No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
Multi-Prototype Grouping for Continual Learning in Visual Question Answering
ResearchGate has not been able to resolve any citations for this publication.
Cross-modal alignment aims to build a bridge connecting vision and language. It is an important multi-modal task that efficiently learns the semantic similarities between images and texts. Traditional fine-grained alignment methods heavily rely on pre-trained object detectors to extract region features for subsequent region-word alignment thereby incurring substantial computational costs for region detection and error propagation issues for two-stage training. In this paper, we focus on the mainstream vision transformer incorporating patch features for patch-word alignment while addressing the resultant issue of visual patch redundancy and patch ambiguity for semantic alignment. We propose a novel Linguistic-Aware Patch Slimming (LAPS) framework for fine-grained alignment which explicitly identifies redundant visual patches with language supervision and rectifies their semantic and spatial information to facilitate more effective and consistent patch-word alignment. Extensive experiments on various evaluation benchmarks and model backbones show LAPS outperforms the state-of-the-art fine-grained alignment methods by 5%-15% rSum. Our code is available at https://github.com/CrossmodalGroup/LAPS
Image-text matching, a bridge connecting image and language, is an important task, which generally learns a holistic cross-modal embedding to achieve a high-quality semantic alignment between the two modalities. However, previous studies only focus on capturing fragment-level relation within a sample from a particular modality, e.g., salient regions in an image or text words in a sentence, where they usually pay less attention to capturing instance-level interactions among samples and modalities, e.g., multiple images and texts. In this paper, we argue that sample relations could help learn subtle differences for hard negative instances, and thus transfer shared knowledge for infrequent samples should be promising in obtaining better holistic embeddings. Therefore, we propose a novel hierarchical relation modeling framework (HREM), which explicitly capture both fragment- and instance-level relations to learn discriminative and robust cross-modal embeddings. Extensive experiments on Flickr30K and MS-COCO show our proposed method outperforms the state-of-the-art ones by 4%-10% in terms of rSum. Our code is available at https://github.com/CrossmodalGroup/HREM
Visual Question Answering (VQA) requires a fine-grained and simultaneous understanding of both the visual content of images and the textual content of questions. Therefore, designing an effective 'co-attention' model to associate key words in questions with key objects in images is central to VQA performance. So far, most successful attempts at co-attention learning have been achieved by using shallow models, and deep co-attention models show little improvement over their shallow counterparts. In this paper, we propose a deep Modular Co-Attention Network (MCAN) that consists of Modular Co-Attention (MCA) layers cascaded in depth. Each MCA layer models the self-attention of questions and images, as well as the question-guided-attention of images jointly using a modular composition of two basic attention units. We quantitatively and qualitatively evaluate MCAN on the benchmark VQA-v2 dataset and conduct extensive ablation studies to explore the reasons behind MCAN's effectiveness. Experimental results demonstrate that MCAN significantly outperforms the previous state-of-the-art. Our best single model delivers 70.63% overall accuracy on the test-dev set.
The purpose of this study is to determine whether current video datasets have sufficient data for training very deep convolutional neural networks (CNNs) with spatio-temporal three-dimensional (3D) kernels. Recently, the performance levels of 3D CNNs in the field of action recognition have improved significantly. However, to date, conventional research has only explored relatively shallow 3D architectures. We examine the architectures of various 3D CNNs from relatively shallow to very deep ones on current video datasets. Based on the results of those experiments, the following conclusions could be obtained: (i) ResNet-18 training resulted in significant overfitting for UCF-101, HMDB-51, and ActivityNet but not for Kinetics. (ii) The Kinetics dataset has sufficient data for training of deep 3D CNNs, and enables training of up to 152 ResNets layers, interestingly similar to 2D ResNets on ImageNet. ResNeXt-101 achieved 78.4% average accuracy on the Kinetics test set. (iii) Kinetics pretrained simple 3D architectures outperforms complex 2D architectures, and the pretrained ResNeXt-101 achieved 94.5% and 70.2% on UCF-101 and HMDB-51, respectively. The use of 2D CNNs trained on ImageNet has produced significant progress in various tasks in image. We believe that using deep 3D CNNs together with Kinetics will retrace the successful history of 2D CNNs and ImageNet, and stimulate advances in computer vision for videos. The codes and pretrained models used in this study are publicly available. https://github.com/kenshohara/3D-ResNets-PyTorch
Natural language questions are inherently compositional, and many are most easily answered by reasoning about their decomposition into modular sub-problems. For example, to answer "is there an equal number of balls and boxes?" we can look for balls, look for boxes, count them, and compare the results. The recently proposed Neural Module Network (NMN) architecture implements this approach to question answering by parsing questions into linguistic substructures and assembling question-specific deep networks from smaller modules that each solve one subtask. However, existing NMN implementations rely on brittle off-the-shelf parsers, and are restricted to the module configurations proposed by these parsers rather than learning them from data. In this paper, we propose End-to-End Module Networks (N2NMNs), which learn to reason by directly predicting instance-specific network layouts without the aid of a parser. Our model learns to generate network structures (by imitating expert demonstrations) while simultaneously learning network parameters (using the downstream task loss). Experimental results on the new CLEVR dataset targeted at compositional question answering show that N2NMNs achieve an error reduction of nearly 50% relative to state-of-the-art attentional approaches, while discovering interpretable network architectures specialized for each question.
Significance
Deep neural networks are currently the most successful machine-learning technique for solving a variety of tasks, including language translation, image classification, and image generation. One weakness of such models is that, unlike humans, they are unable to learn multiple tasks sequentially. In this work we propose a practical solution to train such models sequentially by protecting the weights important for previous tasks. This approach, inspired by synaptic consolidation in neuroscience, enables state of the art results on multiple reinforcement learning problems experienced sequentially.
Problems at the intersection of vision and language are of significant importance both as challenging research questions and for the rich set of applications they enable. However, inherent structure in our world and bias in our language tend to be a simpler signal for learning than visual modalities, resulting in models that ignore visual information, leading to an inflated sense of their capability. We propose to counter these language priors for the task of Visual Question Answering (VQA) and make vision (the V in VQA) matter! Specifically, we balance the popular VQA dataset (Antol et al., ICCV 2015) by collecting complementary images such that every question in our balanced dataset is associated with not just a single image, but rather a pair of similar images that result in two different answers to the question. Our dataset is by construction more balanced than the original VQA dataset and has approximately twice the number of image-question pairs. Our complete balanced dataset will be publicly released as part of the 2nd iteration of the Visual Question Answering Challenge (VQA v2.0). We further benchmark a number of state-of-art VQA models on our balanced dataset. All models perform significantly worse on our balanced dataset, suggesting that these models have indeed learned to exploit language priors. This finding provides the first concrete empirical evidence for what seems to be a qualitative sense among practitioners. Finally, our data collection protocol for identifying complementary images enables us to develop a novel interpretable model, which in addition to providing an answer to the given (image, question) pair also provides a counter-example based explanation - specifically, it identifies an image that is similar to the original image, but it believes has a different answer to the same question. This can help in building trust for machines among their users.
Recent progress in artificial intelligence (AI) has renewed interest in building systems that learn and think like people. Many advances have come from using deep neural networks trained end-to-end in tasks such as object recognition, video games, and board games, achieving performance that equals or even beats humans in some respects. Despite their biological inspiration and performance achievements, these systems differ from human intelligence in crucial ways. We review progress in cognitive science suggesting that truly human-like learning and thinking machines will have to reach beyond current engineering trends in both what they learn, and how they learn it. Specifically, we argue that these machines should (a) build causal models of the world that support explanation and understanding, rather than merely solving pattern recognition problems; (b) ground learning in intuitive theories of physics and psychology, to support and enrich the knowledge that is learned; and (c) harness compositionality and learning-to-learn to rapidly acquire and generalize knowledge to new tasks and situations. We suggest concrete challenges and promising routes towards these goals that can combine the strengths of recent neural network advances with more structured cognitive models.
A new graphical display is proposed for partitioning techniques. Each cluster is represented by a so-called silhouette, which is based on the comparison of its tightness and separation. This silhouette shows which objects lie well within their cluster, and which ones are merely somewhere in between clusters. The entire clustering is displayed by combining the silhouettes into a single plot, allowing an appreciation of the relative quality of the clusters and an overview of the data configuration. The average silhouette width provides an evaluation of clustering validity, and might be used to select an ‘appropriate’ number of clusters.
VQA is an ambitious task aiming to answer any image-related question. However, in reality, it is hard to build such a system once for all since the needs of users are continuously updated, and the system has to implement new functions. Thus, Continual Learning (CL) ability is a must in developing advanced VQA systems. Recently, a pioneer work split a VQA dataset into disjoint answer sets to study this topic. However, CL on VQA involves not only the expansion of label sets (new Answer sets). It is crucial to study how to answer questions when deploying VQA systems to new environments (new Visual scenes) and how to answer questions requiring new functions (new Question types). Thus, we propose CLOVE, a benchmark for Continual Learning On Visual quEstion answering, which contains scene- and function-incremental settings for the two aforementioned CL scenarios. In terms of methodology, the main difference between CL on VQA and classification is that the former additionally involves expanding and preventing forgetting of reasoning mechanisms, while the latter focusing on class representation. Thus, we propose a real-data-free replay-based method tailored for CL on VQA, named Scene Graph as Prompt for Symbolic Replay. Using a piece of scene graph as a prompt, it replays pseudo scene graphs to represent the past images, along with correlated QA pairs. A unified VQA model is also proposed to utilize the current and replayed data to enhance its QA ability. Finally, experimental results reveal challenges in CLOVE and demonstrate the effectiveness of our method. Code and data are available at https://github.com/showlab/CLVQA.
Composed Query Based Image Retrieval (
CQBIR
) aims at retrieving images relevant to a composed query containing a reference image with a requested modification expressed via a textual sentence. Compared with the conventional image retrieval which takes one modality as query to retrieve relevant data of another modality, CQBIR poses great challenge over the semantic gap between the reference image and modification text in the composed query. To solve the challenge, previous methods either resort to feature composition that cannot model interactions in the query or explore inter-modal attention while ignoring the spatial structure and visual-semantic relationship. In this paper, we propose a geometry sensitive cross-modal reasoning network for
CQBIR
by jointly modeling the geometric information of the image and the visual-semantic relationship between the reference image and modification text in the query. Specifically, it contains two key components: a geometry sensitive inter-modal attention module (GS-IMA) and a text-guided visual reasoning module (TG-VR). The GS-IMA introduces the spatial structure into the inter-modal attention in both implicit and explicit manners. The TG-VR models the unequal semantics not included in the reference image to guide further visual reasoning. As a result, our method can learn effective feature for the composed query which does not exhibit literal alignment. Comprehensive experimental results on three standard benchmarks demonstrate that the proposed model performs favorably against state-of-the-art methods.
Humans can learn in a continuous manner. Old rarely utilized knowledge can be overwritten by new incoming information while important, frequently used knowledge is prevented from being erased. In artificial learning systems, lifelong learning so far has focused mainly on accumulating knowledge over tasks and overcoming catastrophic forgetting. In this paper, we argue that, given the limited model capacity and the unlimited new information to be learned, knowledge has to be preserved or erased selectively. Inspired by neuroplasticity, we propose a novel approach for lifelong learning, coined Memory Aware Synapses (MAS). It computes the importance of the parameters of a neural network in an unsupervised and online manner. Given a new sample which is fed to the network, MAS accumulates an importance measure for each parameter of the network, based on how sensitive the predicted output function is to a change in this parameter. When learning a new task, changes to important parameters can then be penalized, effectively preventing important knowledge related to previous tasks from being overwritten. Further, we show an interesting connection between a local version of our method and Hebb’s rule, which is a model for the learning process in the brain. We test our method on a sequence of object recognition tasks and on the challenging problem of learning an embedding for predicting <subject, predicate, object> triplets. We show state-of-the-art performance and, for the first time, the ability to adapt the importance of the parameters based on unlabeled data towards what the network needs (not) to forget, which may vary depending on test conditions.
We present a new dataset with the goal of advancing the state-of-the-art in object recognition by placing the question of object recognition in the context of the broader question of scene understanding. This is achieved by gathering images of complex everyday scenes containing common objects in their natural context. Objects are labeled using per-instance segmentations to aid in understanding an object's precise 2D location. Our dataset contains photos of 91 objects types that would be easily recognizable by a 4 year old along with per-instance segmentation masks. With a total of 2.5 million labeled instances in 328k images, the creation of our dataset drew upon extensive crowd worker involvement via novel user interfaces for category detection, instance spotting and instance segmentation. We present a detailed statistical analysis of the dataset in comparison to PASCAL, ImageNet, and SUN. Finally, we provide baseline performance analysis for bounding box and segmentation detection results using a Deformable Parts Model.
Riemannian walk for incremental learning: Understanding forgetting and intransigence
- A Chaudhry
- P K Dokania
- T Ajanthan
- P H Torr
Dark experience for general continual learning: a strong, simple baseline
- P Buzzega
- M Boschini
- A Porrello
- D Abati
- S Calderara
Continual learning with tiny episodic memories
- A Chaudhry
- M Rohrbach
- M Elhoseiny
- T Ajanthan
- P Dokania
- P Torr
Measuring compositional generalization: A comprehensive method on realistic data
- D Keysers
- N Scharli
- N Scäles
- H Buisman
- D Furrer
- S Kashubin
- N Momchev
- D Sinopalnikov
- L Stafiniak
- T Tihon
Unifying vision-and-language tasks via text generation
- J Cho
- J Lei
- H Tan
- M Bansal
Efficient lifelong learning with a-gem
- A Chaudhry
- M Ranzato
- M Rohrbach
- M Elhoseiny