Whether what you see in Figure 1 is a "labrador" or a "dog", is the question we ask in this paper. While fine-grained visual classification (FGVC) strives to arrive at the former, for the majority of us non-experts just "dog" would probably suffice. The real question is therefore -- how can we tailor for different fine-grained definitions under divergent levels of expertise. For that, we re-envisage the traditional setting of FGVC, from single-label classification, to that of top-down traversal of a pre-defined coarse-to-fine label hierarchy -- so that our answer becomes "dog"-->"gun dog"-->"retriever"-->"labrador". To approach this new problem, we first conduct a comprehensive human study where we confirm that most participants prefer multi-granularity labels, regardless whether they consider themselves experts. We then discover the key intuition that: coarse-level label prediction exacerbates fine-grained feature learning, yet fine-level feature betters the learning of coarse-level classifier. This discovery enables us to design a very simple albeit surprisingly effective solution to our new problem, where we (i) leverage level-specific classification heads to disentangle coarse-level features with fine-grained ones, and (ii) allow finer-grained features to participate in coarser-grained label predictions, which in turn helps with better disentanglement. Experiments show that our method achieves superior performance in the new FGVC setting, and performs better than state-of-the-art on traditional single-label FGVC problem as well. Thanks to its simplicity, our method can be easily implemented on top of any existing FGVC frameworks and is parameter-free.
相關內容
The development of neural networks and pretraining techniques has spawned many sentence-level tagging systems that achieved superior performance on typical benchmarks. However, a relatively less discussed topic is what if more context information is introduced into current top-scoring tagging systems. Although several existing works have attempted to shift tagging systems from sentence-level to document-level, there is still no consensus conclusion about when and why it works, which limits the applicability of the larger-context approach in tagging tasks. In this paper, instead of pursuing a state-of-the-art tagging system by architectural exploration, we focus on investigating when and why the larger-context training, as a general strategy, can work. To this end, we conduct a thorough comparative study on four proposed aggregators for context information collecting and present an attribute-aided evaluation method to interpret the improvement brought by larger-context training. Experimentally, we set up a testbed based on four tagging tasks and thirteen datasets. Hopefully, our preliminary observations can deepen the understanding of larger-context training and enlighten more follow-up works on the use of contextual information.
Self-supervised clustering methods have achieved increasing accuracy in recent years but do not yet perform as well as supervised classification methods. This contrasts with the situation for feature learning, where self-supervised features have recently surpassed the performance of supervised features on several important tasks. We hypothesize that the performance gap is due to the difficulty of specifying, without supervision, which features correspond to class differences that are semantic to humans. To reduce the performance gap, we introduce the "single-noun" prior - which states that semantic clusters tend to correspond to concepts that humans label by a single-noun. By utilizing a pre-trained network that maps images and sentences into a common space, we impose this prior obtaining a constrained optimization task. We show that our formulation is a special case of the facility location problem, and introduce a simple-yet-effective approach for solving this optimization task at scale. We test our approach on several commonly reported image clustering datasets and obtain significant accuracy gains over the best existing approaches.
The explanation dimension of Artificial Intelligence (AI) based system has been a hot topic for the past years. Different communities have raised concerns about the increasing presence of AI in people's everyday tasks and how it can affect people's lives. There is a lot of research addressing the interpretability and transparency concepts of explainable AI (XAI), which are usually related to algorithms and Machine Learning (ML) models. But in decision-making scenarios, people need more awareness of how AI works and its outcomes to build a relationship with that system. Decision-makers usually need to justify their decision to others in different domains. If that decision is somehow based on or influenced by an AI-system outcome, the explanation about how the AI reached that result is key to building trust between AI and humans in decision-making scenarios. In this position paper, we discuss the role of XAI in decision-making scenarios, our vision of Decision-Making with AI-system in the loop, and explore one case from the literature about how XAI can impact people justifying their decisions, considering the importance of building the human-AI relationship for those scenarios.
Target-based sentiment analysis or aspect-based sentiment analysis (ABSA) refers to addressing various sentiment analysis tasks at a fine-grained level, which includes but is not limited to aspect extraction, aspect sentiment classification, and opinion extraction. There exist many solvers of the above individual subtasks or a combination of two subtasks, and they can work together to tell a complete story, i.e. the discussed aspect, the sentiment on it, and the cause of the sentiment. However, no previous ABSA research tried to provide a complete solution in one shot. In this paper, we introduce a new subtask under ABSA, named aspect sentiment triplet extraction (ASTE). Particularly, a solver of this task needs to extract triplets (What, How, Why) from the inputs, which show WHAT the targeted aspects are, HOW their sentiment polarities are and WHY they have such polarities (i.e. opinion reasons). For instance, one triplet from "Waiters are very friendly and the pasta is simply average" could be ('Waiters', positive, 'friendly'). We propose a two-stage framework to address this task. The first stage predicts what, how and why in a unified model, and then the second stage pairs up the predicted what (how) and why from the first stage to output triplets. In the experiments, our framework has set a benchmark performance in this novel triplet extraction task. Meanwhile, it outperforms a few strong baselines adapted from state-of-the-art related methods.
While the general task of textual sentiment classification has been widely studied, much less research looks specifically at sentiment between a specified source and target. To tackle this problem, we experimented with a state-of-the-art relation extraction model. Surprisingly, we found that despite reasonable performance, the model's attention was often systematically misaligned with the words that contribute to sentiment. Thus, we directly trained the model's attention with human rationales and improved our model performance by a robust 4~8 points on all tasks we defined on our data sets. We also present a rigorous analysis of the model's attention, both trained and untrained, using novel and intuitive metrics. Our results show that untrained attention does not provide faithful explanations; however, trained attention with concisely annotated human rationales not only increases performance, but also brings faithful explanations. Encouragingly, a small amount of annotated human rationales suffice to correct the attention in our task.
When we are faced with challenging image classification tasks, we often explain our reasoning by dissecting the image, and pointing out prototypical aspects of one class or another. The mounting evidence for each of the classes helps us make our final decision. In this work, we introduce a deep network architecture that reasons in a similar way: the network dissects the image by finding prototypical parts, and combines evidence from the prototypes to make a final classification. The model thus reasons in a way that is qualitatively similar to the way ornithologists, physicians, geologists, architects, and others would explain to people on how to solve challenging image classification tasks. The network uses only image-level labels for training, meaning that there are no labels for parts of images. We demonstrate our method on the CUB-200-2011 dataset and the CBIS-DDSM dataset. Our experiments show that our interpretable network can achieve comparable accuracy with its analogous standard non-interpretable counterpart as well as other interpretable deep models.
Object detectors tend to perform poorly in new or open domains, and require exhaustive yet costly annotations from fully labeled datasets. We aim at benefiting from several datasets with different categories but without additional labelling, not only to increase the number of categories detected, but also to take advantage from transfer learning and to enhance domain independence. Our dataset merging procedure starts with training several initial Faster R-CNN on the different datasets while considering the complementary datasets' images for domain adaptation. Similarly to self-training methods, the predictions of these initial detectors mitigate the missing annotations on the complementary datasets. The final OMNIA Faster R-CNN is trained with all categories on the union of the datasets enriched by predictions. The joint training handles unsafe targets with a new classification loss called SoftSig in a softly supervised way. Experimental results show that in the case of fashion detection for images in the wild, merging Modanet with COCO increases the final performance from 45.5% to 57.4%. Applying our soft distillation to the task of detection with domain shift on Cityscapes enables to beat the state-of-the-art by 5.3 points. We hope that our methodology could unlock object detection for real-world applications without immense datasets.
A popular recent approach to answering open-domain questions is to first search for question-related passages and then apply reading comprehension models to extract answers. Existing methods usually extract answers from single passages independently. But some questions require a combination of evidence from across different sources to answer correctly. In this paper, we propose two models which make use of multiple passages to generate their answers. Both use an answer-reranking approach which reorders the answer candidates generated by an existing state-of-the-art QA model. We propose two methods, namely, strength-based re-ranking and coverage-based re-ranking, to make use of the aggregated evidence from different passages to better determine the answer. Our models have achieved state-of-the-art results on three public open-domain QA datasets: Quasar-T, SearchQA and the open-domain version of TriviaQA, with about 8 percentage points of improvement over the former two datasets.
Fine-grained image classification is to recognize hundreds of subcategories belonging to the same basic-level category, which is a highly challenging task due to the quite subtle visual distinctions among similar subcategories. Most existing methods generally learn part detectors to discover discriminative regions for better performance. However, not all localized parts are beneficial and indispensable for classification, and the setting for number of part detectors relies heavily on prior knowledge as well as experimental results. As is known to all, when we describe the object of an image into text via natural language, we only focus on the pivotal characteristics, and rarely pay attention to common characteristics as well as the background areas. This is an involuntary transfer from human visual attention to textual attention, which leads to the fact that textual attention tells us how many and which parts are discriminative and significant. So textual attention of natural language descriptions could help us to discover visual attention in image. Inspired by this, we propose a visual-textual attention driven fine-grained representation learning (VTA) approach, and its main contributions are: (1) Fine-grained visual-textual pattern mining devotes to discovering discriminative visual-textual pairwise information for boosting classification through jointly modeling vision and text with generative adversarial networks (GANs), which automatically and adaptively discovers discriminative parts. (2) Visual-textual representation learning jointly combine visual and textual information, which preserves the intra-modality and inter-modality information to generate complementary fine-grained representation, and further improve classification performance. Experiments on the two widely-used datasets demonstrate the effectiveness of our VTA approach, which achieves the best classification accuracy.
Most existing works in visual question answering (VQA) are dedicated to improving the accuracy of predicted answers, while disregarding the explanations. We argue that the explanation for an answer is of the same or even more importance compared with the answer itself, since it makes the question and answering process more understandable and traceable. To this end, we propose a new task of VQA-E (VQA with Explanation), where the computational models are required to generate an explanation with the predicted answer. We first construct a new dataset, and then frame the VQA-E problem in a multi-task learning architecture. Our VQA-E dataset is automatically derived from the VQA v2 dataset by intelligently exploiting the available captions. We have conducted a user study to validate the quality of explanations synthesized by our method. We quantitatively show that the additional supervision from explanations can not only produce insightful textual sentences to justify the answers, but also improve the performance of answer prediction. Our model outperforms the state-of-the-art methods by a clear margin on the VQA v2 dataset.
小貼士
登錄享
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191