Densely sampled candidate moments cause redundant computation and degrade the performance of ranking process. To this end, we propose a novel model termed LPNet (Learnable Proposal Network for NLVL) with a fixed set of learnable moment proposals. The position and length of these proposals are dynamically adjusted during training process. Moreover, a boundary-aware loss has been proposed to leverage frame-level information and further improve the performance. Extensive ablations on two challenging NLVL benchmarks have demonstrated the effectiveness of LPNet over existing state-of-the-art methods.
Video-and-Language Inference is a recently proposed task for joint video-and-language understanding. This new task requires a model to draw inference on whether a natural language statement entails or contradicts a given video clip. In this paper, we study how to address three critical challenges for this task: judging the global correctness of the statement involved multiple semantic meanings, joint reasoning over video and subtitles, and modeling long-range relationships and complex social interactions. First, we propose an adaptive hierarchical graph network that achieves in-depth understanding of the video over complex interactions. Specifically, it performs joint reasoning over video and subtitles in three hierarchies, where the graph structure is adaptively adjusted according to the semantic structures of the statement. Secondly, we introduce semantic coherence learning to explicitly encourage the semantic coherence of the adaptive hierarchical graph network from three hierarchies. The semantic coherence learning can further improve the alignment between vision and linguistics, and the coherence across a sequence of video segments. Experimental results show that our method significantly outperforms the baseline by a large margin.
It is a consensus that small models perform quite poorly under the paradigm of self-supervised contrastive learning. Existing methods usually adopt a large off-the-shelf model to transfer knowledge to the small one via knowledge distillation. Despite their effectiveness, distillation-based methods may not be suitable for some resource-restricted scenarios due to the huge computational expenses of deploying a large model. In this paper, we study the issue of training self-supervised small models without distillation signals. We first evaluate the representation spaces of the small models and make two non-negligible observations: (i) small models can complete the pretext task without overfitting despite its limited capacity; (ii) small models universally suffer the problem of over-clustering. Then we verify multiple assumptions that are considered to alleviate the over-clustering phenomenon. Finally, we combine the validated techniques and improve the baseline of five small architectures with considerable margins, which indicates that training small self-supervised contrastive models is feasible even without distillation signals.
The challenge of the Class Incremental Learning~(CIL) lies in difficulty for a learner to discern the old classes' data from the new as no previous classes' data is preserved. In this paper, we reveal three causes for catastrophic forgetting at the representational level, namely, representation forgetting, representation overlapping, and classifier deviation. Based on the observation above, we propose a new CIL framework, Contrastive Class Concentration for CIL (C4IL) to alleviate the phenomenon of representation overlapping that works in both memory-based and memory-free methods. Our framework leverages the class concentration effect of contrastive representation learning, therefore yielding a representation distribution with better intra-class compatibility and inter-class separability. Quantitative experiments showcase the effectiveness of our framework: it outperforms the baseline methods by 5% in terms of the average and top-1 accuracy in 10-phase and 20-phase CIL. Qualitative results also demonstrate that our method generates a more compact representation distribution that alleviates the overlapping problem.