United States

Rehearsal, seeking to remind the model by storing old knowledge in lifelong learning, is one of the most effective ways to mitigate catastrophic forgetting, i.e., biased forgetting of previous knowledge when moving to new tasks. However, the old tasks of the most previous rehearsal-based methods suffer from the unpredictable domain shift when training the new task. This is because these methods always ignore two significant factors. First, the Data Imbalance between the new task and old tasks that makes the domain of old tasks prone to shift. Second, the Task Isolation among all tasks will make the domain shift toward unpredictable directions; To address the unpredictable domain shift, in this paper, we propose Multi-Domain Multi-Task (MDMT) rehearsal to train the old tasks and new task parallelly and equally to break the isolation among tasks. Specifically, a two-level angular margin loss is proposed to encourage the intra-class/task compactness and inter-class/task discrepancy, which keeps the model from domain chaos. In addition, to further address domain shift of the old tasks, we propose an optional episodic distillation loss on the memory to anchor the knowledge for each old task. Experiments on benchmark datasets validate the proposed approach can effectively mitigate the unpredictable domain shift.

AAAI 2021

Multi-Domain Multi-Task Rehearsal for Lifelong Learning

The purpose of the AAAI conference is to promote research in artificial intelligence (AI) and scientific exchange among AI researchers, practitioners, scientists, and engineers in affiliated disciplines. 

AAAI 2022

technical paper

Single-image deraining is rather challenging due to the unknown rain model. Existing methods often make specific assumptions of the rain model, which can hardly cover many diverse circumstances in the real world, compelling them to employ complex optimization or progressive refinement. This, however, significantly affects these methods' efficiency and effectiveness for many efficiency-critical applications. To fill this gap, in this paper, we regard the single-image deraining as a general image-enhancing problem and originally propose a model-free deraining method, i.e., EfficientDeRain, which is able to process a rainy image within 10 ms (i.e., around 6 ms on average), over 80 times faster than the state-of-the-art method (i.e., RCDNet), while achieving similar de-rain effects. We first propose novel pixel-wise dilation filtering. In particular, a rainy image is filtered with the pixel-wise kernels estimated from a kernel prediction network, by which suitable multi-scale kernels for each pixel can be efficiently predicted. Then, to eliminate the gap between synthetic and real data, we further propose an effective data augmentation method (i.e., RainMix) that helps to train the network for handling real rainy images. We perform a comprehensive evaluation on both synthetic and real-world rainy datasets to demonstrate the effectiveness and efficiency of our method. We release the model and code in https://github.com/tsingqguo/efficientderain.git.

EfficientDeRain: Learning Pixel-Wise Dilation Filtering for High-Efficiency Single-Image Deraining

Deformable convolution, originally proposed for the adaptation to geometric variations of objects, has recently shown compelling performance in aligning multiple frames and is increasingly adopted for video super-resolution. Despite its remarkable performance, its underlying mechanism for alignment remains unclear. In this study, we carefully investigate the relation between deformable alignment and the classic flow-based alignment. We show that deformable convolution can be decomposed into a combination of spatial warping and convolution. This decomposition reveals the commonality of deformable alignment and flow-based alignment in formulation, but with a key difference in their offset diversity. We further demonstrate through experiments that the increased diversity in deformable alignment yields better-aligned features, and hence significantly improves the quality of video super-resolution output. Based on our observations, we propose an offset-fidelity loss that guides the offset learning with optical flow. Experiments show that our loss successfully avoids the overflow of offsets and alleviates the instability problem of deformable alignment. Aside from the contributions to deformable alignment, our formulation inspires a more flexible approach to introduce offset diversity to flow-based alignment, improving its performance.

Understanding Deformable Alignment in Video Super-Resolution

In 1989, computer searches by Lam, Thiel, and Swiercz experimentally resolved Lam's problem from projective geometryâ€”the long-standing problem of determining if a projective plane of order ten exists.  Both the original search and an independent verification in 2011 discovered no such projective plane.  However, these searches were each performed using highly specialized custom-written code and did not produce nonexistence certificates.  In this paper, we resolve Lam's problem by translating the problem into Boolean logic and use satisfiability (SAT) solvers to produce nonexistence certificates that can be verified by a third party.  Our work uncovered consistency issues in both previous searchesâ€”highlighting the difficulty of relying on special-purpose search code for nonexistence results.

A SAT-Based Resolution of Lam's Problem

Deep neural networks (DNNs) have been widely applied to active learning. Despite of its effectiveness, the generalization ability of the discriminative classifier (the softmax classifier) is questionable when there is a significant distribution bias between the labeled set and the unlabeled set. In this paper, we attempt to replace the softmax classifier in deep neural network with a nearest neighbor classifier, considering its progressive generalization ability within the unknown sub-space. Our proposed active learning approach, termed nearest Neighbor Classifier Embedded network (NCE-Net), targets at reducing the risk of over-estimating unlabeled samples while improving the opportunity to query informative samples. NCE-Net is conceptually simple but surprisingly powerful, as justified from the perspective of the subset information, which defines a metric to quantify model generalization ability in active learning. Experimental results show that, with simple selection based on rejection or confusion confidence, NCE-Net improves state-of-the-arts on image classification and object detection tasks with significant margins.

Nearest Neighbor Classifier Embedded Network for Active Learning

Learning single-image 3D reconstruction with only 2D images supervision is a promising research topic. The main challenge in image-supervised 3D reconstruction is the shape-pose ambiguity, which means a 2D supervision can be explained by an erroneous 3D shape from an erroneous pose. It will introduce high uncertainty and mislead the learning process. Existed works rely on multi-view images or pose-aware annotations to resolve the ambiguity. In this paper, we propose to resolve the ambiguity without extra pose-aware labels or annotations. Our training data is single-view images from the same object category. To overcome the shape-pose ambiguity, we introduce a pose-independent GAN to learn the category-specific shape manifold from the image collections. With the learned shape space, we resolve the shape-pose ambiguity in original images by training a pseudo pose regressor. Finally, we learn a reconstruction network with both the common re-projection loss and a pose-independent discrimination loss, making the results plausible from all views. Through experiments on synthetic and real image datasets, we demonstrate that our method can perform comparably to existing methods while not requiring any extra pose-aware annotations, making it more applicable and adaptable.

Shape-Pose Ambiguity in Learning 3D Reconstruction from Images

Long after Turing's seminal Reaction-Diffusion (RD) model, the elegance of his fundamental equations alleviated much of the skepticism surrounding pattern formation. Though Turing model is a simplification and an idealization, it is one of the best-known theoretical models to explain patterns as a reminiscent of those observed in nature. Over the years, concerted efforts have been made to align theoretical models to explain patterns in real systems. The apparent difficulty in identifying the specific dynamics of the RD system makes the problem particularly challenging. Interestingly, we observe Turing-like patterns in a system of neurons with adversarial interaction. In this study, we establish the involvement of Turing instability to create such patterns. By theoretical and empirical studies, we present a \textit{pseudo-reaction-diffusion} model to explain the mechanism that may underlie these phenomena. While supervised learning attains homogeneous equilibrium, this paper suggests that the introduction of an adversary helps break this homogeneity to create non-homogeneous patterns at equilibrium. Further, we prove that randomly initialized gradient descent with over-parameterization can converge exponentially fast to an $\epsilon$-stationary point even under adversarial interaction. In addition, different from sole supervision, we show that the solutions obtained under adversarial interaction are not limited to a tiny subspace around initialization.

Why Adversarial Interaction Creates Non-Homogeneous Patterns: A Pseudo-Reaction-Diffusion Model for Turing Instability

This paper proposes a method to disentangle and quantify interactions among words that are encoded inside a DNN for natural language processing. We construct a tree to encode salient interactions extracted by the DNN. Six metrics are proposed to analyze properties of interactions between constituents in a sentence. The interaction is defined based on Shapley values of words, which are considered as an unbiased estimation of word contributions to the network prediction. Our method is used to quantify word interactions encoded inside the BERT, ELMo, LSTM, CNN, and Transformer networks. Experimental results have provided a new perspective to understand these DNNs, and have demonstrated the effectiveness of our method.

Building Interpretable Interaction Trees for Deep NLP Models

In classical planning as search, duplicate state pruning is a standard method to avoid unnecessarily handling the same state multiple times. In decoupled search, similar to symbolic search approaches, search nodes, called decoupled states, do not correspond to individual states, but to sets of states. Therefore, duplicate state pruning is less effective in decoupled search, and dominance pruning is employed, taking into account the state sets. We observe that the time required for dominance checking dominates the overall runtime, and propose two ways to tackle this issue. Our main contribution is a stronger variant of dominance checking for optimal planning, where efficiency and pruning power are most crucial. The new variant greatly improves the latter, without incurring a computational overhead. Moreover, we develop three methods that make the dominance check more efficient: exact duplicate checking, which, albeit resulting in weaker pruning, can pay off due to the use of hashing; avoiding the dominance check in non-optimal planning if leaf state spaces are invertible; and exploiting the transitivity of the dominance relation to only check against the relevant subset of visited decoupled states. We show empirically that all our improvements are indeed beneficial in many standard benchmarks.

Revisiting Dominance Pruning in Decoupled Search

Neural abstractive summarization has been studied in many pieces of literature and achieves great success with the aid of large corpora. However, when encountering novel tasks, one may not always benefit from transfer learning due to the domain shifting problem, and overfitting could happen without adequate labeled examples. Furthermore, the annotations of abstractive summarization are costly, which often demand domain knowledge to ensure the ground-truth quality. Thus, there are growing appeals for Low-Resource Abstractive Summarization, which aims to leverage past experience to improve the performance with limited labeled examples of target corpus. In this paper, we propose to utilize two knowledge-rich sources to tackle this problem, which are large pre-trained models and diverse existing corpora. The former can provide the primary ability to tackle summarization tasks; the latter can help discover common syntactic or semantic information to improve the generalization ability. We conduct extensive experiments on various summarization corpora with different writing styles and forms. The results demonstrate that our approach achieves the state-of-the-art on 6 corpora in low-resource scenarios, with only 0.7% of trainable parameters compared to previous work.

Meta-Transfer Learning for Low-Resource Abstractive Summarization

A video-grounded dialogue system referred to as the Structured Co-reference Graph Attention (SCGA) is presented for decoding the answer sequence to a question regarding a given video while keeping track of the dialogue context. Although recent efforts have made great strides in improving the quality of the response, performance is still far from satisfactory. The two main challenging issues are as follows: (1) how to deduce co-reference among multiple modalities and (2) how to reason on the rich underlying semantic structure of video with complex spatial and temporal dynamics. To this end, SCGA is based on (1) Structured Co-reference Resolver that performs dereferencing via building a structured graph over multiple modalities, (2) Spatio-temporal Video Reasoner that captures local-to-global dynamics of video via gradually neighboring graph attention. SCGA makes use of pointer network to dynamically replicate parts of the question for decoding the answer sequence. The validity of the proposed SCGA is demonstrated on AVSD@DSTC7 and AVSD@DSTC8 datasets, a challenging video-grounded dialogue benchmarks, and TVQA dataset, a large-scale videoQA benchmark. Our empirical results show that SCGA outperforms other state-of-the-art dialogue systems on both benchmarks, while extensive ablation study and qualitative analysis reveal performance gain and improved interpretability.

Downloads

Next from AAAI 2021

EfficientDeRain: Learning Pixel-Wise Dilation Filtering for High-Efficiency Single-Image Deraining

Similar lecture

Lifelong Person Re-Identification by Pseudo Task Knowledge Preservation

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from AAAI 2021

EfficientDeRain: Learning Pixel-Wise Dilation Filtering for High-Efficiency Single-Image Deraining

Similar lecture

Lifelong Person Re-Identification by Pseudo Task Knowledge Preservation

Downloads