Many studies focus on improving pretraining or developing new backbones in text-video retrieval. However, existing methods may suffer from the learning and inference bias issue, as recent research suggests in other text-video-related tasks. For instance, spatial appearance features on action recognition or temporal object co-occurrences on video scene graph generation could induce spurious correlations. In this work, we present a unique and systematic study of a temporal bias due to frame length discrepancy between training and test sets of trimmed video clips, which is the first such attempt for a text-video retrieval task, to the best of our knowledge. We first hypothesise and verify the bias on how it would affect the model illustrated with a baseline study. Then, we propose a causal debiasing approach and perform extensive experiments and ablation studies on the Epic-Kitchens-100, YouCook2, and MSR-VTT datasets. Our model overpasses the baseline and SOTA on nDCG, a semantic-relevancy-focused evaluation metric which proves the bias is mitigated, as well as on the other conventional metrics.
Text-video retrieval contains various challenges, including biases coming from diverse sources. We highlight some of them supported by illustrations to open a discussion. Besides, we address one of the biases, frame length bias, with a simple method which brings a very incremental but promising increase. We conclude with future directions.
Bio-inspired learning has been gaining popularity recently given that Backpropagation (BP) is not considered biologically plausible. Many algorithms have been proposed in the literature which are all more biologically plausible than BP. However, apart from overcoming the biological implausibility of BP, a strong motivation for using Bio-inspired algorithms remains lacking. In this study, we undertake a holistic comparison of BP vs. multiple Bio-inspired algorithms to answer the question of whether Bio-learning offers additional benefits over BP, rather than just biological plausibility. We test Bio-algorithms under different design choices such as access to only partial training data, resource constraints in terms of the number of training epochs, sparsification of the neural network parameters and addition of noise to input samples. Through these experiments, we notably find two key advantages of Bio-algorithms over BP. Firstly, Bio-algorithms perform much better than BP when the entire training dataset is not supplied. Four of the five Bio-algorithms tested outperform BP by upto 5% accuracy when only 20% of the training dataset is available. Secondly, even when the full dataset is available, Bio-algorithms learn much quicker and converge to a stable accuracy in far lesser training epochs than BP. Hebbian learning, specifically, is able to learn in just 5 epochs compared to around 100 epochs required by BP. These insights present practical reasons for utilising Bio-learning rather than just its biological plausibility and also point towards interesting new directions for future work on Bio-learning.
Tremendous progress has been made in continual learning to maintain good performance on old tasks when learning new tasks by tackling the catastrophic forgetting problem of neural networks. This paper advances continual learning by further considering its out-of-distribution robustness, in response to the vulnerability of continually trained models to distribution shifts (e.g., due to data corruptions and domain shifts) in inference. To this end, we propose shape-texture debiased continual learning. The key idea is to learn generalizable and robust representations for each task with shape-texture debiased training. In order to transform standard continual learning to shape-texture debiased continual learning, we propose shape-texture debiased data generation and online shape-texture debiased self-distillation. Experiments on six datasets demonstrate the benefits of our approach in improving generalization and robustness, as well as reducing forgetting. Our analysis on the flatness of the loss landscape explains the advantages. Moreover, our approach can be easily combined with new advanced architectures such as vision transformer, and applied to more challenging scenarios such as exemplar-free continual learning.
A tiny object in the sky cannot be an elephant. Context reasoning is critical in visual recognition, where current inputs need to be interpreted in the light of previous experience and knowledge. To date, research into contextual reasoning in visual recognition has largely proceeded with supervised learning methods. The question of whether contextual knowledge can be captured with self-supervised learning regimes remains under-explored. Here, we established a methodology for context-aware self-supervised learning. We proposed a novel Self-supervised Learning Method for Context Reasoning (SeCo), where the only inputs to SeCo are unlabeled images with multiple objects present in natural scenes. Similar to the distinction between fovea and periphery in human vision, SeCo processes self-proposed target object regions and their contexts separately, and then employs a learnable external memory for retrieving and updating context-relevant target information. To evaluate the contextual associations learned by the computational models, we introduced two evaluation protocols, lift-the-flap and object priming, addressing the problems of "what" and "where" in context reasoning. In both tasks, SeCo outperformed all state-of-the-art (SOTA) self-supervised learning methods by a significant margin. Our network analysis revealed that the external memory in SeCo learns to store prior contextual knowledge, facilitating target identity inference in lift-the-flap task. Moreover, we conducted psychophysics experiments and introduced a Human benchmark in Object Priming dataset (HOP). Our quantitative and qualitative results demonstrate that SeCo approximates human-level performance and exhibits human-like behavior. All our source code and data are publicly available here.
Scene text images have different shapes and are subjected to various distortions, e.g. perspective distortions. To handle these challenges, the state-of-the-art methods rely on a rectification network, which is connected to the text recognition network. They form a linear pipeline which uses text rectification on all input images, even for images that can be recognized without it. Undoubtedly, the rectification network improves the overall text recognition performance. However, in some cases, the rectification network generates unnecessary distortions on images, resulting in incorrect predictions in images that would have otherwise been correct without it. In order to alleviate the unnecessary distortions, the portmanteauing of features is proposed. The portmanteau feature, inspired by the portmanteau word, is a feature containing information from both the original text image and the rectified image. To generate the portmanteau feature, a non-linear input pipeline with a block matrix initialization is presented. In this work, the transformer is chosen as the recognition network due to its utilization of attention and inherent parallelism, which can effectively handle the portmanteau feature. The proposed method is examined on 6 benchmarks and compared with 13 state-of-the-art methods. The experimental results show that the proposed method outperforms the state-of-the-art methods on various of the benchmarks.
Fine-grained action recognition is a challenging task in computer vision. As fine-grained datasets have small inter-class variations in spatial and temporal space, fine-grained action recognition model requires good temporal reasoning and discrimination of attribute action semantics. Leveraging on CNN's ability in capturing high level spatial-temporal feature representations and Transformer's modeling efficiency in capturing latent semantics and global dependencies, we investigate two frameworks that combine CNN vision backbone and Transformer Encoder to enhance fine-grained action recognition: 1) a vision-based encoder to learn latent temporal semantics, and 2) a multi-modal video-text cross encoder to exploit additional text input and learn cross association between visual and text semantics. Our experimental results show that both our Transformer encoder frameworks effectively learn latent temporal semantics and cross-modality association, with improved recognition performance over CNN vision model. We achieve new state-of-the-art performance on the FineGym benchmark dataset for both proposed architectures.
In this report, we present our approach for EPIC-KITCHENS-100 Multi-Instance Retrieval Challenge 2022. We first parse sentences into semantic roles corresponding to verbs and nouns; then utilize self-attentions to exploit semantic role contextualized video features along with textual features via triplet losses in multiple embedding spaces. Our method overpasses the strong baseline in normalized Discounted Cumulative Gain (nDCG), which is more valuable for semantic similarity. Our submission is ranked 3rd for nDCG and ranked 4th for mAP.